Information query protection method, device, electronic device, medium and program product

Abstract

The present disclosure provides a method, apparatus, electronic device, medium, and computer program product for protecting information query based on a knowledge graph. The above method and apparatus can be used in the fields of big data and information security technologies. The method includes: obtaining a query request, where the query request includes an initiating query enterprise, query information, and a receiving query enterprise; based on a pre-constructed knowledge graph, obtaining an intermediate enterprise node that has an association relationship with both the node corresponding to the initiating query enterprise and the node corresponding to the receiving query enterprise; calculating a first association degree between the node corresponding to the initiating query enterprise and the intermediate enterprise node; calculating a second association degree between the node corresponding to the receiving query enterprise and the intermediate enterprise node; calculating the intimacy between the node corresponding to the initiating query enterprise and the node corresponding to the receiving query enterprise according to the first association degree and the second association degree; determining noise according to the privacy budget and the intimacy; and adding the noise to the reply information made for the query information to obtain privacy data.

Description

Technical Field

[0001] The present disclosure relates to the technical fields of big data and information security, and more particularly, to an information query protection method, apparatus, electronic device, medium, and computer program product based on a knowledge graph. Background Art

[0002] Differential privacy is a new type of privacy protection mechanism proposed by Dwork in 2006. It mainly solves the problems of how to define privacy when sharing data in privacy protection and how to provide privacy protection when protecting the availability of data publication. Since the definition of differential privacy does not depend on the background knowledge of the attacker, it is widely used as a new type of privacy protection and model in various fields such as data mining and machine learning. Under the definition of differential privacy, the calculation result of the data set is insensitive to the change of a certain record. Whether a single record is in the data set or not has little impact on the calculation result.

[0003] Therefore, the privacy leakage risk caused by a record being added to the data set can be controlled within a very small and acceptable range, and the attacker cannot obtain accurate individual information by observing the calculation result. In the definition of differential privacy, the privacy budget can determine the degree of privacy protection. Generally speaking, the smaller the privacy budget, the better the privacy protection, but the more noise is added, resulting in a decrease in the availability of the data. Summary of the Invention

[0004] In view of this, the present disclosure provides an information query protection method, apparatus, electronic device, computer-readable storage medium, and computer program product based on a knowledge graph with good privacy protection and high data availability.

[0005] One aspect of the present disclosure provides an information query protection method based on a knowledge graph, including: obtaining a query request, where the query request includes an initiating query enterprise, query information, and a receiving query enterprise; obtaining an intermediate enterprise node that has an association relationship with both the node corresponding to the initiating query enterprise and the node corresponding to the receiving query enterprise based on a pre-constructed knowledge graph; calculating a first association degree between the node corresponding to the initiating query enterprise and the intermediate enterprise node; calculating a second association degree between the node corresponding to the receiving query enterprise and the intermediate enterprise node; calculating the intimacy between the node corresponding to the initiating query enterprise and the node corresponding to the receiving query enterprise according to the first association degree and the second association degree; determining noise according to the privacy budget and the intimacy; and adding the noise to the reply information for the query information to obtain privacy data.

[0006] According to the information query protection method based on a knowledge graph according to an embodiment of the present disclosure, information of the query - initiating enterprise, the query - receiving enterprise, and the intermediate enterprise can be efficiently and accurately obtained through the knowledge graph. Thus, it is convenient to calculate the intimacy, and further, it is convenient to implement the determination of noise jointly by the privacy budget and the intimacy. Since the noise is determined according to the privacy budget and the intimacy, the privacy budget can be allocated based on the node intimacy. When the relationship between the query - initiating enterprise and the query - receiving enterprise changes, the intimacy will change accordingly, so that the privacy budget can be dynamically updated, and the data availability is improved on the premise of ensuring data privacy.

[0007] In some embodiments, the construction steps of the pre - constructed knowledge graph include: obtaining enterprise data, where the enterprise data includes entity data and association relationship data, the entity data includes enterprise names, and the association relationship data includes the association relationships between the entity data; and constructing a knowledge graph according to the enterprise data, where nodes are constructed according to the entity data and edges are constructed according to the association relationship data.

[0008] In some embodiments, when the enterprise data is updated, the knowledge graph is updated according to the updated enterprise data.

[0009] In some embodiments, calculating the first association degree between the node corresponding to the query - initiating enterprise and the intermediate enterprise node includes: calculating the first degree value of each node corresponding to the query - initiating enterprise; and calculating the first association degree according to the first degree value.

