Data processing method and system, and related devices

Abstract

Disclosed in embodiments of the present application are a data processing method and system, and related devices. The method comprises: receiving first request information input by a user; sending the first request information to a second unit; receiving first response information corresponding to the first request information and sent by the second unit; sending second request information to the second unit, wherein the second request information is used for obfuscating the first request information; and receiving second response information corresponding to the second request information and sent by the second unit. By acquiring false request information by means of a trusted unit or device (a first unit or a third unit), and using the false request information to obfuscate true request information, an untrusted unit cannot determine the true request information, thereby improving the privacy protection of a user.

Description

Data processing method, system and related equipment

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on September 22, 2023, with application number 202311241182.7 and invention name “A data processing method and related equipment”, and claims priority to the Chinese patent application filed with the State Intellectual Property Office on October 30, 2023, with application number 202311429037.1 and invention name “A data processing method, system and related equipment”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The embodiments of the present application relate to the field of artificial intelligence, and in particular to a data processing method, system, and related equipment. Background Art

[0003] Artificial intelligence (AI) is the theory, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, to perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a branch of computer science that seeks to understand the essence of intelligence and develop new intelligent machines that can respond in a manner similar to human intelligence. AI also studies the design principles and implementation methods of various intelligent machines, enabling them to possess the capabilities of perception, reasoning, and decision-making. Research in the field of AI includes robotics, natural language processing, computer vision, decision-making and reasoning, human-computer interaction, recommendation and search, and basic AI theory.

[0004] In a device-cloud scenario, the device sends user-entered request information (such as a question) to the cloud. The cloud, which stores the neural network, performs inference and returns a response (such as the answer) to the device, which then presents the response to the user. This process shows that the user-entered request information is actually transmitted out of the user's device, which poses a potential privacy risk.

[0005] Therefore, how to reduce the leakage of user privacy while using cloud-based reasoning capabilities is a technical problem that needs to be solved urgently.

[0006] Summary of the Invention

[0007] The embodiment of the present application provides a data processing method and related equipment, which can obtain false request information based on the real request information input by the user or the real response information corresponding to the real request information, so that the first unit can use the false request information to confuse the real request information, and then use the false request information to confuse the model, thereby improving the user's privacy protection.

[0008] The first aspect of the embodiment of the present application provides a data processing method. The method can be executed by the first device / first unit, or by a component of the first device / first unit (such as a processor, a chip, or a chip system, etc.). In this method, a first request message input by a user is sent to the second unit; a first response message corresponding to the first request message sent by the second unit is received; it is characterized in that the method further includes: sending a second request message to the second unit, the second request message being used to confuse the first request message; and receiving a second response message corresponding to the second request message sent by the second unit. Among them, the first request message can also be understood as a real request message, the first response message can also be understood as a real response message, the second request message can be understood as a false request message, and the second response message can also be understood as a false response message.

[0009] In an embodiment of the present application, false request information is obtained through a trusted unit or device (first unit or third unit), so that the first unit can use the false request information to confuse the real request information, making it impossible for the untrusted unit to clearly identify the real request information, thereby improving user privacy protection.

[0010] Optionally, in a possible implementation manner of the first aspect, the above steps further include: acquiring second request information based on the first request information.

[0011] In this possible implementation, false request information corresponding to the real request information is obtained through a trusted unit or device (first unit or third unit), so that the first unit can use the false request information to prevent the untrusted unit from clarifying the real request information, thereby improving user privacy protection.

[0012] Optionally, in a possible implementation manner of the first aspect, the above step of: obtaining the second request information based on the first request information includes: determining a first keyword in the first request information; and obtaining the second request information based on the first keyword and the first request information.

[0013] In this possible implementation, false request information is obtained by means of the first keyword, thereby confusing the untrusted unit by blurring / obfuscating the keyword, so that the untrusted unit cannot clearly identify the real request information, thereby improving user privacy protection.

[0014] Optionally, in a possible implementation of the first aspect, the above step of obtaining the second request information based on the first keyword and the first request information includes: determining a first replacement word corresponding to the first keyword; replacing the first keyword in the first request information with the first replacement word to obtain the second request information.

[0015] In this possible implementation, a related first replacement word is obtained through the first keyword, and the first replacement word is used to replace the first keyword in the first request information, so that the first keyword can be hidden and obfuscated, reducing the risk of the first keyword being identified by an untrusted unit and improving user privacy.

