User information inquiry protection methods, devices, equipment, media and program products

Abstract

This disclosure provides a method, apparatus, electronic device, medium, and computer program product for protecting user information queries based on a social network graph. The method and apparatus can be used in the fields of artificial intelligence and information security. The method for protecting user information queries based on a social network graph includes: obtaining a query request, wherein the query request includes personal information of the queried user and / or content posted by the queried user; calculating the overlap similarity between the user initiating the query request and the queried user based on a pre-constructed social network graph; determining noise according to a set privacy budget and the overlap similarity; and adding the noise to the response information to the query request to obtain privacy data.

Description

Technical Field

[0001] This disclosure relates to the fields of artificial intelligence and information security technology, and more specifically, to a method, apparatus, electronic device, medium, and computer program product for protecting user information queries based on social network graphs. Background Technology

[0002] In existing social networks, when a user queries information about another unfamiliar user, if the queried user does not set any permissions, all of their posted information can often be seen, including personal information, frequent location, login IP address, zodiac sign, hobbies, and personal habits. If the querying user has certain background knowledge, such as having overlapping social circles with the queried user, they can easily infer and locate the queried user's privacy. Current privacy protection methods rely on the queried user controlling their access to personal information and posted content, such as the scope of disclosure of personal information and posted content. Summary of the Invention

[0003] In view of this, this disclosure provides a method, apparatus, electronic device, computer-readable storage medium, and computer program product for protecting user information query based on social network graphs, which enables information to be readable, usable, and disseminated while preventing background knowledge attacks and protecting user privacy.

[0004] One aspect of this disclosure provides a method for protecting user information queries based on a social network graph, comprising: obtaining a query request, wherein the query request includes personal information of the queried user and / or content posted by the queried user; calculating the overlap similarity between the user initiating the query request and the queried user based on a pre-constructed social network graph; determining noise according to a set privacy budget and the overlap similarity; and adding the noise to the response information made in response to the query request to obtain privacy data.

[0005] According to the user information query protection method based on social network graphs in this disclosure, the overlap similarity between the user initiating the query request and the queried user can be calculated using a pre-constructed social network graph. Noise can be determined based on a set privacy budget and the overlap similarity. Adding this noise to the response information to the query request yields protected privacy data. This method constructs the correlation between two users based on overlap similarity. A higher correlation increases the likelihood of background knowledge attacks, thus allocating a smaller privacy budget and adding greater perturbation noise to the queried user's personal information and published content, reducing the probability of privacy being compromised. Furthermore, this disclosure dynamically allocates the privacy budget based on overlap similarity, preventing background knowledge attacks while ensuring information remains readable, usable, and disseminable, thereby protecting user privacy.

[0006] In some embodiments, the pre-construction of the social network graph includes: acquiring social data, wherein the social data includes user information and relationship information between users; and constructing a social network graph based on the social data, wherein the nodes of the social network graph are constructed based on the user information, and the edges of the social network graph are constructed based on the relationship information.

[0007] In some embodiments, when the social data is updated, the social network graph is updated based on the updated social data.

[0008] In some embodiments, calculating the overlap similarity between the user initiating the query request and the queried user based on a pre-constructed social network graph includes: determining, based on the social network graph, the number of users related to the user initiating the query request to obtain a first correlation number; determining, based on the social network graph, the number of users related to the queried user to obtain a second correlation number; determining, based on the social network graph, the number of users commonly related to both the user initiating the query request and the queried user to obtain a third correlation number; and calculating the overlap similarity between the user initiating the query request and the queried user based on the first correlation number, the second correlation number, and the third correlation number.

[0009] In some embodiments, determining noise based on a set privacy budget and the overlap similarity includes: determining a noise distribution based on the set privacy budget and the overlap similarity; and the noise conforming to the noise distribution.

[0010] In some embodiments, determining the noise distribution based on a set privacy budget and the overlap similarity includes: mapping the overlap similarity to obtain a mapping value; and determining the noise distribution based on the set privacy budget and the mapping value.

[0011] Another aspect of this disclosure provides a user information query protection device based on a social network graph, comprising: an acquisition module for executing an acquisition query request, wherein the query request includes personal information of the queried user and / or content posted by the queried user; a calculation module for calculating the overlap similarity between the user initiating the query request and the queried user based on a pre-built social network graph; a determination module for determining noise based on a set privacy budget and the overlap similarity; and an addition module for adding the noise to the response information to the query request to obtain privacy data.