[0010] In some embodiments, calculating the second association degree between the node corresponding to the query - receiving enterprise and the intermediate enterprise node includes: calculating the second degree value of each node corresponding to the query - receiving enterprise; and calculating the second association degree according to the second degree value.

[0011] In some embodiments, determining the noise according to the privacy budget and the intimacy includes: determining a noise distribution according to the privacy budget and the intimacy; and the noise follows the noise distribution.

[0012] In some embodiments, determining the noise distribution according to the privacy budget and the intimacy includes: performing a mapping process on the intimacy to obtain a mapping value; and determining the noise distribution according to the privacy budget and the mapping value.

[0013] In some embodiments, the sensitivity is determined according to the reply information, and the noise distribution is also determined according to the sensitivity.

[0014] In some embodiments, determining the sensitivity based on the reply information includes: determining a first data set of the reply information; obtaining a second data set after adjusting one or more data in the first data set, where the adjustment includes deletion, addition, or modification; and determining the sensitivity according to the first data set and the second data set.

[0015] Another aspect of the present disclosure provides an information query protection device based on a knowledge graph, including: a first acquisition module configured to acquire a query request, where the query request includes an initiating query enterprise, query information, and a receiving query enterprise; a second acquisition module configured to acquire, based on a pre-constructed knowledge graph, an intermediate enterprise node that has an association relationship with both the node corresponding to the initiating query enterprise and the node corresponding to the receiving query enterprise; a first calculation module configured to calculate a first association degree between the node corresponding to the initiating query enterprise and the intermediate enterprise node; a second calculation module configured to calculate a second association degree between the node corresponding to the receiving query enterprise and the intermediate enterprise node; a third calculation module configured to calculate an intimacy between the node corresponding to the initiating query enterprise and the node corresponding to the receiving query enterprise according to the first association degree and the second association degree; a determination module configured to determine noise according to a privacy budget and the intimacy; and an addition module configured to add the noise to the reply information made for the query information to obtain privacy data.

[0016] Another aspect of the present disclosure provides an electronic device, including one or more processors and one or more memories, where the memory is configured to store executable instructions, and when the executable instructions are executed by the processor, the above-mentioned method is implemented.

[0017] Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, and the instructions are used to implement the above-mentioned method when executed.

[0018] Another aspect of the present disclosure provides a computer program product, including a computer program, where the computer program includes computer-executable instructions, and the instructions are used to implement the above-mentioned method when executed. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Through the following description of the embodiments of the present disclosure with reference to the drawings, the above and other objects, features, and advantages of the present disclosure will become clearer. In the drawings:

[0020] Figure 1Schematically shows an exemplary system architecture to which the method and apparatus according to embodiments of the present disclosure can be applied;

[0021] Figure 2 Schematically shows a flowchart of an information query protection method based on a knowledge graph according to an embodiment of the present disclosure;

[0022] Figure 3 Schematically shows a flowchart of constructing a knowledge graph according to an embodiment of the present disclosure;

[0023] Figure 4 Schematically shows a flowchart of determining noise according to a privacy budget and intimacy according to an embodiment of the present disclosure;

[0024] Figure 5 Schematically shows a flowchart of determining a noise distribution according to a privacy budget and intimacy according to an embodiment of the present disclosure;

[0025] Figure 6 Schematically shows a flowchart of calculating a first degree of association between a node corresponding to an initiating query enterprise and an intermediate enterprise node according to an embodiment of the present disclosure;

[0026] Figure 7 Schematically shows a flowchart of calculating a second degree of association between a node corresponding to a receiving query enterprise and an intermediate enterprise node according to an embodiment of the present disclosure;

[0027] Figure 8 Schematically shows a structural block diagram of an information query protection apparatus based on a knowledge graph according to an embodiment of the present disclosure;

[0028] Figure 9 Schematically shows a block diagram of an electronic device according to an embodiment of the present disclosure. Detailed implementation manners

[0029] Hereinafter, embodiments of the present disclosure will 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 present disclosure. In the following detailed description, for the sake of explanation, many specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure. However, it is obvious that one or more embodiments can be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present disclosure.

[0030] In the technical solutions of the present disclosure, the acquisition, storage, and application of user personal information involved all comply with the provisions of relevant laws and regulations, adopt necessary confidentiality measures, and do not violate public order and good customs. In the technical solutions of the present disclosure, the processing of data such as acquisition, collection, storage, use, processing, transmission, provision, disclosure, and application all comply with the provisions of relevant laws and regulations, adopt necessary confidentiality measures, and do not violate public order and good customs.