[0016] Optionally, in a possible implementation of the first aspect, the above step of obtaining the second request information based on the first keyword and the first request information includes: sending the first keyword and the first request information to a third unit; and receiving the second request information sent by the third unit.

[0017] In this possible implementation, fake request information is generated by a trusted unit (ie, the third unit), thereby hiding the real request information from the untrusted unit and improving user privacy.

[0018] Optionally, in a possible implementation manner of the first aspect, the step of determining the first keyword in the first request information includes determining the first keyword based on a first operation of the user or a first preset rule.

[0019] In this possible implementation, there are multiple ways to determine the keyword, which can be selected based on user operations or preset rules, thereby improving the applicability of the solution.

[0020] Optionally, in a possible implementation manner of the first aspect, the above step of: obtaining the second request information based on the first request information includes: sending the first request information to the third unit; and receiving the second request information sent by the third unit.

[0021] In this possible implementation, fake request information is generated by a trusted unit (ie, the third unit), thereby hiding the real request information from the untrusted unit and improving user privacy.

[0022] Optionally, in a possible implementation manner of the first aspect, the above steps further include: generating second request information based on the first response information.

[0023] In this possible implementation, the real response information is first obtained from the real request information, and then multiple false request information is obtained based on the real response information. Since the second unit generally retrieves logs and other methods within a certain time period, as long as the time interval between the real request information and the false request information is less than the aforementioned time period, the first unit can use multiple false request information to obfuscate the real request information in the log, thereby improving user privacy protection.

[0024] Optionally, in a possible implementation of the first aspect, the above step of: generating the second request information based on the first response information includes: obtaining the third response information based on the first response information; and obtaining the second request information based on the third response information.

[0025] In this possible implementation, the real response information is first obtained through the real request information, and then the real response information is obfuscated to obtain multiple false response information, so that the multiple false response information can be reversely inferred to obtain multiple false request information. Since under normal circumstances, the second unit retrieves logs and other methods within a certain time period, as long as the second unit infers that the time interval between the real request information and the false request information is less than the above time period. In terms of log representation, the first unit can obfuscate the real request information through multiple false request information, thereby improving user privacy protection.

[0026] Optionally, in a possible implementation of the first aspect, the above steps of obtaining the third response information based on the first response information include: determining the second keyword in the first response information; determining the second replacement word corresponding to the second keyword; and replacing the second keyword in the first response information with the second replacement word to obtain the third response information.

[0027] In this possible implementation, multiple fake request information is obtained based on the second keyword in the real result. Since the second unit generally retrieves logs within a certain time period, as long as the time interval between the real request information and the fake request information inferred by the second unit is less than the aforementioned time period, the first unit can use multiple fake request information to obfuscate the real request information in the log, thereby improving user privacy protection.

[0028] Optionally, in a possible implementation manner of the first aspect, the above steps further include: presenting multiple response information or first response information to the user, where the multiple response information includes the first response information and the second response information.

[0029] In this possible implementation, it is convenient for the user to use the second unit to process data and obtain the response information required by the user, thereby improving the user experience.

[0030] Optionally, in a possible implementation of the first aspect, the above steps also include: receiving a first request message sent by the third unit; sending multiple response messages or first response messages to the third unit, the multiple response messages including the first response message and the second response message.

[0031] In this possible implementation, the third unit used by the user can obtain response information through the trusted first unit, thereby providing the response information required by the user and improving the user experience.

[0032] Optionally, in a possible implementation manner of the first aspect, the first unit or the first device is a question answering device.

[0033] In this possible implementation, the first unit may be a question answering device that provides requested services to users. Users may ask questions to the question answering device and receive responses from the question answering device, thereby providing the responses required by users and improving user experience.

[0034] Optionally, in a possible implementation manner of the first aspect, the first request information includes at least one of the following: a question, a text processing request, and a translation request.

[0035] In this possible implementation, the first request information can provide multiple requirements for the user, thereby improving the flexibility of the solution.

[0036] A second aspect of an embodiment of the present application provides a data processing method. The method can be executed by a third device / third unit, or by a component of the third device / third unit (such as a processor, chip, or chip system). In this method, a first request message sent by a first unit or a first response message corresponding to the first request message is received; based on the first request message or the first response message, a second request message is sent to the first unit, where the second request message is used to obfuscate the first request message.

[0037] In an embodiment of the present application, false request information is obtained based on real request information or real response information through a trusted unit or device (third unit), so that the false request information can be used to confuse the real request information, making it impossible for the untrusted unit to clearly identify the real request information, thereby improving the user's privacy protection.

