Product portrait storage method and device, electronic equipment and computer readable medium

Abstract

The embodiment of the invention discloses a product portrait storage method and device, electronic equipment and a computer readable medium. A specific embodiment of the method comprises the steps of obtaining user value transfer data from a user database; determining at least one piece of user group information and a user value attribute information set according to the user value transfer data; generating a value numerical value; in response to the fact that the value value is greater than the target value, encrypting the value value and the information of the at least one user group to generate an initial encryption result; sending the initial encryption result to a multi-layer auditing terminal for auditing the value value; in response to the received audit qualification information, generating a product value use portrait corresponding to the target user; and carrying out portrait encryption storage on the product value use portrait. According to the embodiment, the user information security is effectively guaranteed through multiple times of encryption. In addition, the use portrait related to the product use and corresponding to the target user can be accurately generated.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a product image storage method, device, electronic device, and computer-readable medium. Background Art

[0002] At present, with the continuous development of virtual value products, it is very important to accurately determine the product usage profile of virtual value products, which can effectively screen out users who are eligible to use virtual value products. The method usually adopted for generating product usage profiles is: relevant technical personnel manually judge the user history data of each user to determine the product usage profile of the user using the virtual value product.

[0003] However, when using the above method to generate product usage portraits, the following technical problems often occur:

[0004] The process of manually determining product usage profiles carries the risk of leaking user privacy information, and the uncertainty factor of human judgment is large, resulting in the generated product usage profiles being inaccurate. In addition, product usage profiles often waste a lot of storage resources.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0006] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0007] Some embodiments of the present disclosure propose product portrait storage methods, devices, electronic devices and computer-readable media to solve one or more of the technical problems mentioned in the above background technology section.

[0008] In a first aspect, some embodiments of the present disclosure provide a product portrait storage method, including: obtaining user value flow data corresponding to a target user from a user database; determining at least one user group information and a user value attribute information set corresponding to the target user based on the user value flow data; generating a value value corresponding to the target user that can be provided by a target virtual value product based on the at least one user group information and the user value attribute information set; in response to monitoring that the value value is greater than the target value, encoding and encrypting the value value and the at least one user group information to generate an initial encryption result; sending the initial encryption result to a multi-layer audit terminal to audit the value value; in response to receiving audit qualification information indicating that the audit has passed, generating a product value usage portrait corresponding to the target user based on the value value, the at least one user group information and the user value attribute information set; and encrypting and storing the product value usage portrait on the target blockchain.

[0009] In a second aspect, some embodiments of the present disclosure provide a product portrait storage device, including: an acquisition unit, configured to acquire user value flow data corresponding to a target user from a user database; a determination unit, configured to determine at least one user group information and a user value attribute information set corresponding to the target user based on the user value flow data; a first generation unit, configured to generate a value value corresponding to the target user that can be provided by a target virtual value product based on the at least one user group information and the user value attribute information set; an encryption unit, configured to encode and encrypt the value value and the at least one user group information in response to monitoring that the value value is greater than the target value to generate an initial encryption result; a sending unit, configured to send the initial encryption result to a multi-layer audit terminal to audit the value value; a second generation unit, configured to generate a product value usage portrait corresponding to the target user based on the value value, the at least one user group information and the user value attribute information set in response to receiving audit qualification information representing the passing of the audit; and a storage unit, configured to encrypt and store the product value usage portrait on the target blockchain.

[0010] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner in the first aspect.

[0011] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner in the first aspect is implemented.

[0012] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the product portrait storage method of some embodiments of the present disclosure, user information security is effectively guaranteed through multiple encryption. In addition, the use portraits corresponding to the target user and related to the use of the product can also be accurately generated. Specifically, the reason why the generation process of the relevant use portraits is leaked and inaccurate is that there is a risk of leakage of user personal privacy information in the process of manually determining the product use portrait, and the uncertainty factor of human judgment is large, resulting in the generated product use portraits being inaccurate. In addition, product use portraits often waste a lot of storage resources. Based on this, the product portrait storage method of some embodiments of the present disclosure first obtains the user value flow data corresponding to the target user from the user database, so as to determine the subsequent user group information and the user value attribute information based on the user value flow data. Then, according to the above-mentioned user value flow data, at least one user group information and a user value attribute information set corresponding to the above-mentioned target user can be accurately determined. Here, by determining at least one user group information, the value value is subsequently determined from the perspective of the user group. By determining the user value attribute information set, the value value is subsequently determined from the perspective of the user value attribute. Then, according to the at least one user group information and the user value attribute information set, the value value that can be provided by the target virtual value product corresponding to the target user can be accurately generated in many aspects. Then, in response to monitoring that the value value is greater than the target value, the value value and the at least one user group information are encrypted to generate an initial encryption result. Here, by encoding and encrypting the value value and the at least one user group information, the risk of information leakage in the subsequent process of sending to the audit terminal is guaranteed. At the same time, by encoding and encrypting, the transmission volume of data transmission can be reduced, the transmission efficiency is improved, the transmission time is saved, and too many transmission resources are avoided. Then, the initial encryption result is sent to the multi-layer audit terminal for the audit of the value value. Here, by sending it to the multi-layer audit terminal, the accuracy of the result content in the initial encryption result is ensured without information leakage. Then, in response to receiving the audit qualification information representing the audit passing, according to the value value, the at least one user group information and the user value attribute information set, the product value use portrait corresponding to the target user can be accurately generated. Here, the product value use portrait can be a use portrait with pictures and texts. By adding pictures, it is possible to effectively identify whether the person who subsequently requests to use the virtual value product is the person himself, while also avoiding information leakage in the subsequent request process. Finally, the above product value usage portrait is encrypted and stored on the target blockchain to avoid the leakage of the product usage portrait, facilitate subsequent use, and avoid waste of storage resources.In summary, through multiple encryption processing, generating product value usage portraits from the perspective of user groups and user value attributes and encrypting and storing them on the target area chain, not only can the product value usage portraits be accurately generated, the waste of data transmission resources can be reduced, and transmission efficiency can be improved, but also user information leakage during the generation and use processes can be avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0014] Figure 1 is a flow chart of some embodiments of the product portrait storage method according to the present disclosure;

