Object processing method, device and equipment based on privacy protection

Abstract

The embodiments of this specification disclose a method, apparatus and device for object processing based on privacy protection, the method comprising: obtaining an object identifier and content risk information of an object accessed by a user, performing differential privacy processing on the object identifier to obtain a processed object identifier, the content risk information including information on whether the object is at risk and the number of visits to the object; sending the processed object identifier and the content risk information of the object to a server so that the server performs restoration processing on the processed object identifier to obtain an object identifier, and determining a target object at risk in the object based on the object identifier and the content risk information; receiving the object identifier of the target object sent by the server, and obtaining target data generated by the user accessing the target object based on the object identifier of the target object; performing differential privacy processing on the object identifier of the target object, and sending the processed object identifier and target data of the target object to the server.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device and apparatus for object processing based on privacy protection. Background Art

[0002] In the era of big data, while data brings huge value, it also brings difficulties in user privacy protection. How to protect user privacy and prevent the leakage of sensitive information in the process of big data development and application has become a new challenge.

[0003] In business scenarios such as marketing and information recommendation, attention is usually paid to objects with high access volume (such as certain data or applications), while in the security field, attention is usually paid to objects with high risks. The proportion of high-risk objects in the total access volume is often low, which means that if high-risk objects need to be mined from a large number of objects or object sets, more privacy processing work is required, resulting in an increased risk of user privacy leakage. Therefore, it is necessary to provide a technical solution with a lower risk of user privacy leakage. Summary of the invention

[0004] The purpose of the embodiments of this specification is to provide a technical solution with a lower risk of user privacy leakage.

[0005] In order to implement the above technical solution, the embodiments of this specification are implemented as follows:

[0006] An object processing method based on privacy protection is provided in an embodiment of the present specification. The method includes: obtaining an object identifier of an object accessed by a user and content risk information of the object, performing differential privacy processing on the object identifier to obtain a processed object identifier, and the content risk information includes information on whether the object is at risk and the number of visits to the object. The processed object identifier and the content risk information of the object are sent to a server so that the server performs a restoration process on the processed object identifier to obtain the object identifier, and based on the object identifier and the content risk information, a target object at risk in the object is determined. The object identifier of the target object sent by the server is received, and the target data generated by the user accessing the target object is obtained based on the object identifier of the target object. The object identifier of the target object is differentially privacy processed, and the processed object identifier of the target object and the target data are sent to the server.

[0007] An object processing method based on privacy protection is provided in an embodiment of the present specification, and the method comprises: receiving an object identifier of an object accessed by a user and processed by differential privacy and content risk information of the object sent by a terminal device, wherein the content risk information comprises information on whether the object is at risk and the number of visits to the object. The object identifier after differential privacy processing is restored to obtain a restored object identifier. Based on the restored object identifier and the content risk information, a target object at risk in the object is determined. The object identifier of the target object is sent to the terminal device to obtain target data generated by the user accessing the target object from the terminal device.

[0008] An object processing device based on privacy protection is provided in an embodiment of the present specification. The device includes: a first differential privacy module, which obtains the object identification of an object accessed by a user and the content risk information of the object, performs differential privacy processing on the object identification to obtain the processed object identification, and the content risk information includes information on whether the object is at risk and the number of visits to the object. An information sending module, which sends the processed object identification and the content risk information of the object to a server, so that the server performs restoration processing on the processed object identification to obtain the object identification, and determines the target object at risk in the object based on the object identification and the content risk information. An identification receiving module, which receives the object identification of the target object sent by the server, and obtains the target data generated by the user accessing the target object based on the object identification of the target object. A second differential privacy module, which performs differential privacy processing on the object identification of the target object, and sends the processed object identification of the target object and the target data to the server.

[0009] An object processing device based on privacy protection is provided in an embodiment of the present specification, and the device includes: an information receiving module, which receives an object identifier of an object accessed by a user and processed by differential privacy, and content risk information of the object, which is sent by a terminal device, and the content risk information includes information on whether the object is at risk and the number of visits to the object. A restoration module, which performs restoration processing on the object identifier after differential privacy processing to obtain a restored object identifier. An object determination module, which determines a target object at risk among the objects based on the restored object identifier and the content risk information. An identifier sending module, which sends the object identifier of the target object to the terminal device to obtain target data generated by the user accessing the target object from the terminal device.

[0010] An object processing device based on privacy protection is provided in an embodiment of the present specification. The object processing device based on privacy protection includes: a processor; and a memory arranged to store computer executable instructions. When the executable instructions are executed, the processor: obtains an object identification of an object accessed by a user and content risk information of the object, performs differential privacy processing on the object identification, and obtains a processed object identification. The content risk information includes information on whether the object is at risk and the number of visits to the object. The processed object identification and the content risk information of the object are sent to a server so that the server performs restoration processing on the processed object identification to obtain the object identification, and determines a target object at risk in the object based on the object identification and the content risk information. The object identification of the target object sent by the server is received, and the target data generated by the user accessing the target object is obtained based on the object identification of the target object. The object identification of the target object is differentially privacy processed, and the processed object identification of the target object and the target data are sent to the server.

[0011] An object processing device based on privacy protection is provided in an embodiment of the present specification. The object processing device based on privacy protection includes: a processor; and a memory arranged to store computer executable instructions, wherein the executable instructions, when executed, cause the processor to: receive an object identifier of an object accessed by a user and processed by differential privacy and content risk information of the object, which is sent by a terminal device, and the content risk information includes information on whether the object is at risk and the number of visits to the object. Perform a restoration process on the object identifier after differential privacy processing to obtain a restored object identifier. Based on the restored object identifier and the content risk information, determine a target object at risk in the object. Send the object identifier of the target object to the terminal device to obtain target data generated by the user accessing the target object from the terminal device.

[0012] The embodiments of this specification also provide a storage medium, wherein the storage medium is used to store computer executable instructions, and the executable instructions implement the following process when executed: obtaining the object identification of the object accessed by the user and the content risk information of the object, performing differential privacy processing on the object identification to obtain the processed object identification, and the content risk information includes information on whether the object is at risk and the number of visits to the object. Sending the processed object identification and the content risk information of the object to a server so that the server performs restoration processing on the processed object identification to obtain the object identification, and determining the target object at risk in the object based on the object identification and the content risk information. Receive the object identification of the target object sent by the server, and obtain the target data generated by the user accessing the target object based on the object identification of the target object. Perform differential privacy processing on the object identification of the target object, and send the processed object identification of the target object and the target data to the server.

[0013] The embodiments of this specification also provide a storage medium, wherein the storage medium is used to store computer executable instructions, and the executable instructions implement the following process when executed: receiving an object identifier of an object accessed by a user and processed by differential privacy and content risk information of the object sent by a terminal device, wherein the content risk information includes information on whether the object is at risk and the number of visits to the object. Performing a restoration process on the object identifier after differential privacy processing to obtain a restored object identifier. Based on the restored object identifier and the content risk information, determining a target object at risk in the object. Sending the object identifier of the target object to the terminal device to obtain target data generated by the user accessing the target object from the terminal device. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0015] Figure 1A This is an embodiment of an object processing method based on privacy protection in this specification;

[0016] Figure 1B This is a schematic diagram of an object processing process based on privacy protection in this specification;

[0017] Figure 2This is a schematic diagram of the structure of a system for object processing based on privacy protection in this specification;

[0018] Figure 3 This is a schematic diagram of another object processing process based on privacy protection in this specification;

[0019] Figure 4 This is a schematic diagram of another object processing process based on privacy protection in this specification;

[0020] Figure 5A This is another embodiment of an object processing method based on privacy protection in this specification;

[0021] Figure 5B This is a schematic diagram of another object processing process based on privacy protection in this specification;

[0022] Figure 6 This is a schematic diagram of another object processing process based on privacy protection in this specification;

[0023] Figure 7 This is an embodiment of an object processing device based on privacy protection in this specification;

[0024] Figure 8 This is another embodiment of an object processing device based on privacy protection in this specification;

[0025] Fig. 9 This is an embodiment of an object processing device based on privacy protection in this specification. DETAILED DESCRIPTION

[0026] The embodiments of this specification provide a method, apparatus and device for object processing based on privacy protection.

[0027] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0028] Embodiment 1

[0029] like Figure 1A and Figure 1BAs shown, the embodiment of this specification provides an object processing method based on privacy protection. The execution subject of the method can be a terminal device, wherein the terminal device can be a mobile phone, a tablet computer, a personal computer, etc. The terminal device can be a terminal device capable of running an application, and the application includes a host program and any small program installed in the host program, and / or the terminal device can be a terminal device that provides a user with access to a certain object. The method can specifically include the following steps:

[0030] In step S102, the object identifier of the object accessed by the user and the content risk information of the object are obtained, and differential privacy processing is performed on the object identifier to obtain a processed object identifier. The content risk information includes information on whether the object has risks and the number of visits to the object.