[0038] Optionally, in a possible implementation manner of the second aspect, the third device / third unit is deployed on a network server, and the first unit is deployed on a terminal device.

[0039] In this possible implementation, a trusted network server determines the second request information for the terminal device, so that the terminal device can use false request information to confuse the real request information, making it impossible for the untrusted second unit to clearly identify the real request information, thereby improving user privacy protection.

[0040] Optionally, in a possible implementation of the second aspect, the above-mentioned step of sending the second request information to the first unit based on the first request information or the first response information includes: obtaining the second request information based on the first request information or the first response information, and sending the second request information to the first unit.

[0041] In this possible implementation, a trusted unit or device (third unit) obtains false request information based on the real request information or real response information, and sends the second request information to the first unit. The first unit can then use the false request information to obfuscate the real request information, reducing the risk of the real request information being identified by the untrusted unit (third unit).

[0042] The third aspect of the embodiment of the present application provides a data processing method. The method can be performed jointly by the first unit and the third unit, or can be performed by a component of the first unit (such as a processor, a chip, or a chip system, etc.) and a component of the third unit (such as a processor, a chip, or a chip system, etc.). In this method, the first unit sends a first request message input by a user to the second unit; the second unit sends a first response message corresponding to the first request message to the first unit; the second unit receives a second request message sent by the first unit, and the second request message is used to confuse the first request message; the first unit receives a second response message corresponding to the second request message sent by the second unit.

[0043] In an embodiment of the present application, a trusted first unit sends real request information and false request information to an untrusted second unit. The first unit can use the false request information to confuse the real request information, so that the untrusted second unit cannot clearly identify the real request information, thereby improving user privacy protection.

[0044] Optionally, in a possible implementation manner of the third aspect, the above steps further include: the first unit obtains the second request information based on the first request information or the first response information.

[0045] In this possible implementation, the false request information corresponding to the real request information is obtained by the trusted first unit, so that the first unit can use the false request information to prevent the untrusted unit from clarifying the real request information, thereby improving user privacy protection.

[0046] Optionally, in a possible implementation manner of the third aspect, the above steps further include: the first unit obtains the second request information based on the first response information.

[0047] In this possible implementation, the real response information is first obtained from the real request information, and then multiple false request information is obtained based on the real response information. Since the second unit generally retrieves logs and other methods within a certain time period, as long as the time interval between the real request information and the false request information is less than the aforementioned time period, the first unit can use multiple false request information to obfuscate the real request information in the log, thereby improving user privacy protection.

[0048] The fourth aspect of an embodiment of the present application provides a first device, which includes: a transceiver unit, used to send a first request information input by a user to a second unit; the transceiver unit, also used to receive a first response information corresponding to the first request information sent by the second unit; the transceiver unit, also used to send a second request information to the second unit, the second request information being used to confuse the first request information; the transceiver unit, also used to receive a second response information corresponding to the second request information sent by the second unit.

[0049] Optionally, in a possible implementation manner of the fourth aspect, the first device further includes: a processing unit, configured to obtain second request information based on the first request information.

[0050] Optionally, in a possible implementation of the fourth aspect, the above-mentioned processing unit is specifically used to determine the first keyword in the first request information; the processing unit is specifically used to obtain the second request information based on the first keyword and the first request information.

[0051] Optionally, in a possible implementation of the fourth aspect, the above-mentioned processing unit is specifically used to determine a first replacement word corresponding to the first keyword; the processing unit is specifically used to replace the first keyword in the first request information with the first replacement word to obtain the second request information.

[0052] Optionally, in a possible implementation of the fourth aspect, the above-mentioned processing unit is specifically used to send the first keyword and the first request information to the third unit; the processing unit is specifically used to receive the second request information sent by the third unit.

[0053] Optionally, in a possible implementation manner of the fourth aspect, the above-mentioned processing unit is specifically configured to determine the first keyword based on a first operation of the user or a first preset rule.

[0054] Optionally, in a possible implementation manner of the fourth aspect, the above-mentioned processing unit is specifically used to send the first request information to the third unit; the processing unit is specifically used to receive the second request information sent by the third unit.

[0055] Optionally, in a possible implementation manner of the fourth aspect, the first device further includes: a processing unit, configured to generate second request information based on the first response information.

[0056] Optionally, in a possible implementation of the fourth aspect, the above-mentioned processing unit is specifically used to obtain third response information based on the first response information; the processing unit is specifically used to obtain second request information based on the third response information.