[0015] Figure 2 is a schematic diagram of the structure of some embodiments of the product image storage device according to the present disclosure;

[0016] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0018] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0019] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0020] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0021] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0022] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0023] refer to Figure 1 , shows a process 100 of some embodiments of the product image storage method according to the present disclosure. The product image storage method includes the following steps:

[0024] Step 101: Obtain user value flow data corresponding to the target user from the user database.

[0025] In some embodiments, in response to receiving session communication request information for the first user terminal and the second user terminal, the execution subject (e.g., electronic device) of the above-mentioned product portrait storage method can obtain the user value flow data corresponding to the target user from the user database. Among them, the user database can be a database storing various data related to the user. The various data related to the user can be a value processing data set stored after the user performs various value processing operations. For example, the value processing operation can be one of the following: value flow operation, value storage operation, value borrowing operation. In practice, for the credit investigation field, the corresponding value flow operation can be a credit operation in the target virtual value product. The target virtual value product can be a pre-set virtual product related to the value operation. For example, for the credit investigation scenario, the target virtual value product can be a credit product. The target user can be a user of the product portrait to be determined. The product portrait can characterize various possible usage characteristics of the target user using the product portrait. In practice, the product portrait can include: at least one user group information related to the target user, a user value attribute information set, a value value, and user information. The user group information can be group information of the user group. For example, the group information can be a group identifier. At least one user group can be a user group whose corresponding group characteristics are similar to the user characteristics corresponding to the target user. That is, the target user is part of at least one user group. For example, the user group may be a group with a high amount of credit. The corresponding target user may also be a group with a high amount of credit. User value attribute information may be attribute information related to the user value transfer operation. Attribute information may be attribute content. In practice, for user value transfer operations, the corresponding attribute may be one of the following: deposit amount, usage time, loan amount, loan time, repayment amount, and repayment time. The value value may be the value of the value information that the target virtual value product can provide to the target user. In practice, for the credit investigation field, the corresponding value value may be the loan amount, the repayment amount, the loan time, or the repayment time. User information may be the basic personal information of the target user. For example, user information may include but is not limited to at least one of the following: user name, user ID, user gender, user age, and user residence.

[0026] Step 102: Determine at least one user group information and user value attribute information set corresponding to the target user based on the user value transfer data.

[0027] In some embodiments, the execution entity may determine at least one user group information and a user value attribute information set corresponding to the target user based on the user value transfer data.

[0028] As an example, first, the execution subject may determine at least one user with the most similar flow data to the target user based on the user value flow data, as at least one similar user information. Then, determine the user group to which the at least one similar user belongs, and obtain at least one user group information. Next, determine the user group attribute set corresponding to the at least one user group information. Finally, extract the user value attribute information set corresponding to the user group attribute set from the user value flow data.

[0029] In some optional implementations of some embodiments, the execution subject may determine at least one user group information and a user value attribute information set corresponding to the target user according to the user value flow data, including the following steps:

[0030] In the first step, a user group characteristic information group corresponding to each user group identifier in the user group identifier set is obtained from the user group database to obtain a user group characteristic information group set. Each user group characteristic information in the user group characteristic information group has corresponding encrypted first user group value attribute information. The user group database may be a database storing group data related to the user group. The user group identifier may represent the identity information of the user group. For example, the user group identifier may be "0087". There is a one-to-one correspondence between the user group characteristic information in the user group characteristic information group and the user group value attribute in the user group value attribute group. The user group value attribute may represent the group significant characteristics of the user group. The user group value attribute may be an attribute highlighted by the user group in terms of value. For example, for the user group A, the corresponding user group value attribute may be but not limited to one of the following: user high consumption characteristics, user high loan amount characteristics, user high income characteristics. The user group characteristic information group may include at least one user group characteristic information. The corresponding user group characteristic groups between the user groups may be different. The user group characteristic information may be feature information in vector form, representing the content of each attribute under the corresponding user group. Here, by encrypting the first user group value attribute information, it is possible to effectively ensure that the user group value attribute information can be traced through the user group characteristic information, thereby avoiding leakage of the user group privacy.

[0031] The second step is to extract the user group value attribute information corresponding to each user group value attribute from the above user value circulation data. There is a one-to-one correspondence between the user group value attribute in each user group value attribute and the user group value attribute information in each user group value attribute information. The user group value attribute information can be the attribute content corresponding to the user group value attribute.