[0031] The terms used herein are merely for the purpose of describing specific embodiments and are not intended to limit the present disclosure. The terms "including", "comprising", etc. used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0032] In the case of using expressions such as "at least one of A, B, or C, etc.", generally, it should be interpreted according to the meaning that those skilled in the art usually understand this expression (for example, "a system having at least one of A, B, or C" should include, but is not limited to, a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C). The terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features.

[0033] Differential privacy is a new type of privacy protection mechanism proposed by Dwork in 2006. It mainly solves the problems of how to define privacy when sharing data in privacy protection and how to provide privacy protection when protecting the availability of data publication. Since the definition of differential privacy for privacy does not depend on the background knowledge of the attacker, it is widely used as a new type of privacy protection and model in various fields such as data mining and machine learning. Under the definition of differential privacy, the calculation result of the data set is insensitive to the change of a certain record. Whether a single record is in the data set or not has little impact on the calculation result.

[0034] Therefore, the privacy leakage risk caused by a record's addition to the data set can be controlled within a very small and acceptable range, and the attacker cannot obtain accurate individual information by observing the calculation result. In the definition of differential privacy, the privacy budget can determine the degree of privacy protection. Generally speaking, the smaller the privacy budget, the better the privacy protection, but the more noise is added, resulting in a decrease in the availability of the data.

[0035] In the related art, for a query device that uses differential privacy for privacy protection, it first makes an overall setting for the privacy budget. When a user makes a data query, each time data is accessed, some budget will be deducted. When the number of accesses is too large, the privacy budget will quickly drop to a minimum value, resulting in the data obtained by the query party being almost unusable. In a situation where privacy queries are required, a fixed privacy budget cannot meet the changing query needs of the query party.

[0036] The related art has the following defects. In terms of data availability, the static one does not take into account the changing needs of the query party, resulting in too low data availability for high-authority users. In terms of data security, not setting different privacy budgets for the query party will cause the same query results to lead to the leakage of privacy information when query users with different permissions and credit levels query data with different sensitivities.

[0037] Embodiments of the present disclosure provide a method, device, electronic device, computer-readable storage medium, and computer program product for information query protection based on a knowledge graph. The method for information query protection based on a knowledge graph includes: constructing a knowledge graph; obtaining a query request, where the query request includes an initiating query enterprise, query information, and a receiving query enterprise; based on the knowledge graph, obtaining an intermediate enterprise node that has an association relationship with both the node corresponding to the initiating query enterprise and the node corresponding to the receiving query enterprise; calculating a first association degree between the node corresponding to the initiating query enterprise and the intermediate enterprise node; calculating a second association degree between the node corresponding to the receiving query enterprise and the intermediate enterprise node; calculating the intimacy between the node corresponding to the initiating query enterprise and the node corresponding to the receiving query enterprise according to the first association degree and the second association degree; determining noise according to the privacy budget and the intimacy; and generating privacy data, where the privacy data includes a reply message for the query information and the noise added to the reply message.

[0038] It should be noted that the method, device, electronic device, computer-readable storage medium, and computer program product for information query protection based on a knowledge graph of the present disclosure can be used in the fields of big data and information security technologies, and can also be used in any field other than the fields of big data and information security technologies, such as the financial field. The field of the present disclosure is not limited here.

[0039] Figure 1 Schematically shows an exemplary system architecture 100 to which the method, device, electronic device, computer-readable storage medium, and computer program product for information query protection based on a knowledge graph according to an embodiment of the present disclosure can be applied. It should be noted that Figure 1 The shown is only an example of the system architecture to which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments, or scenarios.

[0040] As shown Figure 1 in FIG. 1, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0041] Users can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the terminal devices 101, 102, 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (for example only).

[0042] The terminal devices 101, 102, 103 may be various electronic devices with a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, and desktop computers, etc.

[0043] The server 105 may be a server providing various services, such as a background management server (for example only) that supports the websites browsed by users using the terminal devices 101, 102, 103. The background management server may analyze and process data such as received user requests, and feedback the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0044] It should be noted that the information query protection method based on the knowledge graph provided by the embodiments of the present disclosure can generally be executed by the server 105. Correspondingly, the information query protection device based on the knowledge graph provided by the embodiments of the present disclosure can generally be set in the server 105. The information query protection method based on the knowledge graph provided by the embodiments of the present disclosure can also be executed by a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and / or the server 105. Correspondingly, the information query protection device based on the knowledge graph provided by the embodiments of the present disclosure can also be set in a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and / or the server 105.