[0057] Optionally, in a possible implementation of the fourth aspect, the above-mentioned processing unit is specifically used to determine the second keyword in the first response information; the processing unit is specifically used to determine the second replacement word corresponding to the second keyword; the processing unit is specifically used to replace the second keyword in the first response information with the second replacement word to obtain a third response information.

[0058] Optionally, in a possible implementation of the fourth aspect, the above-mentioned first device also includes: a presentation unit, used to present multiple response information or first response information to the user, and the multiple response information includes the first response information and the second response information.

[0059] Optionally, in a possible implementation of the fourth aspect, the above-mentioned transceiver unit is also used to receive the first request information sent by the third unit; the transceiver unit is also used to send multiple response information or first response information to the third unit, and the multiple response information includes the first response information and the second response information.

[0060] Optionally, in a possible implementation manner of the fourth aspect, the first unit or the first device is a question answering device.

[0061] Optionally, in a possible implementation manner of the fourth aspect, the first request information includes at least one of the following: a question, a text processing request, or a translation request.

[0062] The fifth aspect of an embodiment of the present application provides a third device, which includes: a transceiver unit, used to receive a first request message sent by a first unit or a first response message corresponding to the first request message; the transceiver unit is also used to send a second request message to the first unit based on the first request message or the first response message, and the second request message is used to confuse the first request message.

[0063] Optionally, in a possible implementation of the fifth aspect, the third device is deployed on a network server, and the first unit is deployed on a terminal device.

[0064] Optionally, in a possible implementation of the fifth aspect, the above-mentioned transceiver unit is specifically used to obtain the second request information based on the first request information or the first response information, and the transceiver unit is specifically used to send the second request information to the first unit.

[0065] The sixth aspect of an embodiment of the present application provides a first device, comprising: a processor, the processor being coupled to a memory, the memory being used to store programs or instructions, and when the programs or instructions are executed by the processor, the first device implements the method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0066] The seventh aspect of an embodiment of the present application provides a third device, including: a processor, the processor is coupled to a memory, the memory is used to store programs or instructions, and when the program or instructions are executed by the processor, the third device implements the method in any possible implementation of the above-mentioned second aspect.

[0067] An eighth aspect of an embodiment of the present application provides a communication system, which includes the first unit in the above-mentioned first aspect and the second unit in the first aspect, or the communication system includes the first unit in the above-mentioned first aspect, the second unit in the first aspect and the third unit in the second aspect, or the communication system includes the first device in the above-mentioned fourth aspect and the third device in the fifth aspect.

[0068] A ninth aspect of the embodiments of the present application provides a communication system, the communication system including a first unit and a second unit;

[0069] The first unit is configured to send first request information input by a user to the second unit;

[0070] The second unit is configured to send first response information corresponding to the first request information to the first unit;

[0071] The second unit is further configured to receive second request information sent by the first unit, where the second request information is used to obfuscate the first request information;

[0072] The first unit is further configured to receive second response information corresponding to the second request information sent by the second unit.

[0073] The tenth aspect of the embodiment of the present application provides a computer-readable medium on which a computer program or instruction is stored. When the computer program or instruction is run on a computer, the computer executes a method of any possible implementation of any one of the first to third aspects above.

[0074] In an eleventh aspect of the embodiments of the present application, a computer program product is provided. When the computer program product is executed on a computer, the computer executes a method of any possible implementation of any one of the first to third aspects above.

[0075] A twelfth aspect of an embodiment of the present application provides a chip system, which includes at least one processor for supporting a data processing device to implement the functions involved in any possible implementation method of any one of the first to third aspects above.

[0076] In one possible design, the chip system may further include a memory for storing program instructions and data necessary for the data processing device. The chip system may be composed of a chip alone or may include a chip and other discrete components. Optionally, the chip system may also include an interface circuit that provides program instructions and / or data to at least one processor.

[0077] Among them, the technical effects brought about by any design method in the fourth to twelfth aspects can refer to the technical effects brought about by the different design methods in any aspect from the first to third aspects mentioned above, and will not be repeated here.