[0012] Another aspect of this disclosure provides an electronic device including one or more processors and one or more memories, wherein the memories are used to store executable instructions that, when executed by the processor, implement the method described above.

[0013] Another aspect of this disclosure provides a computer-readable storage medium storing computer-executable instructions that, when executed, are used to implement the method described above.

[0014] Another aspect of this disclosure provides a computer program product including a computer program comprising computer executable instructions that, when executed, implement the method described above. Attached Figure Description

[0015] The above and other objects, features and advantages of this disclosure will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0016] Figure 1 This illustration schematically shows an exemplary system architecture to which methods and apparatus can be applied according to embodiments of the present disclosure;

[0017] Figure 2 A flowchart illustrating a user information query protection method based on a social network graph according to an embodiment of the present disclosure is shown in the schematic diagram.

[0018] Figure 3 A flowchart illustrating a pre-constructed social network graph according to an embodiment of the present disclosure is shown schematically;

[0019] Figure 4 A flowchart illustrating a social network graph according to an embodiment of the present disclosure is shown schematically;

[0020] Figure 5 The flowchart illustrates an embodiment of the present disclosure of calculating the overlap similarity between a user initiating a query request and a user being queried, based on a pre-built social network graph.

[0021] Figure 6 A flowchart illustrating the determination of noise based on a set privacy budget and overlap similarity according to an embodiment of the present disclosure is shown schematically.

[0022] Figure 7 A flowchart illustrating the determination of noise distribution based on a set privacy budget and overlap similarity according to an embodiment of the present disclosure is shown.

[0023] Figure 8 A block diagram illustrating a user information query protection device based on a social network graph according to an embodiment of the present disclosure is shown schematically.

[0024] Figure 9 A block diagram of an electronic device according to an embodiment of the present disclosure is shown schematically. Detailed Implementation

[0025] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0026] In the technical solution disclosed herein, the acquisition, storage, and application of user personal information all comply with relevant laws and regulations, necessary confidentiality measures have been taken, and there is no violation of public order and good morals. In the technical solution disclosed herein, the acquisition, collection, storage, use, processing, transmission, provision, disclosure, and application of data all comply with relevant laws and regulations, necessary confidentiality measures have been taken, and there is no violation of public order and good morals.

[0027] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms "comprising," "including," etc., as used herein indicate the presence of the said features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0028] When using expressions such as "at least one of A, B, or C," it should generally be interpreted in accordance with the meaning commonly understood by those skilled in the art (e.g., "a system having at least one of A, B, or C" should include, but is not limited to, systems having A alone, having B alone, having C alone, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.). The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, features defined with "first" or "second" may explicitly or implicitly include one or more of the stated features.

[0029] In existing social networks, when a user queries information about another unfamiliar user, if the queried user does not set any permissions, they can often see all the information posted, including personal information, frequent location, login IP address, zodiac sign, hobbies, and personal habits. If the querying user has certain background knowledge, such as having overlapping social circles with the queried user, they can easily infer and locate the queried user's privacy. Current privacy protection methods rely on the queried user controlling their access to personal information and posted content, such as the scope of disclosure. Existing solutions are mainly based on access control mechanisms to control the dissemination of user information and posted content. The drawback is that this reduces content exposure and dissemination, thus decreasing users' willingness to share. Regarding data security, for information without access control, the querying user can use background knowledge to launch attacks and locate the queried user's privacy.

[0030] Embodiments of this disclosure provide a method, apparatus, electronic device, computer-readable storage medium, and computer program product for protecting user information queries based on social network graphs. The method for protecting user information queries based on social network graphs includes: obtaining a query request, wherein the query request includes personal information of the queried user and / or content posted by the queried user; calculating the overlap similarity between the user initiating the query request and the queried user based on a pre-constructed social network graph; determining noise according to a set privacy budget and the overlap similarity; and adding the noise to the response information to the query request to obtain privacy data.

[0031] It should be noted that the user information query protection method, device, electronic device, computer-readable storage medium and computer program product based on social network graph disclosed herein can be used in the fields of artificial intelligence and information security technology, and can also be used in any field other than artificial intelligence and information security technology, such as the financial field. The field of this disclosure is not limited here.