[0032] The third step is to send the above-mentioned value attribute information of each user group to the attribute information encryption terminal to generate encrypted value attribute information of each second user group. Among them, the attribute information encryption terminal can be a terminal that encrypts the attribute information. There is a one-to-one correspondence between the encrypted second user group value attribute information in each second user group value attribute information and the user group value attribute information in each user group value attribute information. In practice, the attribute information encryption terminal can be a terminal that deploys a pre-set encryption algorithm.

[0033] Here, by using an independent encryption terminal (i.e., attribute information encryption terminal) to encrypt the user group value attribute information, the information security of the user group value attribute information can be effectively guaranteed, avoiding the single-end attribute information generation and single-end attribute information encryption, which leads to information leakage when executing each step on a single end.

[0034] The fourth step is to vectorize the encrypted value attribute information of each second user group to generate a target user group characteristic information group.

[0035] As an example, the execution subject may input the encrypted value attribute information of each second user group into a vector conversion model to generate a target user group characteristic information group. The target user group characteristic information may be characteristic information in vector form.

[0036] The fifth step is to determine the value attribute similarity information between each user group characteristic information group in the above user group characteristic information group set and the above target user group characteristic information group, and obtain the value attribute similarity information set. The value attribute similarity information can be a value between 0 and 1. The larger the value attribute similarity information, the higher the similarity between the corresponding and target user group characteristic information. The value attribute similarity information can be cosine similarity.

[0037] Step 6: Filter out user group characteristic information groups whose value attribute similarity information is higher than the target similarity information from the above-mentioned user group characteristic information groups, and obtain at least one user group characteristic information group. The target similarity information may be pre-set similarity information. For example, the target similarity information may be debugged by relevant experts and technicians based on experience. The target similarity information may be a value between 0 and 1.

[0038] In the seventh step, each user group identifier corresponding to the at least one user group characteristic information group is determined as at least one user group information.

[0039] Step 8: Obtain the user value attribute set corresponding to the above user value risk information. Among them, each user value attribute in the user value attribute set may be a value attribute used to subsequently generate user value risk information. User value risk information may be the size of the risk corresponding to various value operations performed by the user. For example, if the user value operation is a loan operation, the corresponding user value risk information may be loan risk assessment information. Each user value attribute in the corresponding user value attribute set may be a value attribute related to generating loan risk assessment information.

[0040] The ninth step is to extract the user value attribute information set corresponding to the user value attribute set from the above user value flow data. Among them, there is a one-to-one correspondence between the user value attribute in the user value attribute set and the user value attribute information in the user value attribute information set. The user value attribute information can be the attribute content corresponding to the user value attribute.

[0041] Step 103: Generate a value representing the value that can be provided by the target virtual value product corresponding to the target user according to the at least one user group information and the user value attribute information set.

[0042] In some embodiments, the execution subject may generate a value value representing the value that the target virtual value product can provide, corresponding to the target user, based on the at least one user group information and the user value attribute information set.

[0043] In some optional implementations of some embodiments, the execution subject may generate a value value representing the value that the target virtual value product can provide for the target user according to the at least one user group information and the user value attribute information set, including the following steps:

[0044] The first step is to determine at least one first value adjustment information corresponding to the at least one user group information. Among them, there is a one-to-one correspondence between the user group information in the at least one user group information and the first value adjustment information in the at least one first value adjustment information. The first value adjustment information can be adjustment information for numerically adjusting the initial value value corresponding to the user. The initial value value can be the basic value value that the target virtual value product can provide to each user. The initial value value can be the basic value size of the value information that the target virtual value product can provide to the target user. In practice, in the field of credit reporting, the corresponding initial value value can be the basic loan amount, the basic repayment amount, the basic loan period, or the basic repayment period.

[0045] The second step is to generate the user value risk information corresponding to the target user according to the user value attribute information set. The user value risk information may be the risk level of the user in value transfer operations. The user value risk information may be information in numerical form. The higher the numerical value of the user value risk information, the greater the risk of the user in value transfer operations.

[0046] As an example, the execution subject may directly input each user value attribute information in the user value attribute information set into a pre-trained user value risk information generation model to generate user value risk information. In practice, the user value risk information generation model may be a time series neural network model. For example, the user value risk information generation model may be a recurrent neural network model.

[0047] The third step is to generate the second value adjustment information corresponding to the user value risk information, wherein the second value adjustment information may be adjustment information for adjusting the initial value corresponding to the user.

[0048] As an example, the execution entity may determine the second value adjustment information corresponding to the user value risk information by querying an association table.

[0049] The fourth step is to determine the initial value corresponding to the above target users.

[0050] As an example, the execution entity may determine the basic value corresponding to each user as the initial value, that is, each user has the same corresponding value.

[0051] The fifth step is to adjust the initial value value according to the at least one first value adjustment information and the second value adjustment information to generate the value value.

[0052] As an example, the execution entity may add at least one first value adjustment information, the second value adjustment information, and the initial value value to generate a value value.