[0078] It can be seen from the above technical solution that the embodiments of the present application have the following advantages: by obtaining false request information through a trusted unit or device (first unit or third unit), the first unit can use the false request information to confuse the real request information, so that the untrusted unit cannot clearly identify the real request information, thereby improving the user's privacy protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] FIG1A is a schematic diagram of a system architecture provided in an embodiment of the present application;

[0080] FIG1B is another schematic diagram of the system architecture provided in an embodiment of the present application;

[0081] FIG1C is another schematic diagram of the system architecture provided in an embodiment of the present application;

[0082] FIG2 is a flow chart of a data processing method provided in an embodiment of the present application;

[0083] FIG3A is an example diagram of a user interface displayed by the first unit according to an embodiment of the present application;

[0084] FIG3B is another example diagram of a user interface displayed by the first unit according to an embodiment of the present application;

[0085] FIG3C is another example diagram of a user interface displayed by the first unit according to an embodiment of the present application;

[0086] FIG4A is another example diagram of a user interface displayed by the first unit according to an embodiment of the present application;

[0087] FIG4B is another example diagram of a user interface displayed by the first unit according to an embodiment of the present application;

[0088] FIG5 is another flow chart of the data processing method provided in an embodiment of the present application;

[0089] FIG6 is another flow chart of the data processing method provided in an embodiment of the present application;

[0090] FIG7 is another flow chart of the data processing method provided in an embodiment of the present application;

[0091] FIG8 is another flow chart of the data processing method provided in an embodiment of the present application;

[0092] FIG9 is another flow chart of the data processing method provided in an embodiment of the present application;

[0093] FIG10 is another flow chart of the data processing method provided in an embodiment of the present application;

[0094] FIG11 is another flow chart of the data processing method provided in an embodiment of the present application;

[0095] FIG12 is a schematic structural diagram of a data processing device provided in an embodiment of the present application;

[0096] FIG13 is a schematic structural diagram of a first device provided in an embodiment of the present application;

[0097] FIG14 is another structural diagram of the data processing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0098] The embodiments of the present application provide a data processing method and related equipment, which can obtain false request information based on the real request information input by the user or the real response information corresponding to the real request information, use the false request information to confuse the real request information, and then use the false request information to confuse the model, thereby improving the user's privacy protection.

[0099] To facilitate understanding, the following first introduces the relevant terms and concepts mainly involved in the embodiments of this application.

[0100] 1. Neural Network (also called Model)

[0101] A neural network can be composed of neural units. A neural unit can be a unit composed of neural units. s is the weight, b is the bias operation unit, and the output of the operation unit can be:

[0102] Where, s = 1, 2, ... n, n is a natural number greater than 1, W s For X sThe weight of the neural unit, b is the bias of the neural unit. f is the activation function of the neural unit, which is used to introduce nonlinear characteristics into the neural network to convert the input signal in the neural unit into the output signal. The output signal of the activation function can be used as the input of the next convolutional layer. The activation function can be a sigmoid function. A neural network is a network formed by connecting many of the above-mentioned single neural units together, that is, the output of one neural unit can be the input of another neural unit. The input of each neural unit can be connected to the local receptive field of the previous layer to extract the features of the local receptive field. The local receptive field can be an area composed of several neural units.

[0103] 2. Loss Function

[0104] During the training of a deep neural network, because we want the output of the deep neural network to be as close as possible to the desired predicted value, we can compare the current network's predicted value with the desired target value, and then update the weight vector of each layer of the neural network based on the difference between the two. (Of course, there is usually an initialization process before the first update, which is to pre-configure the parameters for each layer in the deep neural network.) For example, if the network's predicted value is too high, the weight vector is adjusted to make it predict a lower value. This adjustment is continued until the neural network can predict the desired target value. Therefore, it is necessary to predefine "how to compare the difference between the predicted value and the target value." This is the loss function or objective function, which is an important equation used to measure the difference between the predicted value and the target value. Among them, taking the loss function as an example, the higher the output value (loss) of the loss function, the greater the difference. Therefore, training a deep neural network becomes a process of minimizing this loss as much as possible.

[0105] 3. Trusted units / devices and untrusted units / devices

[0106] In this application, "trusted" and "untrusted" are relative concepts. "Trusted unit / device" means a unit / device that the user trusts. This application assumes that a "trusted unit / device" will not leak the user's privacy or cause privacy risks to the user after learning about it. Among them, "trusted" can be set by the user, or determined through third-party inspections, etc., or it can be a unit / device that the user has used for a long time. In contrast, "untrusted unit / device" means a unit / device that the user does not trust. This application assumes that an "untrusted unit / device" may leak the user's privacy or there is a risk of privacy being leaked after learning about the user's privacy. Among them, "untrusted" can be set by the user, or determined through third-party inspections, etc., or it can be a unit / device that the user has not used.

[0107] 1A , an embodiment of the present invention provides a system architecture, which includes a user 101 , a first unit 102 , and a second unit 103 .