[0032] Figure 1 This illustration schematically depicts an exemplary system architecture 100 to which a user information query protection method, apparatus, electronic device, computer-readable storage medium, and computer program product based on social network graphs can be applied, according to embodiments of this disclosure. It should be noted that... Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this disclosure, in order to help those skilled in the art understand the technical content of this disclosure, but do not mean that the embodiments of this disclosure cannot be used in other devices, systems, environments or scenarios.

[0033] like Figure 1As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, and 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the terminal devices 101, 102, and 103 and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0034] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0035] Terminal devices 101, 102, and 103 can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0036] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using terminal devices 101, 102, and 103 (for example only). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0037] It should be noted that the user information query protection method based on social network graphs provided in this disclosure can generally be executed by server 105. Correspondingly, the user information query protection device based on social network graphs provided in this disclosure can generally be located in server 105. The user information query protection method based on social network graphs provided in this disclosure can also be executed by a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105. Correspondingly, the user information query protection device based on social network graphs provided in this disclosure can also be located in a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105.

[0038] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0039] The following will be based on Figure 1 The described scene, through Figures 2-7The present disclosure provides a detailed description of the user information query protection method based on social network graphs.

[0040] Figure 2 A flowchart illustrating a user information query protection method based on a social network graph according to an embodiment of the present disclosure is shown.

[0041] like Figure 2 As shown, the user information query protection method based on social network graph in this embodiment includes operations S210 to S240.

[0042] In operation S210, a query request is obtained, wherein the query request includes the personal information of the queried user and / or the content published by the queried user.

[0043] In operation S220, based on a pre-built social network graph, the overlap similarity between the user initiating the query request and the user being queried is calculated.

[0044] It should be noted that overlap similarity is an extension of Jaccard similarity. It uses the intersection size of two sets divided by the smaller of the two sets to represent the degree of similarity between them. The value of overlap similarity ranges from [0, 1], with larger values ​​indicating greater similarity. In this disclosure, the user initiating the query and the queried user are considered as two separate sets, and their connected neighboring users are considered as elements within each set. The intersection elements are the commonly associated users of both the user initiating the query and the queried user. By combining this with the user relationship network topology, the degree of similarity between two target users can be determined based on overlap similarity.

[0045] As an feasible approach, such as Figure 3 As shown, pre-constructing a social network graph may include operations S310 and S320.

[0046] When operating S310, social data is acquired, which includes user information and relationship information between users. User information may include name, gender, address, workplace, job title, zodiac sign, hobbies, and personal habits, etc.; relationship information between users may include kinship, colleague, friend, and transaction relationships, etc.

[0047] When operating the S320, a social network graph is constructed based on social data. Nodes in the social network graph are constructed based on user information, and edges are constructed based on relationship information. The social network graph can be structured as follows: Figure 4 As shown, Figure 4 This is merely an illustrative example and should not be construed as limiting the scope of this disclosure. Operations S310 and S320 facilitate the pre-construction of social network graphs.

[0048] In some specific examples, when social data is updated, the social network graph is updated based on the updated social data. This ensures the timeliness of the data in the social network graph, resulting in high accuracy and timeliness of the data obtained from the social network graph in the following sections.

[0049] As an feasible approach, such as Figure 5 As shown, operation S220 calculates the overlap similarity between the user who initiated the query request and the user being queried based on a pre-built social network graph, including operations S221 to S224.

[0050] In operation S221, based on the social network graph, the number of users related to the user who initiated the query request is determined, and the first number of related users is obtained.

[0051] In operation S222, based on the social network graph, the number of users related to the queried user is determined, and the second number of related users is obtained.

[0052] In operation S223, based on the social network graph, the number of users commonly associated with both the user who initiated the query request and the user being queried is determined, thus obtaining the third correlation count.

[0053] In operation S224, the overlap similarity between the user who initiated the query request and the user being queried is calculated based on the first relevance quantity, the second relevance quantity, and the third relevance quantity.