[0031] Among them, the user can be any user, and in the embodiment of this specification, the user can use or access the user of an object. The object can be any object accessible to the user, specifically, the object can be a certain data, a certain file, an application or an account, etc., wherein the certain data can be analog data such as sound and image, or digital data such as symbols and text, wherein the certain file can be a video file, an audio file, a text document, etc., wherein the application can be a program written in one or more different programming languages, the application can be an application that runs independently without other host programs, or it can be a small program carried in the host program, for example, the host program can be a financial application, and the target application can be a small program developed by a logistics agency that can be carried in the financial application, etc. The object identifier can be set according to the object, for example, if the object is an application, the object identifier can be the name or code of the application, etc. Differential privacy aims to protect the above-mentioned collected data to a certain extent when the user of the collected data does not trust the data collector, although the user will still upload the corresponding data to the data collector. Differential privacy can maximize the accuracy of data queries when querying from a statistical database, while minimizing the probability of identifying its records. Differential privacy is to protect privacy by perturbing data, and the perturbation mechanism can include multiple ones, such as Laplace mechanism, exponential mechanism, etc. Differential privacy can include centralized differential privacy and local differential privacy (LDP). Local differential privacy means that before the data to be uploaded is collected, the user first perturbs the data to be uploaded locally, and then uploads the noisy data to be uploaded to the server (or service center). Local differential privacy can include the following definition: Algorithm A is local differential privacy (∈-LDP) satisfied by ∈, where ∈≥0, if and only if for any two data v and v', the following formula is satisfied:

[0032]

[0033] Among them, v and v' belong to the definition domain of A, and y belongs to the value range of A. From the user's perspective, localized differential privacy can better protect the privacy of user data. Before the user data is collected, it has been disturbed locally, and the private content in the user data has been erased. The differential privacy in the embodiments of this specification can be the above-mentioned localized differential privacy.

[0034] In practice, in the era of big data, while data brings huge value, it also brings difficulties in user privacy protection. How to protect user privacy and prevent the leakage of sensitive information in the process of big data development and application has become a new challenge.

[0035] In business scenarios such as marketing and information recommendation, it is usually necessary to focus on objects with high access volume (such as certain data or applications, etc.), while in the security field, it is usually necessary to focus on objects with high risks, and the proportion of high-risk objects in the total access volume is often low, which means that if it is necessary to mine high-risk objects from a large number of objects or object sets, more privacy processing work is required, resulting in an increased risk of user privacy leakage, so it is necessary to provide a technical solution with a lower risk of user privacy leakage. This embodiment provides a technical solution, which may specifically include the following contents:

[0036] The objects that need to be detected can be pre-set according to the actual situation, and then the detection points can be pre-buried for the above objects. The information of the objects being visited can be recorded through the pre-buried detection points, which may include the time of the object being visited, the current location, the object identifier, and the relevant information of the visitor (such as the visitor's account information, the visitor's operation behavior data, etc.), as well as the cumulative number of visits to the object and the relevant information of whether the object has risks (such as the risk of user privacy leakage or fraud, etc.). It should be noted that whether the object has risks can be determined in a variety of ways. For example, whether the object has risks can be determined based on the business to which the object belongs. The business of the object pre-determined that there are objects with risks or the accounts registered in the object have risks. Alternatively, when the pre-buried detection point detects that the object is visited, it can be determined based on the relevant information or historical data of the object. Alternatively, the object can be detected and determined based on a pre-trained risk detection model, or it can be determined based on user complaints or reports, etc. It can be set according to the actual situation, and the embodiments of this specification do not limit this. When it is necessary to provide relevant data to the server, the object identifier of the object accessed by the user and the content risk information of the object can be obtained from the information recorded by the pre-embedded detection point. The object can be one or more (in this case, the obtained object identifiers can include multiple ones, and the content risk information of the object can include content risk information of multiple different objects, etc.).

[0037] It should be noted that the time for obtaining the object identification of the object accessed by the user and the content risk information of the object can include multiple times. For example, the object identification of the object accessed by the user and the acquisition of the content risk information of the object can be triggered at a preset period (such as every 7 days or 10 days, etc.), or the terminal device can trigger the acquisition of the object identification of the object accessed by the user and the content risk information of the object from time to time, etc. The specific setting can be based on actual conditions, and the embodiments of this specification are not limited to this.

[0038] Since the object identifier of the object accessed by the user and the content risk information of the object obtained above often contain the user's privacy information, in order to protect the user's privacy during data transmission, the above information can be processed by differential privacy. Specifically, in order to avoid the leakage of the user's privacy data such as which objects the user accesses, the object identifier of the object accessed by the user can be differentially privately processed, so that the object identifier of the object is disturbed. Even if the above data is leaked, the object identifier in the data cannot be identified, so that the object accessed by the user will not be known to others, protecting the user's privacy. Among them, differential privacy can include a variety of implementable methods. Taking the differential privacy algorithm of the exponential mechanism as an example, it can include: performing differential privacy processing on the object identifier through the differential privacy algorithm of the exponential mechanism to obtain the processed object identifier. Specifically, for the differential privacy algorithm of the exponential mechanism, let the output domain of the query function be R, and for each output value r∈R in the output domain, the function q(D, r)→R becomes the availability function of the output value r, which is used to evaluate the quality of the output value r. If the input of random algorithm M is data set D, the output is object r∈R, function q(D, r)→R is the availability function, Δq is the sensitivity of function q(D, r)→R, and algorithm M selects and outputs r from R with a probability proportional to exp(∈q(D, r) / 2Δq), then algorithm M provides ∈-differential privacy protection. Based on the above method, for the input of algorithm M is object identity, the output value r∈R corresponding to the object identity, algorithm M selects and outputs r from R with a probability proportional to exp(∈q(object identity, r) / 2Δq), thereby obtaining the object identity after differential processing.

[0039] It should be noted that the above processing process is only one feasible way of differential privacy. In practical applications, in addition to the above processing method, differential privacy processing can also be performed on the object identifier in a variety of ways, which can be set according to actual conditions, and the embodiments of this specification do not limit this. In addition, the above only performs differential privacy processing on the object identifier. In practical applications, differential privacy processing can also be performed on the content risk information of the object, that is, differential privacy processing can be performed on the information whether the object is risky and the number of visits to the object, etc., to obtain the processed data, and then send the processed data to the server, which can be set according to actual conditions, and the embodiments of this specification do not limit this.

[0040] For example, the above-mentioned object is a mini-program installed in a host program. In actual applications, usually, the host program and the mini-program do not belong to the same developer, that is, relative to the host program, the mini-program is usually a third-party application. For example, the host program can be an instant messaging application, and the mini-program can be a program developed by a game development organization that can be installed in an instant messaging application, etc.; or, the host program can be a financial application, and the mini-program can be a program developed by a logistics organization that can be installed in a financial application, etc. In some scenarios, some mini-programs may be risky. For this reason, detection points can be pre-embedded in the host program. The pre-embedded detection points record the program identification of each mini-program in the host program and the content risk information of the mini-program. The content risk information includes information on whether the mini-program is risky and the number of visits to the mini-program.

[0041] In order to avoid the leakage of user privacy data such as which mini-programs the user uses, differential privacy processing can be performed on the program identifiers of the mini-programs used by the user, so that the program identifiers of the mini-programs are disrupted. Even if the above data is leaked, the program identifiers in the data cannot be identified, so that the mini-programs used by the user will not be known to others, thereby protecting the user's privacy.

[0042] In step S104, the processed object identification and the content risk information of the object are sent to the server, so that the server restores the processed object identification to obtain the object identification, and determines the target object with risks in the object based on the object identification and the content risk information.

[0043] The server may be a server for risk prevention and control, or a server for building a risk prevention and control mechanism, etc.

[0044] In implementation, Figure 2As shown, after obtaining the processed object identification and the object content risk information in the above manner, the processed object identification and the object content risk information can be sent to the server. The server may restore the processed object identifier to obtain the original object identifier, wherein the restoration processing of the processed object identifier may be based on the differential privacy algorithm used in the process of performing differential privacy processing on the original object identifier to determine the algorithm to be used in the restoration processing. For example, if the processed object identifier is obtained by performing differential privacy processing on the differential privacy algorithm based on the Laplace mechanism, then the restoration processing of the processed object identifier may be performed by restoring the processed object identifier according to the inverse algorithm of the differential privacy algorithm based on the Laplace mechanism or the inverse process of the processing process corresponding to the differential privacy algorithm based on the Laplace mechanism. For example, the processing process corresponding to the differential privacy algorithm based on the Laplace mechanism may be to first execute process A, then execute process B through the processing result of process A, and finally execute process C through the processing result of process B to obtain the processed object identifier. The inverse process of the above processing process may be to first execute process C, then execute process B through the processing result of process C, and finally execute process A through the processing result of process B to obtain the restored object identifier (i.e., the original object identifier). The server can determine the target objects with risks among the above objects based on the restored object identification and the above content risk information. Specifically, each object can be set with information on whether there is a risk. The information can be presented in a variety of different ways. For example, it can be marked in the form of a label to indicate whether an object is at risk. If a label indicating the existence of a risk (also called a risk label) is set in an object, it indicates that the object is at risk. The object identification that is at risk and whose access volume exceeds a predetermined threshold can be used as the object identification of the target object, thereby determining the target objects with risks among the above objects.

[0045] In step S106, the object identification of the target object sent by the server is received, and the target data generated by the user accessing the target object is acquired based on the object identification of the target object.

[0046] Among them, the target data can be data for the target object, which can also include data generated during the user's access to the target object. In actual applications, the target data can include the content risk information as described above (i.e., information on whether the target object is at risk and the number of visits to the object, etc.). The target data can be data used to train a certain model (such as a risk identification model, etc.), or data used to process a certain business, etc. It can be set specifically according to actual conditions, and the embodiments of this specification do not limit this.

[0047] During implementation, after the server determines the target object, it can send the object identifier of the target object to the terminal device. The terminal device can record the data generated by the user's access to the target object. After the terminal device receives the object identifier of the target object, it can obtain data related to a certain business or data for training a certain model from the above-mentioned recorded data based on the object identifier of the target object, and can use the obtained data as the target data generated by the user's access to the target object.