[0053] In some optional implementations of some embodiments, the first value adjustment information in the at least one first value adjustment information is generated by the following steps:

[0054] The first step is to obtain the user group information corresponding to the first value adjustment information as the target user group information.

[0055] The second step is to determine the user group characteristic information group corresponding to the above target user group information as the target user group characteristic information group.

[0056] As an example, the execution subject may determine the user group characteristic information group corresponding to the target user group information by means of characteristic information query as the target user group characteristic information group.

[0057] The third step is to determine the attribute importance information corresponding to each user group attribute in the user group attribute set. There is a one-to-one correspondence between the user group attributes in the user group attribute set and the target user group characteristic information in the target user group characteristic information group. That is, the target user group characteristic information may be the attribute content corresponding to the user group attribute. The attribute importance information may represent the importance of the attribute content corresponding to the user group attribute. The attribute importance information may be a value between 0 and 1. The higher the value, the higher the importance of the corresponding attribute content.

[0058] In the fourth step, according to the attribute importance information corresponding to the user group attributes, attribute intervals are divided for each user group attribute in the above user group attribute set to obtain a user group attribute group set. The above user group attribute group set includes: a first user group attribute group, a second user group attribute group and a third user group attribute group. The importance of each user group attribute corresponding to the first user group attribute group is higher than the importance of each user group attribute corresponding to the second user group attribute group. The importance of each user group attribute corresponding to the second user group attribute group is higher than the importance of each user group attribute corresponding to the third user group attribute group. Each attribute interval may be a pre-set attribute value interval.

[0059] Step 5: determine the currently available computing resources corresponding to the value adjustment information generating terminal. The value adjustment information generating terminal may be a terminal that generates value adjustment information. That is, the first value adjustment information corresponding to the user group information may be updated and generated in the value adjustment information generating terminal. The currently available computing resources may be computing resources that can be used by the current value adjustment information generating terminal.

[0060] As an example, the above-mentioned execution subject can determine the currently available computing resources corresponding to the value adjustment information generation terminal through a computing resource query instruction.

[0061] The sixth step is to determine the user group attribute extraction ratios corresponding to the first user group attribute group, the second user group attribute group, and the third user group attribute group based on the currently available computing resources. There is a correlation between the currently available computing resources and the user group attribute extraction ratio. The user group attribute extraction ratio may be the ratio of the number of attributes extracted from the first user group attribute group, the second user group attribute group, and the third user group attribute group. For example, the user group attribute extraction ratio may be {5:4:2}. Then, 5 first user group attributes are extracted from the first user group attribute group, 4 second user group attributes are extracted from the second user group attribute group, and 2 third user group attributes are extracted from the third user group attribute group.

[0062] As an example, the execution subject may extract the user group attribute extraction ratio corresponding to the currently available computing resources from the resource and extraction ratio association table, wherein the resource and extraction ratio association table may represent the correspondence between the available computing resources corresponding to the value adjustment information generating terminal and the user group attribute extraction ratio.

[0063] In the seventh step, according to the user group attribute extraction ratio, group attributes are extracted from the first user group attribute group, the second user group attribute group and the third user group attribute group to generate an extracted group attribute group.

[0064] Step 8: extracting a user group characteristic information subgroup corresponding to the extracted group attribute group from the target user group characteristic information group, wherein there is a one-to-one correspondence between the extracted group attributes in the extracted group attribute group and the user group characteristic information in the user group characteristic information subgroup.

[0065] In the ninth step, the user group characteristic information subgroup is input into a pre-trained value adjustment information generation model to generate the first value adjustment information. The value adjustment information generation model may be a neural network model for generating value adjustment information. In practice, the value adjustment information generation model may be a multi-input multi-layer serial convolutional network. In practice, the multi-layer serial convolutional network may be an 11-layer serial convolutional network. The value adjustment information generation model may be obtained by conventional model training methods.

[0066] Step 104, in response to monitoring that the value value is greater than the target value, encrypting the value value and the at least one user group information to generate an initial encryption result.

[0067] In some embodiments, in response to monitoring that the value value is greater than a target value, the execution subject may encrypt the value value and the at least one user group information to generate an initial encryption result, wherein the target value may be a preset number.

[0068] As an example, first, the execution subject may obtain the encryption algorithm sent by the target terminal, and then encrypt the value and the at least one user group information using the encryption algorithm to generate an initial encryption result.

[0069] Step 105, sending the above initial encryption result to the multi-layer audit terminal to audit the above value value.

[0070] In some embodiments, the execution subject may send the initial encryption result to a multi-layer audit terminal to audit the value, wherein the multi-layer audit terminal may be a terminal for auditing the content corresponding to the initial encryption result at multiple levels.

[0071] Step 106, in response to receiving the audit qualification information indicating that the audit has passed, generating a product value usage portrait corresponding to the target user according to the value value, the at least one user group information and the user value attribute information set.

[0072] In some embodiments, in response to receiving audit qualification information indicating that the audit has passed, the execution entity may generate a product value usage portrait corresponding to the target user based on the value value, the at least one user group information and the user value attribute information set.

[0073] Step 107, encrypt and store the above product value using the portrait.

[0074] In some embodiments, the execution entity may encrypt and store the product value usage portrait.