[0045] It should be understood Figure 1 that the numbers of terminal devices, networks, and servers in FIG. 1 are only illustrative. According to actual needs, there may be any number of terminal devices, networks, and servers.

[0046] The following will be based on Figure 1The described scenario, through Figures 2 to 7 describe in detail the information query protection method based on the knowledge graph of the embodiments of the present disclosure.

[0047] Figure 2 Schematically shows a flowchart of the information query protection method based on the knowledge graph according to the embodiments of the present disclosure.

[0048] As Figure 2 shown, the information query protection method based on the knowledge graph of this embodiment includes operation S220 to operation S260 and operation S001 to operation S002.

[0049] As a possible implementation, a knowledge graph can be pre-constructed. As Figure 3 shown, the steps of pre-constructing the knowledge graph include operation S211 to operation S212.

[0050] In operation S211, enterprise data is obtained. Among them, the enterprise data includes entity data and association relationship data. The entity data includes enterprise names, and the association relationship data includes the association relationships between the entity data. For example, enterprise A is a food delivery company, enterprise B is UnionPay, enterprise C is a supplier of enterprise A, the customer payment channel of enterprise A is enterprise B, and enterprise C pays salaries for employees through enterprise B. At this time, enterprise A, enterprise B, and enterprise C are all entity data, and the enterprise names are convenient for distinguishing each enterprise in the entity data. Among them, there is a capital flow relationship between enterprise A and enterprise B, a transaction relationship between enterprise A and enterprise C, a capital flow relationship between enterprise B and enterprise C, the capital flow relationship data between enterprise A and enterprise B, the transaction relationship data between enterprise A and enterprise C, and the capital flow relationship data between enterprise B and enterprise C are all association relationship data.

[0051] In operation S212, a knowledge graph is constructed according to the enterprise data. Among them, nodes are constructed according to the entity data, and edges are constructed according to the association relationship data. Therefore, through operation S211 to operation S212, it is convenient to construct the knowledge graph.

[0052] In some specific examples, when the enterprise data is updated, the knowledge graph is updated according to the updated enterprise data. Thus, the timeliness of the data in the knowledge graph can be ensured, so that the data obtained from the knowledge graph below has good accuracy and high timeliness.

[0053] In operation S220, a query request is obtained. Among them, the query request includes the querying enterprise, the query information, and the receiving query enterprise. Continuing the above example, for example, the querying enterprise is enterprise A, the receiving query enterprise is enterprise B, and the query information is that enterprise A queries the bill details of customers paying to enterprise A through enterprise B in October of this year. Based on the query request initiated by enterprise A, this method can obtain the query request.

[0054] In operation S230, based on the pre-constructed knowledge graph, obtain intermediate enterprise nodes that have an association relationship with both the node corresponding to the query-initiating enterprise and the node corresponding to the query-receiving enterprise. It can be understood that based on the query request, the node corresponding to the query-initiating enterprise can be found in the knowledge graph, that is, node A corresponding to enterprise A, and the node corresponding to the query-receiving enterprise can also be found, that is, node B corresponding to enterprise B. Additionally, intermediate enterprise nodes that have edges with both node A and node B can be found. Continuing with the above example, the intermediate enterprise node is node C corresponding to enterprise C. Of course, there can be multiple intermediate enterprise nodes between the node corresponding to the query-initiating enterprise and the node corresponding to the query-receiving enterprise. Here, only node C is used as an example for illustration, and no further listing is provided.

[0055] In operation S001, calculate the first association degree between the node corresponding to the query-initiating enterprise and the intermediate enterprise node;

[0056] In operation S002, calculate the second association degree between the node corresponding to the query-receiving enterprise and the intermediate enterprise node;

[0057] In operation S240, calculate the intimacy between the node corresponding to the query-initiating enterprise and the node corresponding to the query-receiving enterprise according to the first association degree and the second association degree. For example, the intimacy can be represented by S ij denoted as where i represents the node corresponding to the query-initiating enterprise, j represents the node corresponding to the query-receiving enterprise, x represents the intermediate enterprise node, Γ(i) represents the set of neighbor nodes of node i, Γ(j) represents the set of neighbor nodes of node j, Γ(i)∩Γ(j) represents the set of intermediate enterprise nodes that have an association relationship with both node i and node j, ID(i, x) represents the association degree between node i and node x, that is, the first association degree, and ID(j, x) represents the association degree between node j and node x, that is, the second association degree.