[0048] In step S108, differential privacy processing is performed on the object identifier of the target object, and the processed object identifier and target data of the target object are sent to the server.

[0049] The specific processing of the above step S108 can refer to the relevant content in the above step S102. It should be noted that the above only performs differential privacy processing on the object identifier of the target object. In actual applications, differential privacy processing can also be performed on the target data to obtain processed data, and then the processed data is sent to the server. The specific setting can be based on actual conditions, and this specification embodiment does not limit this.

[0050] For example, the long short-term memory model can be trained by the acquired object identification and target data to obtain a trained long short-term memory model, or the DeepFM model can be trained by the acquired object identification and target data to obtain a trained DeepFM model, etc.

[0051] The embodiments of this specification provide an object processing method based on privacy protection, which obtains the object identifier of the object accessed by the user and the content risk information of the object, performs differential privacy processing on the object identifier, and obtains the processed object identifier. The content risk information includes information on whether the object is risky and the number of visits to the object. The processed object identifier and the content risk information of the object are sent to the server, so that by performing differential privacy processing on the object identifier of the object accessed by the user, even if the above data is stolen by other people, it is impossible to know which mini-program the user is using, thereby protecting the user's privacy from being leaked. Then, the object identifier of the target object sent by the server is received, and based on the object identifier of the target object, the target data generated by the user accessing the target object is obtained, the object identifier of the target object is differentially privacy processed, and the object identifier and target data of the processed target object are sent to the server, so that for the access of the object, the corresponding data is obtained through a two-round mechanism for uploading, while protecting the user's privacy, the data can achieve high availability.

[0052] Embodiment 2

[0053] like Figure 3As shown, the embodiment of this specification provides an object processing method based on privacy protection. The execution subject of the method can be a terminal device, wherein the terminal device can be a mobile phone, a tablet computer, a personal computer, etc. The terminal device can be a terminal device capable of running an application, the application includes a host program and any small program installed in the host program, and / or the terminal device can be a terminal device that provides a user with access to a certain object. The corresponding object processing system based on privacy protection can be as follows Figure 2 The method may specifically include the following steps:

[0054] In step S302, the object identifier of the object accessed by the user and the content risk information of the object are obtained. The content risk information includes information on whether the object has risks and the number of visits to the object.

[0055] Among them, the above-mentioned objects may include mini-programs installed in the host program. In actual applications, usually, the host program and the mini-program do not belong to the same developer, that is, relative to the host program, the mini-program is usually a third-party application. The above-mentioned objects may include one or more mini-programs accessed by a certain user (such as user A accessed mini-program 1 and mini-program 2), or one or more mini-programs accessed by multiple different users (such as user A accessed mini-program 1 and mini-program 2, user B accessed mini-program 1, mini-program 4 and mini-program 5, etc.). The object identifier can be the name or code of the mini-program, etc. In actual applications, the object identifier can be an identifier set in the host program for the mini-program to uniquely identify the mini-program, and the object identifier can be AppID (Application IDentification).

[0056] The specific processing process of the above step S302 can refer to the relevant content in the above embodiment 1, which will not be repeated here.

[0057] The specific processing of differential privacy processing of object identifiers may include a variety of different implementation methods. An optional processing method is provided below. For details, please refer to the following step S304.

[0058] In step S304, the object identifier is subjected to a first encoding process to obtain a first encoded object identifier, and each bit of the encoded data in the first encoded object identifier is scrambled according to a preset first probability to obtain a scrambled object identifier, and the scrambled object identifier is used as the object identifier after differential privacy processing.

[0059] Among them, the first probability can be determined by a perturbation function, input data, output data, probability and privacy budget parameters, etc., and can be set specifically according to actual conditions, and the embodiments of this specification do not limit this.

[0060] In implementation, there may be multiple specific processing methods for encoding an object identifier. For example, the object identifier may be encoded by a preset encoder or encoding algorithm, thereby performing a first encoding process on the object identifier, and finally obtaining a first encoded object identifier. Alternatively, the object identifier may be first encoded by a preset filter, and the first encoded object identifier may be obtained in the process of processing through the filter. The first encoded object identifier is determined by two optional methods below. Please refer to the following method 1 and method 2 for details.

[0061] Method 1: Based on a preset first Hash algorithm, the object identifier is subjected to a first encoding process to obtain a first encoded object identifier.

[0062] The first hash algorithm may be any hash algorithm, such as MD4, MD5 or SHA-1.

[0063] In implementation, a hash algorithm for encoding object identifiers can be pre-set. After obtaining the object identifier of the object accessed by the user and the content risk information of the object, the object identifier can be calculated using the preset hash algorithm to obtain a hash value corresponding to the object identifier. The obtained hash value can be used as the first encoded object identifier.

[0064] Method 2: Perform a first encoding process on the object identifier based on the first Bloom filter to obtain a first encoded object identifier.

[0065] Among them, the first Bloom filter can be composed of a binary vector and a series of random mapping functions (which can be hash functions). The first Bloom filter can be used to retrieve whether an object is in a set. The first Bloom filter can improve space efficiency and reduce query time. Each position in the array corresponding to the first Bloom filter occupies only 1 bit, and each bit has only two states: 0 and 1. Assume that there are k hash functions, and the output range of each hash function is greater than m. Then, the output value is modulo k (% m), and k [0, m-1] values ​​will be obtained. Since each hash function is independent of each other, the above k values ​​are also independent of each other. Finally, the above k values ​​are mapped to [0, m-1] and marked (can be marked as 1).

[0066] In implementation, if the input data is represented by x, and i is the output data, I is the set of output data. The hash function set H contains k different hash functions. Any function hj∈H maps the input data x to the integer range m, and hj:I→[m], where ∈ represents the privacy budget parameter. Then a value j is randomly selected in the k range as the index for selecting the jth hash function, a vector u of length m is initialized, all elements of the vector u are set to 0 (or 1), and the element uhj(x) in the vector u is set to 1 (or 0). The final vector u is the encoded object identifier. By encoding the object identifier through the above-mentioned first Bloom filter, an array composed of 0 and 1 (which can be a bit array) can be obtained, and the above-mentioned array obtained is the first encoded object identifier.

[0067] It should be noted that the above-mentioned processing of encoding the object identifier is only two optional processing methods. In practical applications, in addition to being implemented in the above-mentioned methods, it can also be implemented in a variety of different ways, which can be set according to actual conditions.

[0068] After determining the first encoded object identifier in the above manner, each element in the vector u (the first encoded object identifier) ​​is flipped with a predetermined probability, that is, the element 0 is changed to 1 or the element 1 is changed to 0 to obtain the disturbed object identifier. Finally, the disturbed object identifier and index j can be obtained, and the disturbed object identifier can be used as the object identifier after differential privacy processing.

[0069] It should be noted that different privacy processing budgets can also be given to different objects (such as accounts, etc.). For example, higher-risk accounts can be given larger privacy processing budgets, while high-quality accounts can be given smaller privacy processing budgets, so as to better balance data availability and privacy protection. Based on this, differential privacy processing is performed on the above-mentioned object identifier in the above-mentioned step S304 to obtain the processed object identifier, which can also include the processing of the following steps A2-A6.

[0070] In step A2, based on the content risk information of the object, the risk level corresponding to the object is determined.

[0071] In implementation, different risk levels can be pre-set according to actual conditions, such as high risk and low risk, etc. Based on this, the content risk information of the object can include information on whether there is a risk, and can also include relevant information on the risk value. In this way, the terminal device can compare the risk value with a preset risk threshold based on the information on whether there is a risk and relevant information on the risk value contained in the content risk information of the above object. If the risk value is greater than the risk threshold, the risk level corresponding to the object can be high risk. If the risk value is less than the risk threshold, the risk level corresponding to the object can be low risk, so that the risk level corresponding to the object can be obtained.

[0072] In step A4, a third probability matching the risk level corresponding to the object is obtained.

[0073] In implementation, different disturbance probabilities can be set for different risk levels. For example, a higher disturbance probability can be set for high risk and a lower disturbance probability can be set for low risk, so that the disturbance probability corresponding to the risk level corresponding to the above object can be obtained, that is, the third probability.

[0074] In step A6, the object identifier is subjected to a third encoding process to obtain a third encoded object identifier, and each bit of the encoded data in the third encoded object identifier is scrambled by a third probability to obtain a scrambled object identifier, and the scrambled object identifier is used as the object identifier after differential privacy processing.

[0075] Among them, the above-mentioned object identifier can be subjected to third encoding processing based on a preset hash algorithm to obtain a third-encoded object identifier, or the above-mentioned object identifier can be subjected to third encoding processing based on a preset Bloom filter to obtain a third-encoded object identifier. For specific processing, please refer to the above-mentioned related content, which will not be repeated here.

[0076] In step S306, the content risk information of the object is encrypted to obtain encrypted content risk information.

[0077] Among them, the encryption algorithm used for the above encryption processing may include one or more of a homomorphic encryption algorithm, a partially homomorphic encryption algorithm and a full-state encryption algorithm. A homomorphic encryption algorithm may allow the encrypted ciphertext to be processed, and the result obtained is still an encrypted result, that is, the result obtained by directly processing the encrypted ciphertext is the same as the result obtained by encrypting the result obtained after the above processing of the plaintext (i.e., the original text before encryption). The full-state encryption algorithm may be a fully homomorphic encryption algorithm.