[0054] Continue with Figure 4 Taking a social network graph as an example, suppose user A is the user who initiates the query request and user B is the user being queried. From this, we can find that users who have an edge relationship with user A are user C, user D, and user F, a total of three users, which means the first correlation number is 3. We can find that users who have an edge relationship with user B are user C, user D, and user E, a total of three users, which means the second correlation number is 3. Furthermore, we can find that users who are jointly correlated with user A and user B are user C and user D, a total of two users, which means the third correlation number is 2.

[0055] For example, the overlap similarity can be represented by S0(A, B), the first correlation number can be represented by |A|, the second correlation number can be represented by |B|, and the third correlation number can be represented by |A∩B|. The overlap similarity can be obtained through formula (1).

[0056]

[0057] Therefore, by operating S221 to S224, it is easy to calculate the overlap similarity between the user who initiates the query request and the user being queried based on a pre-built social network graph.

[0058] In operation S230, noise is determined based on the set privacy budget and overlap similarity.

[0059] As one possible implementation method, such as Figure 6 As shown, operation S230 determines noise based on the set privacy budget and overlap similarity, including operations S231 and S232.

[0060] In operation S231, the noise distribution is determined based on the set privacy budget and overlap similarity.

[0061] In some specific examples, such as Figure 7 As shown, operation S231 determines the noise distribution based on the set privacy budget and overlap similarity, including operation S2311 and operation S2312.

[0062] In operation S2311, the overlap similarity is mapped to obtain the mapped value. The mapped value can be represented as S′0, which can be obtained through formula (2).

[0063] S′0=sigmoid(S0) (2)

[0064] Where S0 represents the overlap similarity.

[0065] In operation S2312, the noise distribution is determined based on the set privacy budget and mapping value. For example, the noise distribution can be... ε represents the set privacy budget.

[0066] Since the initial privacy budget value is generally small, usually within the range of [0, 1], mapping the overlap similarity S0 and determining the noise distribution based on the mapped value can improve the display effect and rationality of the noise distribution. Operations S2311 and S2312 facilitate determining the noise distribution based on the set privacy budget and overlap similarity.

[0067] In operation S232, the noise follows a noise distribution. Therefore, by operating S231 and S232, it is easy to determine the noise based on a set privacy budget and overlap similarity.

[0068] In operation S240, noise is added to the response information to the query request to obtain private data.

[0069] According to the user information query protection method based on social network graphs in this disclosure, the overlap similarity between the user initiating the query request and the queried user can be calculated using a pre-constructed social network graph. Noise can be determined based on a set privacy budget and the overlap similarity. Adding this noise to the response information to the query request yields protected privacy data. This method constructs the correlation between two users based on overlap similarity. A higher correlation increases the likelihood of background knowledge attacks, thus allocating a smaller privacy budget and adding greater perturbation noise to the queried user's personal information and published content, reducing the probability of privacy being compromised. Furthermore, this disclosure dynamically allocates the privacy budget based on overlap similarity, preventing background knowledge attacks while ensuring information remains readable, usable, and disseminable, thereby protecting user privacy.

[0070] Based on the above-described method for protecting user information queries based on social network graphs, this disclosure also provides a device for protecting user information queries based on social network graphs. The following will be combined with... Figure 8 A detailed description is provided of the user information query protection device 10 based on social network graphs.

[0071] Figure 8 The diagram illustrates the structure of a user information query protection device 10 based on a social network graph according to an embodiment of the present disclosure.

[0072] The user information query protection device 10 based on social network graphs includes an acquisition module 1, a calculation module 2, a determination module 3, and an addition module 4.

[0073] Acquisition module 1 is used to perform operation S210: acquire query request, wherein the query request includes the personal information of the queried user and / or the content published by the queried user.

[0074] Calculation module 2 is used to perform operation S220: based on a pre-built social network graph, calculate the overlap similarity between the user who initiated the query request and the user being queried.

[0075] Determine module 3, which is used to perform operation S230: determine noise based on the set privacy budget and overlap similarity.

[0076] Add module 4, which is used to perform operation S240: add noise to the response information made in response to the query request to obtain privacy data.

[0077] According to some embodiments of this disclosure, the user information query protection device based on social network graphs further includes a construction module, which is used to pre-construct the social network graph. The construction module includes an acquisition unit and a construction unit.

[0078] The acquisition unit is used to acquire social data, which includes user information and information on relationships between users.