[0058] In operation S250, determine the noise according to the privacy budget and the intimacy.

[0059] As a possible implementation method, as Figure 4 shown, operation S250 determining the noise according to the privacy budget and the intimacy includes operation S251 and operation S252.

[0060] In operation S251, determine the noise distribution according to the privacy budget and the intimacy.

[0061] As some specific examples, the sensitivity can be determined according to the reply information, and the noise distribution is also determined according to the sensitivity. For example, the noise distribution can be where F DSensitivity obtained based on the reply information, ε is the initial privacy budget. The privacy budget generally takes a small value, usually within the range of [0, 1]. Here, the initial privacy budget can be set to 0.01. Of course, the initial privacy budget is not limited to this, and the initial privacy budget can be any value within the range of [0, 1]. S′ ij is the mapped value.

[0062] In some examples, such as Figure 5 shown, operation S251 to determine the noise distribution based on the privacy budget and the intimacy includes operation S2511 and operation S2512.

[0063] In operation S2511, map the intimacy S ij to obtain the mapped value S′ ij , for example, S′ ij = sigmoid(S ij ).

[0064] In operation S2512, determine the noise distribution based on the privacy budget and the mapped value.

[0065] Since the initial privacy budget value generally takes a small value, usually within the range of [0, 1], mapping the intimacy S ij and determining the noise distribution based on the mapped value can make the display effect and rationality of the noise distribution better.

[0066] In some examples, determining the sensitivity based on the reply information includes: determining the first data set of the reply information; after adjusting one or more data in the first data set to obtain the second data set, where the adjustment includes deletion, addition or modification; and determining the sensitivity based on the first data set and the second data set. For example, the sensitivity F D = maX r，r′ |D(r)-D(r′)|, where r is the data set of the reply information, r′ is the data set after adjusting one or more data in the data set of the reply information, the adjustment includes deletion, addition or modification, D(r) is the mean value of the data set r, and D(r′) is the mean value of the data set r′.

[0067] Continuing with the example of querying information to check the bill details that customers of Company A paid to Company A through Company B in October of this year, for the above query information, the reply information can be 20 details of the payments that customers made to Company A through Company B in October of this year. At this time, r is the dataset of the 20 details, r′1 can be the dataset of the remaining 19 details after deleting the smallest amount, r′2 can be the dataset of the remaining 19 details after deleting the middle amount, and r′3 can be the dataset of the remaining 19 details after deleting the largest amount. Calculate the averages of r′1, r′2, and r′3 respectively to obtain D(r′)1, D(r′)2, and D(r′)3. Calculate the differences between the averages of r′1, r′2, and r′3 and the average of r respectively. The differences are the Hellinger distances, and the sensitivity is the maximum Hellinger distance.

[0068] In operation S252, the noise follows a noise distribution. It can be understood that when the intimacy between nodes is higher, the noise is smaller, that is, less noise can be introduced; conversely, the noise is larger, that is, more noise needs to be introduced to protect the data.

[0069] Thus, through operation S251 and operation S252, it is convenient to determine the noise according to the privacy budget and intimacy.

[0070] In operation S260, add the noise to the reply information made for the query information to obtain the private data.

[0071] Among them, as a possible implementation method, the reply information can be a number. Adding the noise to the reply information made for the query information to obtain the private data can be understood as adding the noise value that follows the noise distribution to the reply information, and the private data is the sum.

[0072] As another possible implementation method, the reply information can exist in the form of a function value. Adding the noise value that follows the noise distribution to the function value of the reply information can obtain the private data value, and then the private data value can be converted into private data. For example, the reply information can be a text reply statement. The text reply statement can be converted into a function value through a function model. After adding the function value and the noise value to obtain the private data value, the private data value can be parsed into private data through the function model. The private data can be understood as the reply statement after noise processing.

[0073] As yet another possible implementation method, the noise can be the perturbation degree value that follows the noise distribution. The degree of perturbation introduced to the reply information can be determined according to the noise distribution.