[0078] In implementation, in order to protect the security of data when a user uses an object or accesses an object, in addition to differential privacy processing of the object identifier, the content risk information of the object can also be encrypted. To this end, an encryption algorithm can be set in advance, such as a homomorphic encryption algorithm, etc. Then, the set encryption algorithm can be used to encrypt the content risk information of the above-mentioned object to obtain the encrypted content risk information.

[0079] In step S308, the processed object identifier and the encrypted content risk information are sent to the server, so that the server restores the processed object identifier to obtain the above-mentioned object identifier, and decrypts the encrypted content risk information to obtain the above-mentioned content risk information, and based on the above-mentioned object identifier and the above-mentioned content risk information, determines the target object with risks among the above-mentioned objects.

[0080] In implementation, after receiving the processed object identifier and the encrypted content risk information, the server may restore the processed object identifier. Specifically, the server may scramble each bit of the encoded data in the first encoded object identifier based on the probability corresponding to the first probability.

[0081] The object identifier is subjected to a first encoding process to obtain a first encoded object identifier, and the inverse process of the above-mentioned scrambling process is performed on each bit of the encoded data in the processed object identifier by a preset first probability, and then the result obtained by the inverse process is subjected to an inverse process based on the first encoding process to restore the processed object identifier to obtain the above-mentioned object identifier. Accordingly, based on the encryption algorithm corresponding to the encryption process of the content risk information of the above-mentioned object, the decryption algorithm corresponding to the encryption algorithm can be determined to obtain the above-mentioned content risk information. Based on the above-mentioned object identifier and the above-mentioned content risk information, the target object with risks in the above-mentioned object can be determined. For the specific process, please refer to the above-mentioned related content, which will not be repeated here.

[0082] In step S310, an object identifier of a target object sent by a server is received, and target data generated when a user accesses the target object is acquired based on the object identifier of the target object.

[0083] In step S312, a second encoding process is performed on the object identifier of the target object to obtain the second encoded object identifier of the target object, and each bit of the encoded data in the second encoded object identifier of the target object is scrambled according to a preset second probability to obtain the scrambled object identifier of the target object, and the scrambled object identifier of the target object is used as the differentially private processed object identifier of the target object.

[0084] The second probability may be determined by a perturbation function, input data, output data, probability, and privacy budget parameters, etc., and may be set according to actual conditions, and the embodiments of this specification do not limit this. The second probability may be the same as the first probability or different from the first probability.

[0085] The second encoded object identifier of the target object is determined in two optional ways below. For details, refer to the following way 1 and way 2.

[0086] Method 1: Based on a preset second Hash algorithm, a second encoding process is performed on the object identifier of the target object to obtain a second encoded object identifier of the target object.

[0087] The second hash algorithm may be any hash algorithm, such as MD4, MD5 or SHA-1, etc. The second hash algorithm may be the same as the first hash algorithm, or may be different from the first hash algorithm.

[0088] The specific processing process of the above method 1 can be found in the above related content, which will not be repeated here.

[0089] Method 2: Perform a second encoding process on the object identifier of the target object based on the second Bloom filter to obtain a second encoded object identifier of the target object.

[0090] The second Bloom filter may be the same as the first Bloom filter or may be different from the first Bloom filter.

[0091] The specific processing process of the above method 2 can be found in the above related content, which will not be repeated here.

[0092] Correspondingly, different privacy processing budgets can be given to different target objects to better balance data availability and privacy protection. Based on this, differential privacy processing of the object identifier of the above target object in the above step S312 can also include the following steps B2-B6.

[0093] In step B2, based on the target data, the risk level corresponding to the target object is determined.

[0094] In step B4, a fourth probability matching the risk level corresponding to the target object is obtained.

[0095] In step B6, the object identifier of the target object is subjected to a fourth encoding process to obtain the fourth encoded object identifier of the target object, and each bit of the encoded data in the fourth encoded object identifier of the target object is scrambled by a fourth probability to obtain the scrambled object identifier of the target object, and the scrambled object identifier of the target object is used as the object identifier of the target object after differential privacy processing.

[0096] Among them, the object identifier of the above-mentioned target object can be subjected to fourth encoding processing based on a preset hash algorithm to obtain a fourth-encoded object identifier, or the object identifier of the above-mentioned target object can be subjected to fourth encoding processing based on a preset Bloom filter to obtain a fourth-encoded object identifier. For specific processing, please refer to the above-mentioned related content and will not be repeated here.

[0097] In step S314, the target data is encrypted to obtain encrypted target data.

[0098] Among them, the encryption algorithm used for the above encryption processing may include one or more of a homomorphic encryption algorithm, a partially homomorphic encryption algorithm and a full-state encryption algorithm.

[0099] The specific processing process of the above step S314 can refer to the above related content and will not be repeated here.

[0100] In step S316, the processed object identifier of the target object and the encrypted target data are sent to the server.

[0101] The embodiments of this specification provide an object processing method based on privacy protection, which obtains the object identifier of the object accessed by the user and the content risk information of the object, performs differential privacy processing on the object identifier, and obtains the processed object identifier. The content risk information includes information on whether the object is risky and the number of visits to the object. The processed object identifier and the content risk information of the object are sent to the server, so that by performing differential privacy processing on the object identifier of the object accessed by the user, even if the above data is stolen by other people, it is impossible to know which mini-program the user is using, thereby protecting the user's privacy from being leaked. Then, the object identifier of the target object sent by the server is received, and based on the object identifier of the target object, the target data generated by the user accessing the target object is obtained, the object identifier of the target object is differentially privacy processed, and the object identifier and target data of the processed target object are sent to the server, so that for the access of the object, the corresponding data is obtained through a two-round mechanism for uploading, while protecting the user's privacy, the data can achieve high availability.

[0102] Embodiment 3

[0103] like Figure 4As shown, the embodiment of this specification provides an object processing method based on privacy protection. The execution subject of the method can be a terminal device, wherein the terminal device can be a mobile phone, a tablet computer, a personal computer, etc. The terminal device can be a terminal device capable of running an application, and the application includes a host program and any small program installed in the host program, and / or the terminal device can be a terminal device that provides a user with access to a certain object. The method can specifically include the following steps:

[0104] In step S402, the object identifier of the object accessed by the user and the content risk information of the object are obtained. The content risk information includes information on whether the object has risks and the number of visits to the object.

[0105] The above-mentioned objects may include small programs installed in the host program.

[0106] The specific processing process of the above step S402 can refer to the relevant content in the above embodiment 1, which will not be repeated here.

[0107] In step S404, the object identifier is subjected to a first encoding process to obtain a first encoded object identifier, and the first encoded object identifier is subjected to a noise disturbance process using predetermined first noise data to obtain a noise-disturbed object identifier, and the noise-disturbed object identifier is used as the object identifier after differential privacy processing.

[0108] The object identifier after the first encoding is determined in two optional ways below. For details, see the following way 1 and way 2.

[0109] Method 1: Based on a preset first Hash algorithm, the object identifier is subjected to a first encoding process to obtain a first encoded object identifier.

[0110] Method 2: Perform a first encoding process on the object identifier based on the first Bloom filter to obtain a first encoded object identifier.

[0111] In addition, randomized noise data or specified noise data (such as Laplace noise data or Gaussian noise data, etc.) can be input into the first encoded object identifier to perform noise interference processing on the first encoded object identifier, thereby masking the first encoded object identifier, so that even if the noise-interrupted object identifier is leaked, others will not be able to distinguish which data or data set generated the above-mentioned data, thereby protecting the privacy of the user.

[0112] The specific processing process of the above step S404 can refer to the relevant content in the above embodiment 2, which will not be repeated here.

[0113] Correspondingly, different privacy processing budgets can be given to different objects to better balance data availability and privacy protection. Based on this, the differential privacy processing of the above-mentioned object identifier in the above-mentioned step S404 can also include the processing of the following steps C2-C6.

[0114] In step C2, based on the content risk information of the object, the risk level corresponding to the object is determined.

[0115] In step C4, third noise data matching the risk level corresponding to the object is obtained.

[0116] In step C6, the object identifier is subjected to a third encoding process to obtain a third encoded object identifier, and the third encoded object identifier is subjected to noise disturbance processing through third noise data to obtain a noise-disturbed object identifier, and the noise-disturbed object identifier is used as the object identifier after differential privacy processing.

[0117] Among them, the above-mentioned object identifier can be subjected to third encoding processing based on a preset hash algorithm to obtain a third-encoded object identifier, or the above-mentioned object identifier can be subjected to third encoding processing based on a preset Bloom filter to obtain a third-encoded object identifier. For specific processing, please refer to the above-mentioned related content, which will not be repeated here.

[0118] In step S406, the content risk information of the object is encrypted to obtain encrypted content risk information.

[0119] Among them, the encryption algorithm used in the encryption processing may include one or more of a homomorphic encryption algorithm, a partially homomorphic encryption algorithm, and a full-state encryption algorithm.

[0120] In step S408, the processed object identification and the encrypted content risk information are sent to the server so that the processed object identification is restored to obtain the above-mentioned object identification, and the encrypted content risk information is decrypted to obtain the above-mentioned content risk information, and based on the above-mentioned object identification and the above-mentioned content risk information, the target object with risks among the above-mentioned objects is determined.

[0121] In step S410, an object identifier of a target object sent by a server is received, and target data generated when a user accesses the target object is acquired based on the object identifier of the target object.