[0079] The building unit is used to construct a social network graph based on social data. The building unit constructs the nodes of the social network graph based on user information and the edges of the social network graph based on the relationship information.

[0080] According to some embodiments of this disclosure, the construction module further includes an update unit, which is used to update the social network graph according to the updated social data when the social data is updated.

[0081] According to some embodiments of this disclosure, the calculation module includes a first determining unit, a second determining unit, a third determining unit, and a calculation unit.

[0082] The first determining unit is used to determine the number of users related to the user who initiated the query request based on the social network graph, and obtain the first related number.

[0083] The second determining unit is used to determine the number of users related to the queried user based on the social network graph, and obtain the second related number.

[0084] The third determining unit is used to determine the number of users that are commonly related to both the user who initiated the query request and the user being queried, based on the social network graph, and thus obtain the third related number.

[0085] The calculation unit is used to calculate the overlap similarity between the user who initiated the query request and the user being queried, based on the first relevance quantity, the second relevance quantity, and the third relevance quantity.

[0086] According to some embodiments of this disclosure, the determining module includes a fourth determining unit and a conforming unit.

[0087] The fourth determining unit is used to determine the noise distribution based on the set privacy budget and overlap similarity.

[0088] Obey the unit; the unit is used to ensure that noise follows the noise distribution.

[0089] According to some embodiments of this disclosure, the fourth determining unit includes a mapping element and a determining element.

[0090] The mapping element is used to map overlap similarity to obtain a mapped value.

[0091] The component is determined to determine the noise distribution based on the set privacy budget and mapping value.

[0092] According to the user information query protection device 10 based on social network graphs in this disclosure, the overlap similarity between the user initiating the query request and the queried user can be calculated using a pre-constructed social network graph. Noise can be determined based on a set privacy budget and overlap similarity. Adding this noise to the response information to the query request yields protected privacy data. The method of this disclosure constructs the correlation between two users based on overlap similarity. The greater the correlation, the higher the probability of background knowledge attacks, thus allocating a smaller privacy budget and adding greater perturbation noise to the queried user's personal information and published content, reducing the probability of their privacy being compromised. Furthermore, this disclosure dynamically allocates the privacy budget based on overlap similarity, preventing background knowledge attacks while ensuring information remains readable, usable, and disseminable, thereby protecting user privacy.

[0093] Furthermore, according to embodiments of this disclosure, any and multiple modules among the acquisition module 1, calculation module 2, determination module 3, and addition module 4 can be combined into one module, or any one of these modules can be split into multiple modules. Alternatively, at least some of the functionality of one or more of these modules can be combined with at least some of the functionality of other modules and implemented in one module.

[0094] According to embodiments of this disclosure, at least one of the acquisition module 1, calculation module 2, determination module 3, and addition module 4 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging the circuitry, or implemented in any one of the three methods of software, hardware, and firmware, or in a suitable combination of any of these.

[0095] Alternatively, at least one of the acquisition module 1, calculation module 2, determination module 3, and addition module 4 can be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0096] The following describes in detail a user information query protection method based on a social network graph according to embodiments of the present disclosure. It is to be understood that the following description is merely illustrative and not intended to limit the scope of the present disclosure.

[0097] The following explanations are provided for the terms used in the embodiments.

[0098] Differential privacy: The concept of differential privacy comes from the concept of semantic security in cryptography. This technique uses random noise to ensure that the public output does not change significantly due to whether an individual is in the dataset, and provides a quantitative model for the degree of privacy leakage. Its specific definition is as follows.

[0099] For any two adjacent datasets X and X′, a randomization algorithm D can be considered to satisfy differential privacy if it satisfies the following conditions.

[0100] Pr[D(X)∈S]≤e ε ·Pr[D(X′)∈S],

[0101] Privacy Budget: In the above formula, ε is called the privacy budget. When ε is sufficiently small, it means that data availability is very low. In practical applications, this parameter is usually set to a very small value. This parameter should be set reasonably according to the specific business scenario and the expected privacy protection requirements.

[0102] Overlap similarity: A set consists of multiple elements, which are unordered and distinct. The number of elements in set A is the size of set A, denoted as |A|. The intersection of set A and set B is A∩B. The overlap similarity between sets A and B can be expressed as:

[0103]

[0104] For example, set A has elements {b, c, e, c, g}, and set B has elements {a, b, d, g}. Their intersection is A ∩ B = {b, g}. Their overlap similarity can be expressed as...