[0075] In some optional implementations of some embodiments, after step 107, the steps further include:

[0076] The first step is to, in response to receiving information indicating that the target user requests value provision from the target virtual value product, obtain the encrypted portrait corresponding to the target user according to the user information corresponding to the target user and decrypt it to generate the product value usage portrait.

[0077] The second step is to use the user image included in the product value use image to determine the user authenticity information corresponding to the target user. The user image can be a real personal image pre-stored by the target user. For example, the user image can be an ID card image.

[0078] In the third step, in response to determining that the user authenticity information indicates that the target user is a real individual user, a value value is extracted from the product value usage portrait.

[0079] The fourth step is to generate the value value reasons corresponding to the target users based on the above product value usage portrait. The value value reasons can be the corresponding generation reasons of the value values.

[0080] As an example, the above-mentioned execution entity can use the Bert model to generate the value numerical reasons corresponding to the target users according to the above-mentioned product value usage portrait.

[0081] Step 5: Determine the value processing operation information corresponding to the above value value. Different value values ​​correspond to different value processing operations. The value processing operation information can be an operation identifier corresponding to the value processing operation.

[0082] The sixth step is to send the value processing operation information and the value numerical reason to the request terminal corresponding to the target user, so that the request terminal can perform the corresponding value processing operation and display the corresponding value processing value numerical reason.

[0083] In some optional implementations of some embodiments, the execution subject may generate user value risk information corresponding to the target user according to the user value attribute information set, including the following steps:

[0084] In the first step, each user value attribute information in the above user value attribute information set is encrypted to generate a user value attribute encrypted information set. The encrypted user value attribute information in the user value attribute encrypted information set has a one-to-one correspondence with the user value attribute information in the user value attribute encrypted information set. The encryption method may be a method of performing encryption processing based on a predetermined encryption algorithm.

[0085] In the second step, the encrypted information set of the user value attribute is sent to the user value risk information generating terminal, so that the user value risk information generating terminal can generate the user value risk information using the graphics processor group set. The user value risk information generating terminal can be a terminal that generates user value risk information. The user value risk information can be the size of the risk of the user's own value operation. In practice, the user value risk information can be information of numerical type. The larger the numerical value, the greater the risk of the corresponding user's value operation.

[0086] And using the above-mentioned graphics processor group set, the above-mentioned user value risk information is generated through the following steps:

[0087] Sub-step 1, divide each user value attribute information in the above user value attribute information set to generate a first user value attribute information subset for generating user credit information, a second user value attribute information subset for generating user value risk information, a third user value attribute information subset for generating product usage credit information, and a fourth user value attribute information subset for generating product usage risk information. Among them, the first user value attribute information subset is an attribute information set for subsequently generating a user credit value. The user credit value can represent the user's credit level. Product usage credit information can be the credit size of the user using the target product. Product usage risk information can be the risk size of the user using the target product.

[0088] Sub-step 2: Input the first user value attribute information subset into the user credit generation model deployed by the pre-trained first image processor group to generate the first user credit information. In practice, the user credit generation model can be a neural network model for generating user credit. For example, the user credit generation model can be a time series neural network model.

[0089] Sub-step 3, input the above-mentioned first user value attribute information subset and the above-mentioned second user value attribute information subset into the first dual-tower model deployed by the pre-trained second image processor group to generate the second user credit information and the first user value risk information. The first dual-tower model can be a dual-tower model used to output user credit and user value risk. For example, the first dual-tower model can be a dual-tower model obtained by splicing multiple time series neural network models. For example, the first dual-tower model includes: a first time series neural network model, a second time series neural network model, a fusion model, a first output layer and a second output layer. The first time series neural network model is a model for extracting user credit features. The second time series neural network model is a model for extracting user value risk features. The fusion model is a model that fuses the corresponding outputs of the first time series neural network model and the second time series neural network model. The first output layer and the second output layer can be fully connected layers that output user credit and user value risk features respectively.

[0090] Sub-step 4, inputting the second user value attribute information subset into the user value risk information generation model deployed by the pre-trained third image processor group to generate second user value risk information. The user value risk information generation model can be a neural network model for generating user value risk information. In practice, the user value risk information generation model can be a regression model. For example, the user value risk information generation model can be a regression model based on a Transformer model.

[0091] Sub-step 5: Input the third user value attribute information subset into the pre-trained product usage credit information generation model deployed by the fourth image processor group to generate the first product usage credit information. The product usage credit information generation model can be a neural network model for generating product usage credit information. In practice, the product usage credit information generation model can be a regression model based on the BERT model.

[0092] Sub-step 6: Input the third user value attribute information subset and the fourth user value attribute information subset into the second dual-tower model deployed by the pre-trained fifth image processor group to generate the second product use credit information and the first product use risk information. The second dual-tower model can refer to the model structure corresponding to the first dual-tower model.

[0093] Sub-step 7, inputting the fourth user value attribute information subset into the pre-trained product use risk information generation model deployed by the sixth image processor group to generate second product use risk information. The product use risk information generation model may be a neural network model for generating product use risk information. In practice, the product use risk information generation model may be a classification model. For example, the product use risk information generation model may be a multi-layer series of convolutional layers.

[0094] Sub-step 8: generating first initial user value risk information based on the first user credit information, the second user credit information, the first user value risk information and the second user value risk information.