[0122] In step S412, a second encoding process is performed on the object identifier of the target object to obtain a second encoded object identifier of the target object, and the second encoded object identifier is subjected to noise disturbance processing using predetermined second noise data to obtain a noise-disturbed object identifier of the target object, and the noise-disturbed object identifier of the target object is used as the object identifier of the target object after differential privacy processing.

[0123] The second encoded object identifier of the target object is determined in two optional ways below. For details, refer to the following way 1 and way 2.

[0124] Method 1: Based on a preset second Hash algorithm, a second encoding process is performed on the object identifier of the target object to obtain a second encoded object identifier of the target object.

[0125] Method 2: Perform a second encoding process on the object identifier of the target object based on the second Bloom filter to obtain a second encoded object identifier of the target object.

[0126] In addition, randomized noise data or specified noise data (such as Laplace noise data or Gaussian noise data, etc.) can be input into the second encoded object identifier of the target object to perform noise disturbance processing on the second encoded object identifier of the target object, thereby masking the second encoded object identifier of the target object and protecting the privacy of the user.

[0127] Correspondingly, different privacy processing budgets can be given to different target objects to better balance data availability and privacy protection. Based on this, differential privacy processing is performed on the object identifier of the above target object in the above step S412, and the processing of the following steps D2-D6 can also be included.

[0128] In step D2, based on the target data, the risk level corresponding to the target object is determined.

[0129] In step D4, fourth noise data matching the risk level corresponding to the target object is acquired.

[0130] In step D6, the object identifier of the target object is subjected to fourth encoding processing to obtain the fourth encoded object identifier of the target object, and the fourth encoded object identifier of the target object is subjected to noise disturbance processing through fourth noise data to obtain the noise-disturbed object identifier of the target object, and the noise-disturbed object identifier of the target object is used as the object identifier of the target object after differential privacy processing.

[0131] Among them, the object identifier of the above-mentioned target object can be subjected to fourth encoding processing based on a preset hash algorithm to obtain a fourth-encoded object identifier, or the object identifier of the above-mentioned target object can be subjected to fourth encoding processing based on a preset Bloom filter to obtain a fourth-encoded object identifier. For specific processing, please refer to the above-mentioned related content and will not be repeated here.

[0132] In step S414, the target data is encrypted to obtain encrypted target data.

[0133] Among them, the encryption algorithm used for encryption processing may include one or more of a homomorphic encryption algorithm, a partially homomorphic encryption algorithm, and a full-state encryption algorithm.

[0134] In step S416, the processed object identifier of the target object and the encrypted target data are sent to the server.

[0135] The embodiments of this specification provide an object processing method based on privacy protection, which obtains the object identifier of the object accessed by the user and the content risk information of the object, performs differential privacy processing on the object identifier, and obtains the processed object identifier. The content risk information includes information on whether the object is risky and the number of visits to the object. The processed object identifier and the content risk information of the object are sent to the server, so that by performing differential privacy processing on the object identifier of the object accessed by the user, even if the above data is stolen by other people, it is impossible to know which mini-program the user is using, thereby protecting the user's privacy from being leaked. Then, the object identifier of the target object sent by the server is received, and based on the object identifier of the target object, the target data generated by the user accessing the target object is obtained, the object identifier of the target object is differentially privacy processed, and the object identifier and target data of the processed target object are sent to the server, so that for the access of the object, the corresponding data is obtained through a two-round mechanism for uploading, while protecting the user's privacy, the data can achieve high availability.

[0136] Embodiment 4

[0137] like Figure 5A and Figure 5B As shown, the embodiment of this specification provides an object processing method based on privacy protection. The execution subject of the method can be a server, wherein the server can be a background server for a certain business (such as a business for conducting transactions or a financial business, etc.) or providing access to a certain object. Specifically, the server can be a payment service server, or a server for services related to finance or instant messaging, etc. The corresponding system for application recognition based on privacy protection can be as follows Figure 2 The method may specifically include the following steps:

[0138] In step S502, an object identifier of an object accessed by a user and processed by differential privacy and content risk information of the object are received from a terminal device. The content risk information includes information on whether the object has risks and the number of visits to the object.

[0139] The processing of the above step S502 can refer to the relevant content in the above embodiment 1, and will not be repeated here.

[0140] In step S504, the object identifier after differential privacy processing is restored to obtain a restored object identifier.

[0141] In implementation, after receiving the object identifier after differential privacy processing, the server can perform two-stage processing: preprocessing stage and aggregation stage. In the preprocessing stage, the server will remove metadata, timestamps, and reorder the disturbed data collected from the terminal devices of different users. In the aggregation stage, the data obtained in the preprocessing stage will be used to perform statistical calculations through algorithms such as unbiased estimation to restore the object identifier after differential privacy processing, and obtain the restored object identifier, that is, the object identifier of the above object.

[0142] In addition, in the case where the program identifier of the target application is processed through a Bloom filter, the server can query and restore the object identifier after differential privacy processing based on the hash function of the Bloom filter to obtain the restored object identifier, that is, the object identifier of the above-mentioned object.

[0143] In step S506, based on the restored object identifier and the content risk information, a target object with risks among the objects is determined.

[0144] In implementation, the target object can be determined based on the information on whether there is a risk and the number of visits in the content risk information. For example, the object identifier of an object that has a risk and whose number of visits exceeds a predetermined threshold can be used as the object identifier of the target object, thereby determining the target object that has a risk among the above objects.

[0145] In step S508, the object identifier of the target object is sent to the terminal device, so as to obtain the target data generated by the user accessing the target object from the terminal device.

[0146] The processing of the above step S508 can refer to the relevant content in the above embodiment 1, and will not be repeated here.

[0147] The embodiments of this specification provide an object processing method based on privacy protection, which obtains the object identifier of the object accessed by the user and the content risk information of the object, performs differential privacy processing on the object identifier, and obtains the processed object identifier. The content risk information includes information on whether the object is risky and the number of visits to the object. The processed object identifier and the content risk information of the object are sent to the server, so that by performing differential privacy processing on the object identifier of the object accessed by the user, even if the above data is stolen by other people, it is impossible to know which mini-program the user is using, thereby protecting the user's privacy from being leaked. Then, the object identifier of the target object sent by the server is received, and based on the object identifier of the target object, the target data generated by the user accessing the target object is obtained, the object identifier of the target object is differentially privacy processed, and the object identifier and target data of the processed target object are sent to the server, so that for the access of the object, the corresponding data is obtained through a two-round mechanism for uploading, while protecting the user's privacy, the data can achieve high availability.

[0148] Embodiment 5

[0149] like Figure 6 As shown, the embodiment of this specification provides an object processing method based on privacy protection. The execution subject of the method can be a terminal device and a server, wherein the terminal device can be a mobile phone, a tablet computer, a personal computer, etc. The terminal device can be a terminal device capable of running an application, and the application includes a host program and any small program installed in the host program, and / or, the terminal device can be a terminal device that provides users with access to a certain object, and the server can be a background server for a certain business (such as a business for conducting transactions or a financial business, etc.) or providing access to a certain object. Specifically, for example, the server can be a server for payment services, or a server for services related to finance or instant messaging, etc. The method can specifically include the following steps:

[0150] In step S602, the terminal device obtains the object identifier of the object accessed by the user and the content risk information of the object, where the content risk information includes information on whether the object has risks and the number of visits to the object.

[0151] In step S604, the terminal device performs a first encoding process on the above-mentioned object identifier to obtain a first encoded object identifier, and scrambles each bit of the encoded data in the first encoded object identifier according to a preset first probability to obtain a scrambled object identifier, and uses the scrambled object identifier as the object identifier after differential privacy processing.

[0152] In addition to obtaining the object identifier after differential privacy processing through the processing of the above-mentioned step S604, the object identifier after differential privacy processing can also be obtained in the following manner, specifically as follows: performing a first encoding process on the above-mentioned object identifier to obtain a first encoded object identifier, and performing a noise disturbance process on the first encoded object identifier through predetermined first noise data to obtain a noise-disturbed object identifier, and using the noise-disturbed object identifier as the object identifier after differential privacy processing.

[0153] The first encoding process for the object identifier may be performed by a hash algorithm or a Bloom filter, and the specific process may be set according to actual conditions.

[0154] In step S606, the terminal device encrypts the content risk information of the object to obtain encrypted content risk information.

[0155] In step S608, the terminal device sends the processed object identification and the encrypted content risk information to the server.

[0156] In step S610, the server restores the object identifier after differential privacy processing to obtain a restored object identifier, and decrypts the encrypted content risk information to obtain the above content risk information.

[0157] In step S612, the server determines the object identification of the object with risky information and whose access volume exceeds a predetermined access volume threshold based on the restored object identification and the above content risk information, and takes the object corresponding to the determined object identification as the target object.

[0158] The access volume threshold may be set according to actual conditions. For example, the access volume threshold may be the number of accesses per unit time, such as 10,000 times per hour.

[0159] In step S614, the server sends the object identifier of the target object to the terminal device.

[0160] In step S616, the terminal device obtains target data generated by the user accessing the target object based on the object identifier of the target object.

[0161] In step S618, the terminal device performs a second encoding process on the object identifier of the target object to obtain the second encoded object identifier of the target object, and scrambles each bit of the encoded data in the second encoded object identifier of the target object according to a preset second probability to obtain the scrambled object identifier of the target object, and uses the scrambled object identifier of the target object as the differentially privacy processed object identifier of the target object.