[0074] According to the information query protection method based on a knowledge graph according to an embodiment of the present disclosure, information about the querying enterprise, the receiving query enterprise, and the intermediate enterprise can be efficiently and accurately obtained through the knowledge graph, thereby facilitating the calculation of the intimacy, and further facilitating the determination of noise by jointly considering the privacy budget and the intimacy. Since the noise is determined based on the privacy budget and the intimacy, the privacy budget can be allocated based on the node intimacy. When the relationship between the querying enterprise and the receiving query enterprise changes, the intimacy will change accordingly, so that the privacy budget can be dynamically updated, improving the data availability while ensuring data privacy.

[0075] According to some embodiments of the present disclosure, as Figure 6 shown, operation S001 for calculating the first association degree between the node corresponding to the querying enterprise and the intermediate enterprise node includes operation S0011 and operation S0012.

[0076] In operation S0011, calculate the first degree value of each node corresponding to the querying enterprise.

[0077] In operation S0012, calculate the first association degree based on the first degree value. For example, the association degree between node i and node x where Γ(x) represents the set of neighbor nodes of node x, ki represents the degree value of node i, that is, the number of edges associated with node i, and k x represents the degree value of node x, that is, the number of edges associated with node x.

[0078] According to some embodiments of the present disclosure, as Figure 7 shown, operation S002 for calculating the second association degree between the node corresponding to the receiving query enterprise and the intermediate enterprise node includes operation S0021 and operation S0022.

[0079] In operation S0021, calculate the second degree value of each node corresponding to the receiving query enterprise.

[0080] In operation S0022, calculate the second association degree based on the second degree value. For example, the association degree between node j and node x where k j represents the degree value of node j. That is, the number of edges associated with node j. Thus, through the association degree between node i and node x can be easily obtained, and through the association degree between node j and node x can be easily obtained, so that the intimacy S ij .

[0081] Based on the above information query protection method based on a knowledge graph, the present disclosure also provides an information query protection device 10 based on a knowledge graph. The following will be combined with Figure 8 to describe the information query protection device 10 based on a knowledge graph in detail.

[0082] Figure 8 The structural block diagram of the information query protection device 10 based on the embodiments of the present disclosure is schematically shown.

[0083] The information query protection device 10 based on a knowledge graph includes a first acquisition module 2, a second acquisition module 3, a first calculation module 7, a second calculation module 8, a third calculation module 4, a determination module 5, and an addition module 6.

[0084] The first acquisition module 2 is configured to perform operation S220: acquire a query request, where the query request includes an initiating query enterprise, query information, and a receiving query enterprise.

[0085] The second acquisition module 3 is configured to perform operation S230: based on a pre-constructed knowledge graph, acquire intermediate enterprise nodes that have an association relationship with both the node corresponding to the initiating query enterprise and the node corresponding to the receiving query enterprise.

[0086] The first calculation module 7 is configured to perform operation S001: calculate a first association degree between the node corresponding to the initiating query enterprise and the intermediate enterprise node.

[0087] The second calculation module 8 is configured to perform operation S002: calculate a second association degree between the node corresponding to the receiving query enterprise and the intermediate enterprise node.

[0088] The third calculation module 4 is configured to perform operation S240: calculate the intimacy between the node corresponding to the initiating query enterprise and the node corresponding to the receiving query enterprise according to the first association degree and the second association degree.

[0089] The determination module 5 is configured to perform operation S250: determine noise according to the privacy budget and the intimacy;

[0090] The addition module 6 is configured to perform operation S260: add the noise to the reply information made for the query information to obtain private data.

[0091] An information query protection device based on a knowledge graph according to an embodiment of the present disclosure can efficiently and accurately obtain information about the query - initiating enterprise, the query - receiving enterprise, and the intermediate enterprise through the knowledge graph. Thus, it is convenient to calculate the intimacy, and further, it is convenient to determine the noise jointly by the privacy budget and the intimacy. Since the noise is determined according to the privacy budget and the intimacy, the privacy budget can be allocated based on the node intimacy. When the relationship between the query - initiating enterprise and the query - receiving enterprise changes, the intimacy will change accordingly, so that the privacy budget can be dynamically updated, improving the data availability while ensuring data privacy.

[0092] In addition, according to an embodiment of the present disclosure, any combination of the first acquisition module 2, the second acquisition module 3, the first calculation module 7, the second calculation module 8, the third calculation module 4, the determination module 5, and the addition module 6 can be combined and implemented in one module, or any one of them can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module.