[0095] As an example, the execution entity may perform weighted sum processing on the first user credit information, the second user credit information, the first user value risk information, and the second user value risk information to generate the first initial user value risk information. The weights corresponding to the first user credit information and the second user credit information are negative numbers. The larger the credit value, the smaller the corresponding value risk information.

[0096] Sub-step 9, generating second initial user value risk information based on the first product usage credit information, the second product usage credit information, the first product usage risk information and the second product usage risk information.

[0097] As an example, the execution entity may perform weighted sum processing on the credit information of the first product, the credit information of the second product, the risk information of the first product, and the risk information of the second product to generate the second initial user value risk information. The weights corresponding to the credit information of the first product and the credit information of the second product are negative numbers. The larger the credit value, the smaller the corresponding value risk information.

[0098] Sub-step 10: generating the user value risk information according to the first initial user value risk information and the second initial user value risk information.

[0099] As an example, the execution entity may determine an average value between the first initial user value risk information and the second initial user value risk information as the user value risk information.

[0100] Optionally, the execution subject may input the first user value attribute information subset and the second user value attribute information subset into a first dual-tower model deployed by a pre-trained second image processor group to generate second user credit information and first user value risk information, including the following steps:

[0101] In the first step, the first user value attribute information subset is input into the first user value attribute extraction layer included in the first dual-tower model to generate first user value attribute feature information. The first user value attribute extraction layer may be a network layer for extracting user value attribute feature information. For example, the first user value attribute extraction layer may be an encoding layer in a Transformer model.

[0102] The second step is to input the second user value attribute information subset into the second user value attribute extraction layer included in the first dual-tower model to generate second user value attribute feature information. The network structure corresponding to the second user value attribute extraction layer can be the same as the network structure of the first user value attribute extraction layer.

[0103] In the third step, the first user value attribute feature information and the second user value attribute feature information are input into the first difference information extraction layer included in the first dual-tower model to generate first feature difference information. The first difference information extraction layer may be a network layer for extracting the feature semantic content difference between the first user value attribute feature information and the second user value attribute feature information. For example, the first difference information extraction layer may be an attention layer based on a convolutional network. The first feature difference information may characterize the difference in feature semantic content between the first user value attribute feature information and the second user value attribute feature information.

[0104] The fourth step is to input the first user value attribute characteristic information and the second user value attribute characteristic information into the second difference information extraction layer included in the first double-tower model to generate second characteristic difference information.

[0105] The fifth step is to set the first feature weight information between the first feature difference information and the first user value attribute feature information, wherein the first feature weight information can represent the feature importance of the first feature difference information and the first user value attribute feature information.

[0106] Step 6: Set the second feature weight information between the second feature difference information and the second user value attribute feature information. The first feature weight information can represent the feature importance of the second feature difference information and the second user value attribute feature information.

[0107] In the seventh step, the first feature weight information, the first user value attribute feature information and the first feature difference information are input into the user credit information generation layer to generate the second user credit information. The user credit information generation layer may be a fully connected layer for generating user credit information.

[0108] In the eighth step, the second feature weight information, the second user value attribute feature information and the second feature difference information are input into the user value risk generation layer to generate the first user value risk information. The user value risk generation layer may be a fully connected layer for generating user value risk information.

[0109] Optionally, as one of the invention points, the problem of insufficiently comprehensive and accurate generation of user credit information and user value risk information is solved. Based on this, through the various network layers included in the first dual-tower model, more feature content can be considered to accurately generate the second user credit information and the first user value risk information.

[0110] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the product portrait storage method of some embodiments of the present disclosure, user information security is effectively guaranteed through multiple encryption. In addition, the use portraits corresponding to the target user and related to the use of the product can also be accurately generated. Specifically, the reason why the generation process of the relevant use portraits is leaked and not accurate enough is that the process of manually determining the product use portraits has the risk of leaking the user's personal privacy information, and the uncertainty factor of human judgment is large, resulting in the generated product use portraits not being accurate enough. Based on this, the product portrait storage method of some embodiments of the present disclosure first obtains the user value flow data corresponding to the target user from the user database, so as to determine the subsequent user group information and the user value attribute information based on the user value flow data. Then, according to the above-mentioned user value flow data, at least one user group information and a user value attribute information set corresponding to the above-mentioned target user can be accurately determined. Here, by determining at least one user group information, the value value is subsequently determined from the perspective of the user group. By determining the user value attribute information set, the value value is subsequently determined from the perspective of the user value attribute. Then, according to the at least one user group information and the user value attribute information set, the value value that can be provided by the target virtual value product corresponding to the target user can be accurately generated in many aspects. Then, in response to monitoring that the value value is greater than the target value, the value value and the at least one user group information are encrypted to generate an initial encryption result. Here, by encoding and encrypting the value value and the at least one user group information, the risk of information leakage in the subsequent process of sending to the audit terminal is guaranteed. At the same time, by encoding and encrypting, the transmission volume of data transmission can be reduced, the transmission efficiency is improved, the transmission time is saved, and too many transmission resources are avoided. Then, the initial encryption result is sent to the multi-layer audit terminal for the audit of the value value. Here, by sending it to the multi-layer audit terminal, the accuracy of the result content in the initial encryption result is ensured without information leakage. Then, in response to receiving the audit qualification information representing the audit passing, according to the value value, the at least one user group information and the user value attribute information set, the product value use portrait corresponding to the target user can be accurately generated. Here, the product value use portrait can be a use portrait with pictures and texts. By adding pictures, it is possible to effectively identify whether the person who subsequently requests to use the virtual value product is the person himself, while also avoiding information leakage in the subsequent request process. Finally, the above product value usage portrait is encrypted and stored on the target blockchain to avoid the leakage of the product usage portrait and facilitate subsequent use.In summary, through multiple encryption processing, generating product value usage portraits from the perspective of user groups and user value attributes and encrypting and storing them on the target area chain, not only can the product value usage portraits be accurately generated, the waste of data transmission resources can be reduced, and transmission efficiency can be improved, but also user information leakage during the generation and use processes can be avoided.