[0162] In addition to obtaining the differential privacy processed object identifier of the target object through the processing of the above-mentioned step S618, the differential privacy processed object identifier of the target object can also be obtained in the following manner, specifically as follows: performing a second encoding process on the object identifier of the target object to obtain the second encoded object identifier of the target object, and performing noise disturbance processing on the second encoded object identifier through predetermined second noise data to obtain the noise-disturbed object identifier of the target object, and using the noise-disturbed object identifier of the target object as the object identifier of the target object after differential privacy processing.

[0163] In step S620, the terminal device encrypts the target data to obtain encrypted target data.

[0164] In step S622, the terminal device sends the processed object identifier of the target object and the encrypted target data to the server.

[0165] The embodiments of this specification provide an object processing method based on privacy protection, which obtains the object identifier of the object accessed by the user and the content risk information of the object, performs differential privacy processing on the object identifier, and obtains the processed object identifier. The content risk information includes information on whether the object is risky and the number of visits to the object. The processed object identifier and the content risk information of the object are sent to the server, so that by performing differential privacy processing on the object identifier of the object accessed by the user, even if the above data is stolen by other people, it is impossible to know which mini-program the user is using, thereby protecting the user's privacy from being leaked. Then, the object identifier of the target object sent by the server is received, and based on the object identifier of the target object, the target data generated by the user accessing the target object is obtained, the object identifier of the target object is differentially privacy processed, and the object identifier and target data of the processed target object are sent to the server, so that for the access of the object, the corresponding data is obtained through a two-round mechanism for uploading, while protecting the user's privacy, the data can achieve high availability.

[0166] Embodiment 6

[0167] The above is a privacy protection-based object processing method provided in the embodiments of this specification. Based on the same idea, the embodiments of this specification also provide a privacy protection-based object processing device, such as Figure 7 shown.

[0168] The object processing device based on privacy protection includes: a first differential privacy module 701, an information sending module 702, an identification receiving module 703 and a second differential privacy module 704, wherein:

[0169] The first differential privacy module 701 obtains the object identifier of the object accessed by the user and the content risk information of the object, performs differential privacy processing on the object identifier to obtain a processed object identifier, and the content risk information includes information on whether the object has risks and the number of visits to the object;

[0170] The information sending module 702 sends the processed object identification and the content risk information of the object to a server, so that the server performs restoration processing on the processed object identification to obtain the object identification, and determines a target object with risk among the objects based on the object identification and the content risk information;

[0171] The identification receiving module 703 receives the object identification of the target object sent by the server, and acquires the target data generated by the user accessing the target object based on the object identification of the target object;

[0172] The second differential privacy module 704 performs differential privacy processing on the object identifier of the target object, and sends the processed object identifier of the target object and the target data to a server.

[0173] In the embodiment of this specification, the device further includes:

[0174] A first encryption module encrypts the content risk information of the object to obtain encrypted content risk information;

[0175] The information sending module 702 sends the processed object identifier and the encrypted content risk information to a server.

[0176] In the embodiment of this specification, the device further includes:

[0177] A second encryption module encrypts the target data to obtain encrypted target data;

[0178] The information sending module 702 sends the processed object identification of the target object and the encrypted target data to the server.

[0179] In the embodiments of this specification, the encryption algorithm used for encryption processing includes one or more of a homomorphic encryption algorithm, a partially homomorphic encryption algorithm, and a full-state encryption algorithm.

[0180] In the embodiment of the present specification, the first differential privacy module 701 performs a first encoding process on the object identifier to obtain a first encoded object identifier, and performs a scrambling process on each bit of the encoded data in the first encoded object identifier according to a preset first probability to obtain the scrambled object identifier, and uses the scrambled object identifier as the object identifier after differential privacy processing; and / or,

[0181] The second differential privacy module 704 performs a second encoding process on the object identifier of the target object to obtain the second encoded object identifier of the target object, and scrambles each bit of the encoded data in the second encoded object identifier of the target object according to a preset second probability to obtain the scrambled object identifier of the target object, and uses the scrambled object identifier of the target object as the differentially privacy processed object identifier of the target object.

[0182] In the embodiment of this specification, the first differential privacy module 701 performs a first encoding process on the object identifier to obtain a first encoded object identifier, and performs a noise disturbance process on the first encoded object identifier through a predetermined first noise data to obtain the object identifier after noise disturbance, and uses the object identifier after noise disturbance as the object identifier after differential privacy processing; and / or,

[0183] The second differential privacy module 704 performs a second encoding process on the object identifier of the target object to obtain a second encoded object identifier of the target object, and performs a noise disturbance process on the second encoded object identifier through predetermined second noise data to obtain the noise-disturbed object identifier of the target object, and uses the noise-disturbed object identifier of the target object as the differential privacy processed object identifier of the target object.

[0184] In the embodiment of this specification, the first differential privacy module 701 performs a first encoding process on the object identifier based on a preset first hash algorithm to obtain a first encoded object identifier; and / or

[0185] The second differential privacy module 704 performs a second encoding process on the object identifier of the target object based on a preset second hash algorithm to obtain a second encoded object identifier of the target object.

[0186] In the embodiment of this specification, the first differential privacy module 701 performs a first encoding process on the object identifier based on the first Bloom filter to obtain a first encoded object identifier; and / or

[0187] The second differential privacy module 704 performs a second encoding process on the object identifier of the target object based on the second Bloom filter to obtain a second encoded object identifier of the target object.

[0188] In the embodiments of this specification, the object includes a small program installed in a host program.

[0189] The embodiment of this specification provides an object processing device based on privacy protection, which obtains the object identification and content risk information of the object accessed by the user, performs differential privacy processing on the object identification, and obtains the processed object identification. The content risk information includes information on whether the object is risky and the number of visits to the object. The processed object identification and the content risk information of the object are sent to the server, so that by performing differential privacy processing on the object identification of the object accessed by the user, even if the above data is stolen by other people, it is impossible to know which mini-program the user is using, thereby protecting the user's privacy from being leaked. Then, the object identification of the target object sent by the server is received, and based on the object identification of the target object, the target data generated by the user accessing the target object is obtained, the object identification of the target object is differentially privacy processed, and the object identification and target data of the processed target object are sent to the server, so that for the access to the object, the corresponding data is obtained through a two-round mechanism for uploading, while protecting the user's privacy, the data can achieve high availability.

[0190] Embodiment 7

[0191] Based on the same idea, the embodiment of this specification also provides an object processing device based on privacy protection, such as Figure 8 shown.

[0192] The object processing device based on privacy protection includes: an information receiving module 801, a restoration module 802, an object determination module 803 and an identification sending module 804, wherein:

[0193] The information receiving module 801 receives the object identifier of the object accessed by the user and processed by differential privacy and the content risk information of the object sent by the terminal device, wherein the content risk information includes information on whether the object has risks and the number of visits to the object;

[0194] Restoration module 802, performs restoration processing on the object identifier after differential privacy processing to obtain a restored object identifier;

[0195] An object determination module 803 determines a target object with risks among the objects based on the restored object identifier and the content risk information;

[0196] The identification sending module 804 sends the object identification of the target object to the terminal device, so as to obtain the target data generated by the user accessing the target object from the terminal device.

[0197] In the embodiment of this specification, the object determination module 803 includes:

[0198] A risk determination unit, based on the restored object identification and the content risk information, determines the object identification of the object having risky information and the access volume exceeding a predetermined access volume threshold;

[0199] The object determining unit uses the object corresponding to the determined object identifier as the target object.

[0200] The embodiment of this specification provides an object processing device based on privacy protection, which obtains the object identification and content risk information of the object accessed by the user, performs differential privacy processing on the object identification, and obtains the processed object identification. The content risk information includes information on whether the object is risky and the number of visits to the object. The processed object identification and the content risk information of the object are sent to the server, so that by performing differential privacy processing on the object identification of the object accessed by the user, even if the above data is stolen by other people, it is impossible to know which mini-program the user is using, thereby protecting the user's privacy from being leaked. Then, the object identification of the target object sent by the server is received, and based on the object identification of the target object, the target data generated by the user accessing the target object is obtained, the object identification of the target object is differentially privacy processed, and the object identification and target data of the processed target object are sent to the server, so that for the access to the object, the corresponding data is obtained through a two-round mechanism for uploading, while protecting the user's privacy, the data can achieve high availability.

[0201] Embodiment 8

[0202] The above is an object processing device based on privacy protection provided by the embodiments of this specification. Based on the same idea, the embodiments of this specification also provide an object processing device based on privacy protection, such as Fig. 9 shown.

[0203] The object processing device based on privacy protection may be the terminal device or server provided in the above embodiment.

[0204] The object processing device based on privacy protection may have relatively large differences due to different configurations or performances, and may include one or more processors 901 and memory 902, and one or more storage applications or data may be stored in the memory 902. Among them, the memory 902 can be a short-term storage or a persistent storage. The application stored in the memory 902 may include one or more modules (not shown in the figure), and each module may include a series of computer executable instructions in the object processing device based on privacy protection. Furthermore, the processor 901 can be configured to communicate with the memory 902 to execute a series of computer executable instructions in the memory 902 on the object processing device based on privacy protection. The object processing device based on privacy protection may also include one or more power supplies 903, one or more wired or wireless network interfaces 904, one or more input and output interfaces 905, and one or more keyboards 906.