[0093] According to an embodiment of the present disclosure, at least one of the first acquisition module 2, the second acquisition module 3, the first calculation module 7, the second calculation module 8, the third calculation module 4, the determination module 5, and the addition module 6 can be at least partially implemented as a hardware circuit, such as a field - programmable gate array (FPGA), a programmable logic array (PLA), a system - on - chip, a system - on - substrate, a system - on - package, an application - specific integrated circuit (ASIC), or can be implemented by any other reasonable way of integrating or packaging circuits, etc., in hardware or firmware, or implemented in any one of the three implementation manners of software, hardware, and firmware, or in any appropriate combination of several of them.

[0094] Alternatively, at least one of the first acquisition module 2, the second acquisition module 3, the first calculation module 7, the second calculation module 8, the third calculation module 4, the determination module 5, and the addition module 6 can be at least partially implemented as a computer program module. When the computer program module runs, it can execute the corresponding functions.

[0095] Figure 9 A block diagram of an electronic device suitable for implementing the information query protection method based on a knowledge graph according to an embodiment of the present disclosure is schematically shown.

[0096] As Figure 9As 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 section 908 into a random access memory (RAM) 903. The processor 901 may include, for example, a general microprocessor (e.g., CPU), an instruction set processor, and / or a related chipset, and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include on-board 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.

[0097] In the RAM 903, various programs and data required for the operation of the electronic device 900 are stored. The processor 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. The processor 901 performs various operations of the method flow according to an embodiment of the present disclosure by executing the programs in the ROM 902 and / or the RAM 903. It should be noted that the program may also be stored in one or more memories other than the ROM 902 and the RAM 903. The processor 901 may also perform various operations of the method flow according to an embodiment of the present disclosure by executing the programs stored in the one or more memories.

[0098] According to an embodiment of the present disclosure, the electronic device 900 may further include an input / output (I / O) interface 905, and the input / output (I / O) interface 905 is also connected to the bus 904. The electronic device 900 may further include one or more of the following components connected to the I / O interface 905: an input section 906 including a keyboard, a mouse, etc.; an output section 907 including, for example, a cathode ray tube (CRT), a 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, a 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 magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed so that a computer program read from it can be installed into the storage section 908 as needed.

[0099] The present disclosure also provides a computer-readable storage medium, which may be included in the device / device / system described in the above embodiment; or may exist separately without being assembled into the device / device / system. The above computer-readable storage medium carries one or more programs, and when the one or more programs are executed, the method according to an embodiment of the present disclosure is implemented.

[0100] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is 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 of the above. In the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, device, or apparatus. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the above-described ROM 902 and / or RAM 903 and / or one or more memories other than ROM 902 and RAM 903.

[0101] An embodiment of the present disclosure also includes a computer program product, which includes a computer program that contains program code for executing the method shown in the flowchart. When the computer program product runs in a computer system, the program code is used to enable the computer system to implement the method of the embodiment of the present disclosure.

[0102] When the computer program is executed by the processor 901, it executes the above-mentioned functions defined in the system / apparatus of the embodiment of the present disclosure. According to an embodiment of the present disclosure, the above-described systems, apparatuses, modules, units, etc. can be implemented by computer program modules.

[0103] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices and magnetic storage devices. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and be downloaded and installed through the communication part 909, and / or be installed from the removable medium 911. The program code contained in the computer program can be transmitted by any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0104] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or be installed from the removable medium 911. When the computer program is executed by the processor 901, it executes the above-mentioned functions defined in the system of the embodiment of the present disclosure. According to an embodiment of the present disclosure, the above-described systems, devices, apparatuses, modules, units, etc. can be implemented by computer program modules.

[0105] According to embodiments of the present disclosure, program code for executing the computer programs provided by the embodiments of the present disclosure may be written in any combination of one or more programming languages. Specifically, these computing programs may be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. The programming languages include, but are not limited to, programming languages such as Java, C++, Python, the "C" language, or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., by connecting through the Internet using an Internet service provider).

[0106] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and combinations of blocks in the block diagram or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0107] Those skilled in the art will appreciate that the features recited in the various embodiments and / or claims of the present disclosure may be combined and / or combined in various ways, even if such combinations or combinations are not explicitly recited in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features recited in the various embodiments and / or claims of the present disclosure may be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of the present disclosure.

[0108] The embodiments of the present disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments have been described separately above, this does not mean that the measures in each embodiment cannot be used advantageously in combination. The scope of the present disclosure is defined by the appended claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art can make various substitutions and modifications, and all such substitutions and modifications should fall within the scope of the present disclosure.