[0105]

[0106] This patent proposes a scheme to desensitize user personal information and posted content in social networks using differential privacy technology.

[0107] Overlap similarity is an extension of Jaccard similarity. It measures the similarity between two sets by dividing the size of their intersection by the smaller of the two sets. The value of overlap similarity ranges from [0, 1], with higher values ​​indicating greater similarity.

[0108] In the embodiments of this disclosure, the querying user and the queried user are considered as two sets, and the neighboring users connected to the user are considered as elements within the sets. The intersection elements are the related users common to both users. Combining the user relationship network topology graph, the similarity between the two target users is calculated based on overlap similarity. This method then constructs the association degree between the two users. The higher the association degree, the higher the probability of background knowledge attacks, thus allocating a smaller privacy budget and adding greater perturbation to the information and content of the queried user, reducing the probability of their privacy being compromised.

[0109] This disclosure introduces a network topology influence factor for adjacent nodes, more accurately defining the degree of association between two individual users in a social network. It dynamically allocates the privacy budget based on overlap similarity, flexibly applying scrambling to reduce the possibility of privacy leaks for individual users. Furthermore, by dynamically allocating the privacy budget based on node overlap similarity, it flexibly balances the protection of individual user privacy with the dissemination of their content within the social network.

[0110] To achieve the above objectives, the present disclosure provides the following technical solution.

[0111] S101, User Information Analysis Module.

[0112] S102, User Network Topology Map Construction Module.

[0113] S103, Overlap Similarity Calculation Module.

[0114] S104, Noise Calculation Module.

[0115] S105, Noise Addition Module.

[0116] S106, Result Return Module.

[0117] S101. Analyze the relationships between users based on their historical activities in social networks, such as whether they follow each other, whether they have private chat records, and whether there are transaction records.

[0118] S102. Based on the user association in S101, construct a user network topology diagram.

[0119] S103. Calculate the overlap similarity between users, i.e., user association degree. Taking user A and user B as an example, their overlap similarity is:

[0120]

[0121] Where A is the querying user, B is the queried user, |A∩B| represents the total number of related users, |A| represents the total number of related users of the querying user, |B| represents the total number of related users of the queried node, and min(|A|, |B|) represents the minimum value between |A| and |B|.

[0122] S104. Based on the overlap similarity S0(A, B) in S103, calculate the allocable privacy budget and the noise that needs to be added.

[0123] Since the privacy budget is generally small, usually in the range of [0, 1], the calculated overlap similarity needs to be mapped first.

[0124] S′0=sigmoid(S0)

[0125] Finally, the noise r that follows a Laplace distribution is calculated, i.e.,

[0126] D′(X)=D(X)+r

[0127] Where r follows a distribution ε is the given initial privacy budget, which can be set to a value less than 1, such as 0.01.

[0128] S105, Noise Addition Module. This module adds the noise generated in S104 to the relevant information and published content of the queried user.

[0129] S106. Return the information generated in S105 to the querying user.

[0130] Figure 9 A block diagram schematically illustrates an electronic device suitable for implementing the above-described method according to an embodiment of the present disclosure.

[0131] like Figure 9 As shown, an electronic device 900 according to an embodiment of the present disclosure includes a processor 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage portion 908 into a random access memory (RAM) 903. The processor 901 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include onboard memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0132] RAM 903 stores various programs and data required for the operation of electronic device 900. Processor 901, ROM 902, and RAM 903 are interconnected via bus 904. Processor 901 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 902 and / or RAM 903. It should be noted that the programs may also be stored in one or more memories other than ROM 902 and RAM 903. Processor 901 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0133] According to embodiments of this disclosure, the electronic device 900 may further include an input / output (I / O) interface 905, which is also connected to a bus 904. The electronic device 900 may also include one or more of the following components connected to the I / O interface 905: an input section 906 including a keyboard, mouse, etc.; an output section 907 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the input / output (I / O) interface 905 as needed. A removable medium 911, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 910 as needed so that computer programs read from it can be installed into the storage section 908 as needed.