[0205] Specifically, in this embodiment, the object processing device based on privacy protection includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer executable instructions in the object processing device based on privacy protection, and the one or more programs are configured to be executed by one or more processors, including computer executable instructions for performing the following:

[0206] Obtaining an object identifier of an object accessed by a user and content risk information of the object, performing differential privacy processing on the object identifier to obtain a processed object identifier, wherein the content risk information includes information on whether the object has risks and the number of visits to the object;

[0207] Sending the processed object identification and the content risk information of the object to a server, so that the server performs restoration processing on the processed object identification to obtain the object identification, and determining a target object with risk in the object based on the object identification and the content risk information;

[0208] receiving an object identifier of the target object sent by the server, and acquiring target data generated by a user accessing the target object based on the object identifier of the target object;

[0209] The object identifier of the target object is differentially privacy processed, and the processed object identifier of the target object and the target data are sent to a server.

[0210] In the embodiments of this specification, it also includes:

[0211] Encrypting the content risk information of the object to obtain encrypted content risk information;

[0212] The sending the processed object identifier and the content risk information of the object to a server includes:

[0213] The processed object identifier and the encrypted content risk information are sent to a server.

[0214] In the embodiments of this specification, it also includes:

[0215] Encrypting the target data to obtain encrypted target data;

[0216] The step of sending the processed object identifier of the target object and the target data to a server includes:

[0217] The processed object identification of the target object and the encrypted target data are sent to the server.

[0218] In the embodiments of this specification, the object includes a small program installed in a host program.

[0219] In addition, specifically in this embodiment, the object processing device based on privacy protection includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer executable instructions in the object processing device based on privacy protection, and the one or more programs are configured to be executed by one or more processors, including computer executable instructions for performing the following:

[0220] Receive an object identifier of an object accessed by a user and processed by differential privacy and content risk information of the object sent by a terminal device, wherein the content risk information includes information on whether the object has risks and the number of visits to the object;

[0221] Restoring the object identity after differential privacy processing to obtain a restored object identity;

[0222] Determining a target object with risks among the objects based on the restored object identifier and the content risk information;

[0223] The object identifier of the target object is sent to the terminal device, so as to obtain target data generated by the user accessing the target object from the terminal device.

[0224] In the embodiment of this specification, the determining of the target object with risk in the object based on the restored object identifier and the content risk information includes:

[0225] Based on the restored object identifier and the content risk information, determine the object identifier of the object whose risky information exists and the access volume exceeds a predetermined access volume threshold;

[0226] The object corresponding to the determined object identifier is used as the target object.

[0227] The embodiment of this specification provides an object processing device based on privacy protection, which obtains the object identification and content risk information of the object accessed by the user, performs differential privacy processing on the object identification, and obtains the processed object identification. The content risk information includes information on whether the object is risky and the number of visits to the object. The processed object identification and the content risk information of the object are sent to the server, so that by performing differential privacy processing on the object identification of the object accessed by the user, even if the above data is stolen by other people, it is impossible to know which mini-program the user is using, thereby protecting the user's privacy from being leaked. Then, the object identification of the target object sent by the server is received, and based on the object identification of the target object, the target data generated by the user accessing the target object is obtained, the object identification of the target object is differentially privacy processed, and the object identification and target data of the processed target object are sent to the server, so that for the access to the object, the corresponding data is obtained through a two-round mechanism for uploading, while protecting the user's privacy, the data can achieve high availability.

[0228] Embodiment 9

[0229] Further, based on the above-mentioned Figures 1 to Figure 6 In one embodiment, the present specification further provides a storage medium for storing computer executable instruction information. In a specific embodiment, the storage medium may be a USB flash drive, an optical disk, a hard disk, etc. When the computer executable instruction information stored in the storage medium is executed by the processor, the following process can be implemented:

[0230] Obtaining an object identifier of an object accessed by a user and content risk information of the object, performing differential privacy processing on the object identifier to obtain a processed object identifier, wherein the content risk information includes information on whether the object has risks and the number of visits to the object;

[0231] Sending the processed object identification and the content risk information of the object to a server, so that the server performs restoration processing on the processed object identification to obtain the object identification, and determining a target object with risk in the object based on the object identification and the content risk information;

[0232] receiving an object identifier of the target object sent by the server, and acquiring target data generated by a user accessing the target object based on the object identifier of the target object;

[0233] The object identifier of the target object is differentially privacy processed, and the processed object identifier of the target object and the target data are sent to a server.

[0234] In the embodiments of this specification, it also includes:

[0235] Encrypting the content risk information of the object to obtain encrypted content risk information;

[0236] The sending the processed object identifier and the content risk information of the object to a server includes:

[0237] The processed object identifier and the encrypted content risk information are sent to a server.

[0238] In the embodiments of this specification, it also includes:

[0239] Encrypting the target data to obtain encrypted target data;

[0240] The step of sending the processed object identifier of the target object and the target data to a server includes:

[0241] The processed object identification of the target object and the encrypted target data are sent to the server.

[0242] In the embodiments of this specification, the object includes a small program installed in a host program.

[0243] In addition, in a specific embodiment, the storage medium may be a USB flash drive, an optical disk, a hard disk, etc. When the computer executable instruction information stored in the storage medium is executed by the processor, the following process can be implemented:

[0244] Receive an object identifier of an object accessed by a user and processed by differential privacy and content risk information of the object sent by a terminal device, wherein the content risk information includes information on whether the object has risks and the number of visits to the object;

[0245] Restoring the object identity after differential privacy processing to obtain a restored object identity;

[0246] Determining a target object with risks among the objects based on the restored object identifier and the content risk information;

[0247] The object identifier of the target object is sent to the terminal device, so as to obtain target data generated by the user accessing the target object from the terminal device.

[0248] In the embodiment of this specification, the determining of the target object with risk in the object based on the restored object identifier and the content risk information includes:

[0249] Based on the restored object identifier and the content risk information, determine the object identifier of the object whose risky information exists and the access volume exceeds a predetermined access volume threshold;

[0250] The object corresponding to the determined object identifier is used as the target object.

[0251] An embodiment of the present specification provides a storage medium, which obtains the object identifier of the object accessed by the user and the content risk information of the object, performs differential privacy processing on the object identifier, and obtains the processed object identifier. The content risk information includes information on whether the object is risky and the number of visits to the object. The processed object identifier and the content risk information of the object are sent to a server, thereby performing differential privacy processing on the object identifier of the object accessed by the user, so that even if the above data is stolen by other people, it is impossible to know which mini-program the user is using, thereby protecting the user's privacy from being leaked. Then, the object identifier of the target object sent by the server is received, and based on the object identifier of the target object, the target data generated by the user accessing the target object is obtained, the object identifier of the target object is differentially privacy processed, and the object identifier and target data of the processed target object are sent to the server, so that for the access to the object, the corresponding data is obtained through a two-round mechanism for uploading, while protecting the user's privacy, the data can achieve high availability.

[0252] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0253] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0254] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0255] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0256] For the convenience of description, the above devices are described in terms of functions and are divided into various units. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0257] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, one or more embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, one or more embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0258] The embodiments of this specification are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable fraud case serial and parallel device to produce a machine, so that the instructions executed by the processor of the computer or other programmable fraud case serial and parallel device produce a device for implementing the function specified in one process or multiple processes of the flowchart and / or one box or multiple boxes of the block diagram.

[0259] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable fraud case serial and parallel device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0260] These computer program instructions may also be loaded onto a computer or other programmable fraud case serial and parallel device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram.

[0261] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0262] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0263] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0264] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0265] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, one or more embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, one or more embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0266] One or more embodiments of the present specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0267] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0268] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.

Claims

1. A method for object processing based on privacy protection, the method comprising: Obtaining an object identifier of an object accessed by a user and content risk information of the object, performing differential privacy processing on the object identifier to obtain a processed object identifier, wherein the content risk information includes information on whether the object has risks and the number of visits to the object; Sending the processed object identification and the content risk information of the object to a server, so that the server performs restoration processing on the processed object identification to obtain the object identification, and determining a target object with risk in the object based on the object identification and the content risk information; receiving an object identifier of the target object sent by the server, and acquiring target data generated by a user accessing the target object based on the object identifier of the target object; The object identifier of the target object is differentially privacy processed, and the processed object identifier of the target object and the target data are sent to a server.

2. The method according to claim 1, further comprising: Encrypting the content risk information of the object to obtain encrypted content risk information; The sending the processed object identifier and the content risk information of the object to a server includes: The processed object identifier and the encrypted content risk information are sent to a server.

3. The method according to claim 1, further comprising: Encrypting the target data to obtain encrypted target data; The step of sending the processed object identifier of the target object and the target data to a server includes: The processed object identification of the target object and the encrypted target data are sent to the server.

4. According to the method described in claim 2 or 3, the encryption algorithm used for encryption processing includes one or more of a homomorphic encryption algorithm, a partially homomorphic encryption algorithm and a full-state encryption algorithm.

5. According to the method of claim 1, performing differential privacy processing on the object identifier to obtain the processed object identifier comprises: Performing a first encoding process on the object identifier to obtain a first encoded object identifier, and performing a scrambling process on each bit of the encoded data in the first encoded object identifier according to a preset first probability to obtain the scrambled object identifier, and using the scrambled object identifier as the object identifier after differential privacy processing; and / or, The performing differential privacy processing on the object identifier of the target object includes: Perform a second encoding process on the object identifier of the target object to obtain the second encoded object identifier of the target object, and perform a scrambling process on each bit of the encoded data in the second encoded object identifier of the target object according to a preset second probability to obtain the scrambled object identifier of the target object, and use the scrambled object identifier of the target object as the differentially private processed object identifier of the target object.