[0111] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a product image storage device. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the product image storage device can be specifically applied to various electronic devices.

[0112] like Figure 2 As shown, a product portrait storage device 200 includes: an acquisition unit 201, a determination unit 202, a first generation unit 203, an encryption unit 204, a sending unit 205, a second generation unit 206 and a storage unit 207. Among them, the acquisition unit 201 is configured to acquire the user value flow data corresponding to the target user from the user database; the determination unit 202 is configured to determine at least one user group information and a user value attribute information set corresponding to the target user according to the user value flow data; the first generation unit 203 is configured to generate a value value corresponding to the target user that can be provided by the target virtual value product according to the at least one user group information and the user value attribute information set; the encryption unit 204 is configured to encode and encrypt the value value and the at least one user group information in response to monitoring that the value value is greater than the target value to generate an initial encryption result; the sending unit 205 is configured to send the initial encryption result to the multi-layer audit terminal to audit the value value; the second generation unit 206 is configured to generate a product value use portrait corresponding to the target user according to the value value, the at least one user group information and the user value attribute information set in response to receiving the audit qualification information representing the audit passing; the storage unit 207 is configured to encrypt and store the product value use portrait on the target blockchain.

[0113] It is understandable that the units recorded in the product image storage device 200 and the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the product image storage device 200 and the units contained therein, and will not be repeated here.

[0114] Reference below Figure 3, which shows a structural schematic diagram of an electronic device (eg, an electronic device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0115] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 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 the bus 304.

[0116] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0117] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0118] It should be noted that the computer-readable medium 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 may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0119] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText 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"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0120] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains the user value flow data corresponding to the target user from the user database; determines at least one user group information and a user value attribute information set corresponding to the target user according to the user value flow data; generates a value value corresponding to the target user that can be provided by the target virtual value product according to the at least one user group information and the user value attribute information set; in response to monitoring that the value value is greater than the target value, encodes and encrypts the value value and the at least one user group information to generate an initial encryption result; sends the initial encryption result to the multi-layer audit terminal to audit the value value; in response to receiving the audit qualification information indicating that the audit has passed, generates the product value usage portrait corresponding to the target user according to the value value, the at least one user group information and the user value attribute information set; and encrypts and stores the product value usage portrait on the target blockchain.

[0121] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0122] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0123] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including an acquisition unit, a determination unit, a first generation unit, an encryption unit, a sending unit, a second generation unit and a storage unit. The names of these units do not constitute limitations on the units themselves in certain circumstances, for example, the acquisition unit may also be described as "a unit for acquiring user value flow data corresponding to a target user from a user database".

[0124] 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: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0125] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A product image storage method, comprising: Obtain user value flow data corresponding to the target user from the user database; Determine at least one user group information and user value attribute information set corresponding to the target user according to the user value flow data; Generate a value value representing the value that the target virtual value product can provide, corresponding to the target user, according to the at least one user group information and the user value attribute information set; In response to monitoring that the value value is greater than the target value, encoding and encrypting the value value and the at least one user group information to generate an initial encryption result; Sending the initial encryption result to a multi-layer audit terminal to audit the value value; In response to receiving the audit qualification information indicating that the audit has passed, generating a product value usage portrait corresponding to the target user according to the value value, the at least one user group information and the user value attribute information set; The product value usage portrait is encrypted and stored on the target blockchain.

2. The method according to claim 1, wherein: The method further comprises: In response to receiving information indicating that the target user requests value provision from the target virtual value product, obtaining an encrypted portrait corresponding to the target user and decrypting the portrait according to user information corresponding to the target user to generate the product value usage portrait; Determine the user authenticity information corresponding to the target user by using the user image included in the product value use image; In response to determining that the user authenticity information represents that the target user is a real individual user, extracting a value value from the product value usage portrait; Generate value numerical reasons corresponding to target users based on the product value usage portrait; Determine value processing operation information corresponding to the value value; The value processing operation information and the value numerical reason are sent to the request terminal corresponding to the target user, so that the request terminal can perform the corresponding value processing operation and display the corresponding value processing value numerical reason.

3. The method according to claim 1, wherein: The generating, according to the at least one user group information and the user value attribute information set, a value value representing the value that can be provided by the target virtual value product corresponding to the target user comprises: Determine at least one first value adjustment information corresponding to the at least one user group information; Generating user value risk information corresponding to the target user according to the user value attribute information set; Generating second value adjustment information corresponding to the user value risk information; Determine the initial value corresponding to the target user; The initial value value is adjusted according to the at least one first value adjustment information and the second value adjustment information to generate the value value.