Claims

1. An information query protection method based on a knowledge graph, characterized in that, Including: Obtain a query request, where the query request includes an initiating query enterprise, query information, and a receiving query enterprise; Based on a pre-constructed knowledge graph, obtain intermediate enterprise nodes that have an association relationship with both the node corresponding to the initiating query enterprise and the node corresponding to the receiving query enterprise; Calculate a first association degree between the node corresponding to the initiating query enterprise and the intermediate enterprise node; Calculate a second association degree between the node corresponding to the receiving query enterprise and the intermediate enterprise node; Calculate the intimacy between the node corresponding to the initiating query enterprise and the node corresponding to the receiving query enterprise according to the first association degree and the second association degree; Determine noise according to the privacy budget and the intimacy; and Add the noise to the reply information made for the query information to obtain privacy data, where the construction steps of the pre-constructed knowledge graph include: Obtain enterprise data, where the enterprise data includes entity data and association relationship data, the entity data includes enterprise names, and the association relationship data includes the association relationships between the entity data; and Construct a knowledge graph according to the enterprise data, where nodes are constructed according to the entity data and edges are constructed according to the association relationship data.

2. The method according to claim 1, wherein When the enterprise data is updated, update the knowledge graph according to the updated enterprise data.

3. The method according to claim 1, characterized in that, The calculating the first association degree between the node corresponding to the initiating query enterprise and the intermediate enterprise node includes: Calculate the first degree value of each node corresponding to the initiating query enterprise; and Calculate the first association degree according to the first degree value.

4. The method according to claim 1, wherein The calculating the second association degree between the node corresponding to the receiving query enterprise and the intermediate enterprise node includes: Calculate the second degree value of each node corresponding to the receiving query enterprise; and Calculate the second association degree according to the second degree value.

5. The method according to claim 1, characterized in that, The determining noise according to the privacy budget and the intimacy includes: Determine a noise distribution according to the privacy budget and the intimacy; and The noise follows the noise distribution.

6. The method according to claim 5, characterized in that, The determining the noise distribution according to the privacy budget and the intimacy includes: Perform a mapping process on the intimacy to obtain a mapping value; and Determine the noise distribution according to the privacy budget and the mapping value.

7. The method according to claim 6, wherein Determine the sensitivity according to the reply information, and the noise distribution is also determined according to the sensitivity.

8. The method according to claim 7, characterized in that, The determining the sensitivity according to the reply information includes: Determine a first data set of the reply information; After adjusting one or more data in the first data set, obtain a second data set, where the adjustment includes deletion, addition, or modification; and Determine the sensitivity according to the first data set and the second data set.

9. An information query protection device based on a knowledge graph, characterized in that Including: A first obtaining module, which is used to execute obtaining a query request, where the query request includes an initiating query enterprise, query information, and a receiving query enterprise; A second obtaining module, which is used to execute obtaining intermediate enterprise nodes that have an association relationship with both the node corresponding to the initiating query enterprise and the node corresponding to the receiving query enterprise based on a pre-constructed knowledge graph; A first computing module configured to perform a calculation of a first degree of association between the node corresponding to the query-initiating enterprise and the intermediate enterprise node; A second computing module configured to perform a calculation of a second degree of association between the node corresponding to the query-receiving enterprise and the intermediate enterprise node; A third computing module configured to perform a calculation of the intimacy between the node corresponding to the query-initiating enterprise and the node corresponding to the query-receiving enterprise according to the first degree of association and the second degree of association; A determination module configured to perform a determination of noise according to the privacy budget and the intimacy; and An addition module configured to perform an addition of the noise to the reply information made for the query information to obtain privacy data, wherein the construction steps of the pre-constructed knowledge graph include: Obtaining enterprise data, wherein the enterprise data includes entity data and association relationship data, the entity data includes enterprise names, and the association relationship data includes the association relationships between the entity data; and Constructing a knowledge graph according to the enterprise data, wherein nodes are constructed according to the entity data and edges are constructed according to the association relationship data.

10. An electronic device, characterized in that, 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 to 8.

11. A computer-readable storage medium, characterized in that, An executable instruction is stored on the storage medium, and when the instruction is executed by the processor, it implements the method according to any one of claims 1 to 8.

12. A computer program product, characterized in that, Comprising a computer program, the computer program comprising one or more executable instructions, which when executed by the processor, implement the method according to any one of claims 1 to 8.

Images