6. According to the method of claim 1, performing differential privacy processing on the object identifier to obtain the processed object identifier comprises: Determining a risk level corresponding to the object based on the content risk information of the object; Acquire a third probability that matches the risk level corresponding to the object; Performing a third encoding process on the object identifier to obtain a third-encoded object identifier, and performing a scrambling process on each bit of the encoded data in the third-encoded object identifier according to the third probability to obtain the scrambled object identifier, and using the scrambled object identifier as the object identifier after differential privacy processing; and / or, The performing differential privacy processing on the object identifier of the target object includes: Based on the target data, determining a risk level corresponding to the target object; Acquire a fourth probability that matches the risk level corresponding to the target object; Perform a fourth encoding process on the object identifier of the target object to obtain a fourth encoded object identifier of the target object, and perform a scrambling process on each bit of the encoded data in the fourth encoded object identifier of the target object according to the fourth probability to obtain the scrambled object identifier of the target object, and use the scrambled object identifier of the target object as the differentially private processed object identifier of the target object.

7. According to the method of claim 1, performing differential privacy processing on the object identifier to obtain the processed object identifier comprises: Performing a first encoding process on the object identifier to obtain a first encoded object identifier, performing a noise disturbance process on the first encoded object identifier using predetermined first noise data to obtain the object identifier after noise disturbance, and using the object identifier after noise disturbance as the object identifier after differential privacy processing; and / or, The performing differential privacy processing on the object identifier of the target object includes: Perform a second encoding process on the object identifier of the target object to obtain a second encoded object identifier of the target object, perform noise disturbance processing on the second encoded object identifier through predetermined second noise data to obtain the noise-disturbed object identifier of the target object, and use the noise-disturbed object identifier of the target object as the object identifier of the target object after differential privacy processing.

8. According to the method of claim 1, performing differential privacy processing on the object identifier to obtain the processed object identifier comprises: Determining a risk level corresponding to the object based on the content risk information of the object; Acquiring third noise data that matches the risk level corresponding to the object; Performing a third encoding process on the object identifier to obtain a third encoded object identifier, performing a noise disturbance process on the third encoded object identifier using the third noise data to obtain the noise disturbed object identifier, and using the noise disturbed object identifier as the object identifier after differential privacy processing; and / or, The performing differential privacy processing on the object identifier of the target object includes: Based on the target data, determining a risk level corresponding to the target object; Acquiring fourth noise data matching the risk level corresponding to the target object; Perform a fourth encoding process on the object identifier of the target object to obtain a fourth encoded object identifier of the target object, perform noise disturbance processing on the fourth encoded object identifier through the fourth noise data to obtain the noise-disturbed object identifier of the target object, and use the noise-disturbed object identifier of the target object as the object identifier of the target object after differential privacy processing.

9. The method according to claim 5 or 7, wherein the step of performing a first encoding process on the object identifier to obtain the first encoded object identifier comprises: Based on a preset first Hash algorithm, performing a first encoding process on the object identifier to obtain a first encoded object identifier; and / or The performing a second encoding process on the object identifier of the target object to obtain the second encoded object identifier of the target object includes: Based on a preset second Hash algorithm, a second encoding process is performed on the object identifier of the target object to obtain a second encoded object identifier of the target object.

10. The method according to claim 5 or 7, wherein performing a first encoding process on the object identifier to obtain a first encoded object identifier comprises: Performing a first encoding process on the object identifier based on a first Bloom filter to obtain a first encoded object identifier; and / or The performing a second encoding process on the object identifier of the target object to obtain the second encoded object identifier of the target object includes: A second encoding process is performed on the object identifier of the target object based on the second Bloom filter to obtain a second encoded object identifier of the target object.

11. The method according to claim 1, wherein the object comprises a small program carried in a host program.

12. A method for object processing based on privacy protection, the method comprising: Receive an object identifier of an object accessed by a user and processed by differential privacy and content risk information of the object sent by a terminal device, wherein the content risk information includes information on whether the object has risks and the number of visits to the object; Restoring the object identity after differential privacy processing to obtain a restored object identity; Determining a target object with risks among the objects based on the restored object identifier and the content risk information; Sending the object identifier of the target object to the terminal device, so as to obtain target data generated by the user accessing the target object from the terminal device; The object identifier after differential privacy processing is obtained by the terminal device disturbing the encoded object identifier with a preset probability.

13. The method according to claim 12, wherein the step of determining a target object with risk in the object based on the restored object identifier and the content risk information comprises: Based on the restored object identifier and the content risk information, determine the object identifier of the object whose risky information exists and the access volume exceeds a predetermined access volume threshold; The object corresponding to the determined object identifier is used as the target object.

14. A device for object processing based on privacy protection, the device comprising: A first differential privacy module obtains an object identifier of an object accessed by a user and content risk information of the object, performs differential privacy processing on the object identifier to obtain a processed object identifier, wherein the content risk information includes information on whether the object has risks and the number of visits to the object; An information sending module, which sends the processed object identification and the content risk information of the object to a server, so that the server performs restoration processing on the processed object identification to obtain the object identification, and determines a target object with risk among the objects based on the object identification and the content risk information; an identification receiving module, receiving the object identification of the target object sent by the server, and acquiring target data generated by the user accessing the target object based on the object identification of the target object; The second differential privacy module performs differential privacy processing on the object identifier of the target object, and sends the processed object identifier of the target object and the target data to a server.

15. The device according to claim 14, further comprising: A first encryption module encrypts the content risk information of the object to obtain encrypted content risk information; The information sending module sends the processed object identifier and the encrypted content risk information to a server.

16. According to the device of claim 14, the first differential privacy module performs a first encoding process on the object identifier to obtain a first encoded object identifier, and performs a scrambling process on each bit of the encoded data in the first encoded object identifier according to a preset first probability to obtain the scrambled object identifier, and uses the scrambled object identifier as the object identifier after differential privacy processing; and / or, The second differential privacy module performs a second encoding process on the object identifier of the target object to obtain the second encoded object identifier of the target object, and scrambles each bit of the encoded data in the second encoded object identifier of the target object according to a preset second probability to obtain the scrambled object identifier of the target object, and uses the scrambled object identifier of the target object as the differentially privacy processed object identifier of the target object.

17. The apparatus according to claim 14, wherein the object comprises a small program loaded in a host program.

18. An object processing device based on privacy protection, the device comprising: An information receiving module receives an object identifier of an object accessed by a user and processed by differential privacy and content risk information of the object sent by a terminal device, wherein the content risk information includes information on whether the object has risks and the number of visits to the object; The restoration module restores the object identity after differential privacy processing to obtain the restored object identity; An object determination module, which determines a target object with risks among the objects based on the restored object identifier and the content risk information; The identification sending module sends the object identification of the target object to the terminal device, so as to obtain the target data generated by the user accessing the target object from the terminal device.

19. An object processing device based on privacy protection, the object processing device based on privacy protection comprising: processor; as well as a memory arranged to store computer executable instructions which, when executed, cause the processor to: Obtaining an object identifier of an object accessed by a user and content risk information of the object, performing differential privacy processing on the object identifier to obtain a processed object identifier, wherein the content risk information includes information on whether the object has risks and the number of visits to the object; Sending the processed object identification and the content risk information of the object to a server, so that the server performs restoration processing on the processed object identification to obtain the object identification, and determining a target object with risk in the object based on the object identification and the content risk information; receiving an object identifier of the target object sent by the server, and acquiring target data generated by a user accessing the target object based on the object identifier of the target object; The object identifier of the target object is differentially privacy processed, and the processed object identifier of the target object and the target data are sent to a server.

20. An object processing device based on privacy protection, the object processing device based on privacy protection comprising: processor; as well as a memory arranged to store computer executable instructions which, when executed, cause the processor to: Receive an object identifier of an object accessed by a user and processed by differential privacy and content risk information of the object sent by a terminal device, wherein the content risk information includes information on whether the object has risks and the number of visits to the object; Restoring the object identity after differential privacy processing to obtain a restored object identity; Determining a target object with risks among the objects based on the restored object identifier and the content risk information; Sending the object identifier of the target object to the terminal device, so as to obtain target data generated by the user accessing the target object from the terminal device; The object identifier after differential privacy processing is obtained by the terminal device disturbing the encoded object identifier with a preset probability.

21. A storage medium for storing computer executable instructions, wherein the executable instructions implement the following process when executed: Obtaining an object identifier of an object accessed by a user and content risk information of the object, performing differential privacy processing on the object identifier to obtain a processed object identifier, wherein the content risk information includes information on whether the object has risks and the number of visits to the object; Sending the processed object identification and the content risk information of the object to a server, so that the server performs restoration processing on the processed object identification to obtain the object identification, and determining a target object with risk in the object based on the object identification and the content risk information; receiving an object identifier of the target object sent by the server, and acquiring target data generated by a user accessing the target object based on the object identifier of the target object; The object identifier of the target object is differentially privacy processed, and the processed object identifier of the target object and the target data are sent to a server.

22. A storage medium for storing computer executable instructions, wherein the executable instructions implement the following process when executed: Receive an object identifier of an object accessed by a user and processed by differential privacy and content risk information of the object sent by a terminal device, wherein the content risk information includes information on whether the object has risks and the number of visits to the object; Restoring the object identity after differential privacy processing to obtain a restored object identity; Determining a target object with risks among the objects based on the restored object identifier and the content risk information; Sending the object identifier of the target object to the terminal device, so as to obtain target data generated by the user accessing the target object from the terminal device; The object identifier after differential privacy processing is obtained by the terminal device disturbing the encoded object identifier with a preset probability.

Images