[0134] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0135] According to embodiments of this disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this disclosure, the computer-readable storage medium may include ROM 902 and / or RAM 903 and / or one or more memories other than ROM 902 and RAM 903 described above.

[0136] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to cause the computer system to implement the methods of the embodiments of this disclosure.

[0137] When the computer program is executed by the processor 901, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0138] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and downloaded and installed via the communication section 909, and / or installed from a removable medium 911. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0139] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 909, and / or installed from the removable medium 911. When the computer program is executed by the processor 901, it performs the functions defined in the system of this disclosure embodiment. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0140] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0141] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0142] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure can be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0143] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A method for protecting user information query based on social network graph, characterized in that, The method comprises: obtaining a query request, wherein the query request comprises personal information of a queried user and / or published content of the queried user; calculating an overlapping similarity between a user initiating the query request and the queried user based on a pre-constructed social network graph; determining noise according to a set privacy budget and the overlapping similarity; and adding the noise to reply information made for the query request to obtain privacy data, wherein the calculating of the overlapping similarity between the user initiating the query request and the queried user based on the pre-constructed social network graph comprises: determining a number of users related to the user initiating the query request according to the social network graph to obtain a first related number; determining a number of users related to the queried user according to the social network graph to obtain a second related number; determining a number of users related to both the user initiating the query request and the queried user according to the social network graph to obtain a third related number; and calculating the overlapping similarity between the user initiating the query request and the queried user according to the first related number, the second related number and the third related number. Wherein, the overlap similarity is represented by |A∩B|, the third correlation quantity is represented by |A∩B|, the overlap similarity is obtained by formula (1). （1）。 2. The method of claim 1, wherein, The pre-constructed social network graph comprises: obtaining social data, wherein the social data comprises user information and association relationship information between users; and constructing a social network graph according to the social data, wherein nodes of the social network graph are constructed according to the user information, and edges of the social network graph are constructed according to the association relationship information.

3. The method of claim 2, wherein, When the social data is updated, the social network graph is updated according to the updated social data.

4. The method of claim 1, wherein, The determining of the noise according to the set privacy budget and the overlapping similarity comprises: determining a noise distribution according to the set privacy budget and the overlapping similarity; and the noise is subject to the noise distribution.

5. The method of claim 4, wherein, The determining of the noise distribution according to the set privacy budget and the overlapping similarity comprises: performing mapping processing on the overlapping similarity to obtain a mapping value; and determining the noise distribution according to the set privacy budget and the mapping value.

6. A user information query protection apparatus based on a social network graph, characterized by, The method comprises: an obtaining module configured to perform obtaining a query request, wherein the query request comprises personal information of a queried user and / or published content of the queried user; a calculating module configured to perform calculating an overlapping similarity between a user initiating the query request and the queried user based on a pre-constructed social network graph; a determining module configured to perform determining noise according to a set privacy budget and the overlapping similarity; and an adding module configured to perform adding the noise to reply information made for the query request to obtain privacy data, wherein the calculating of the overlapping similarity between the user initiating the query request and the queried user based on the pre-constructed social network graph comprises: determining a number of users related to the user initiating the query request according to the social network graph to obtain a first related number; determining a number of users related to the queried user according to the social network graph to obtain a second related number; determining a number of users related to both the user initiating the query request and the queried user according to the social network graph to obtain a third related number; and calculating the overlapping similarity between the user initiating the query request and the queried user according to the first related number, the second related number and the third related number. According to the social network graph, determine a number of users related to the queried user, to obtain a second related number; According to the social network graph, determine a number of users related to both the user initiating the query request and the queried user, to obtain a third related number; and According to the first related number, the second related number and the third related number, calculate an overlapping similarity between the user initiating the query request and the queried user, wherein the overlap similarity is represented by |A∩B|, the third correlation quantity is represented by |A∩B|, the overlap similarity is obtained by formula (1), （1）。 7. An electronic device, comprising: comprising: one or more processors; one or more memories for storing executable instructions, which, when executed by the processor, implement the method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The storage medium has stored executable instructions, which, when executed by the processor, implement the method according to any one of claims 1-5.

9. A computer program product, characterised in that, comprise a computer program comprising one or more executable instructions, which, when executed by the processor, implement the method according to any one of claims 1-5.

Images