4. The method according to claim 1, wherein: The step of determining at least one user group information and a user value attribute information set corresponding to the target user according to the user value flow data includes: Acquire a user group characteristic information group corresponding to each user group identifier in the user group identifier set from the user group database to obtain a user group characteristic information group set, wherein each user group characteristic information in the user group characteristic information group has corresponding encrypted first user group value attribute information; Extracting each user group value attribute information corresponding to each user group value attribute from the user value circulation data; Sending the value attribute information of each user group to the attribute information encryption terminal to generate encrypted value attribute information of each second user group; Vectorizing the encrypted value attribute information of each second user group to generate a target user group characteristic information group; Determine the value attribute similarity information between each user group characteristic information group in the user group characteristic information group set and the target user group characteristic information group to obtain a value attribute similarity information set; Filter out user group characteristic information groups whose value attribute similarity information is higher than target similarity information from the user group characteristic information groups to obtain at least one user group characteristic information group; Determine each user group identifier corresponding to the at least one user group characteristic information group as at least one user group information; Obtaining a user value attribute set corresponding to the user value risk information; A user value attribute information set corresponding to the user value attribute set is extracted from the user value circulation data.

5. The method according to claim 3, wherein: The first value adjustment information in the at least one first value adjustment information is generated by the following steps: Acquire user group information corresponding to the first value adjustment information as target user group information; Determine a user group characteristic information group corresponding to the target user group information as the target user group characteristic information group; Determine attribute importance information corresponding to each user group attribute in the user group attribute set; According to the attribute importance information corresponding to the user group attributes, each user group attribute in the user group attribute set is divided into attribute intervals to obtain a user group attribute group set, wherein the user group attribute group set includes: a first user group attribute group, a second user group attribute group and a third user group attribute group; Determining currently available computing resources corresponding to the value adjustment information generating terminal; Determining, according to the currently available computing resources, user group attribute extraction ratios corresponding to the first user group attribute group, the second user group attribute group, and the third user group attribute group; extracting group attributes from the first user group attribute group, the second user group attribute group, and the third user group attribute group according to the user group attribute extraction ratio to generate an extracted group attribute group; Extracting a user group characteristic information subgroup corresponding to the extracted group attribute group from the target user group characteristic information group; The user group characteristic information subgroup is input into a pre-trained value adjustment information generation model to generate the first value adjustment information.

6. The method according to claim 3, wherein: Generating user value risk information corresponding to the target user according to the user value attribute information set includes: Encrypting each user value attribute information in the user value attribute information set to generate a user value attribute encrypted information set; sending the user value attribute encrypted information set to a user value risk information generating terminal, so that the user value risk information generating terminal generates user value risk information using a graphics processor set; and, Using the graphics processor group set, the user value risk information is generated by the following steps: Dividing each user value attribute information in the user value attribute information set to generate a first user value attribute information subset for generating user credit information, a second user value attribute information subset for generating user value risk information, a third user value attribute information subset for generating product use credit information, and a fourth user value attribute information subset for generating product use risk information; Inputting the first user value attribute information subset into a user credit generation model deployed by a pre-trained first image processor group to generate first user credit information; Inputting the first user value attribute information subset and the second user value attribute information subset into a first dual-tower model deployed by a pre-trained second image processor group to generate second user credit information and first user value risk information; inputting the second user value attribute information subset into a user value risk information generation model deployed by a pre-trained third image processor group to generate second user value risk information; inputting the third user value attribute information subset into a pre-trained product usage credit information generation model deployed by a fourth image processor group to generate first product usage credit information; Inputting the third user value attribute information subset and the fourth user value attribute information subset into a second dual-tower model deployed by a pre-trained fifth image processor group to generate second product use credit information and first product use risk information; inputting the fourth user value attribute information subset into a pre-trained product use risk information generation model deployed by a sixth image processor group to generate second product use risk information; generating first initial user value risk information according to the first user credit information, the second user credit information, the first user value risk information and the second user value risk information; generating second initial user value risk information according to the first product use credit information, the second product use credit information, the first product use risk information, and the second product use risk information; The user value risk information is generated according to the first initial user value risk information and the second initial user value risk information.

7. A product image storage device, comprising: An acquisition unit is configured to acquire user value flow data corresponding to a target user from a user database; a determination unit configured to determine at least one user group information and a user value attribute information set corresponding to the target user according to the user value flow data; A first generating unit is configured to generate a value value representing a target virtual value product that can be provided by the target user according to the at least one user group information and the user value attribute information set; an encryption unit, configured to, in response to monitoring that the value value is greater than a target value, encode and encrypt the value value and the at least one user group information to generate an initial encryption result; A sending unit, configured to send the initial encryption result to a multi-layer audit terminal for auditing the value value; The second generating unit is configured to generate, in response to receiving the audit passing information indicating that the audit has passed, a product value usage portrait corresponding to the target user according to the value value, the at least one user group information and the user value attribute information set; The storage unit is configured to encrypt and store the product value usage portrait on the target blockchain.

8. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images