[0108] The user 101 can be understood as the user of the first unit 102, and the user 101 can operate the first unit 102 by means of voice / touch gestures and other operations. When the user 101 uses the first unit 102, the first unit 102 can independently provide services to the user 101, and can also support joint processing with other devices (such as the third unit 103) to provide services to the user 101.

[0109] The first unit 102 is configured to provide services to the user 101. The first unit 102 may be equipped with an operating system and may be loaded with applications according to the user 101's operation. The first unit 101 may support at least one of the following functions: installing applications, mobilizing cloud services (e.g., public cloud, private cloud, etc.), and built-in services.

[0110] The second unit 103 stores a processing module that processes data to obtain processing results. Alternatively, the second unit 103 can be understood as having a data processing function, which can also be understood as processing user requests (e.g., questioning requests, classification requests, segmentation requests, detection requests, or image generation requests). The processing module can implement the above-mentioned data processing functions using methods such as machine learning. Machine learning includes neural networks, expert systems, symbolic reasoning, decision trees, support vector machines, and the like.

[0111] For the convenience of description, the following description will be given by taking the example of the processing module using a neural network to perform data processing requests. It can be understood that in actual applications, the processing module in the second unit can also use other machine learning methods to implement data processing functions, which is not limited here.

[0112] Optionally, user 101 inputs request information to first unit 102, which then sends the request information to second unit 102. Second unit 103 processes the request information using a neural network to obtain response information, and returns the response information to first unit 102. First unit 102 can then display the response information to user 101.

[0113] When the neural network stored in the second unit 103 is a large language model (LLM), since the model itself has very powerful reasoning capabilities but is limited by factors such as training data, in order to better obtain effective reasoning results, we need to perform a series of processing on the input request information (i.e., the input data of the neural network). These processing methods include but are not limited to:

[0114] 1) Introducing external knowledge (search, knowledge base): Using search engines, vector knowledge bases, and other methods, we retrieve and ask questions with relevant professional knowledge. This knowledge is combined with the question content to form a prompt word input model to obtain response information, thereby improving the reliability of the professional knowledge involved in the answer.

[0115] 2) Request Information Decomposition / Thinking Chain: For overly long and complex request information, which requires strong reasoning capabilities and cannot be directly processed by large models, we can reasonably decompose the request information, breaking down complex request information into a series of simpler request information combinations and allowing the model to gradually solve them.

[0116] 3) Apply new templates to control the response information method: For some request information, we can use the characteristics of the large model to embed the request information into a specific template and require the model output to meet our specific needs.

[0117] We collectively refer to the above processing methods as prompt engineering, which is one of the best ways to use large language models to resolve request information and obtain effective response information.

[0118] Because large language models require very high inference computing power, most users currently use large models through models mounted on cloud services (i.e., the neural network in the second unit 103 shown in Figure 1A). This results in the user's request information and corresponding response information actually being transmitted outside the user's local machine (i.e., the first unit 102 shown in Figure 1A), which can lead to a series of problems and hidden dangers, including but not limited to:

[0119] 1) User privacy data is used for model training. Large model training relies on high-quality data. Currently, many commercial models use user request and response information as training data, which is internalized into the model's capabilities. This results in user data being stored on the service provider's side for a long time, bringing unknown risks.

[0120] 2) User privacy data is leaked in the model. As mentioned in 1), user data is used for training. Therefore, during inference, there is a risk of user privacy data being leaked when training on other users. Attackers can steal or reconstruct LLM training data through techniques such as model extraction, model inversion, or membership inference.

[0121] 3) User profiles based on user request information. Based on information such as the user's historical requests, service providers can build user profiles to provide a series of services such as advertising push.

[0122] The above behaviors will have a significant impact on the privacy and security of user data. Due to the current flourishing of large-scale models and the mixed quality, it is difficult for users to distinguish which model services are safe and which are dangerous. Therefore, we need some technologies that allow us to still use the model capabilities normally while minimizing the leakage of user privacy.

[0123] When we use the large model inference service, an untrusted service provider (i.e., the second unit 103 shown in FIG1A ) can obtain our questions and answers. Using these answers, whether for training its own model or for other purposes, will seriously infringe the user's privacy. Based on this assumption, we need a method to prevent the untrusted service provider from obtaining and using the user's actual request information and response information, while not affecting the user's ability to obtain the desired response information.

[0124] Existing technologies mainly focus on how to protect server-side models to avoid contamination by poisoned data from malicious attacks; or to avoid privacy leakage to a certain extent by replacing the content of user request information at the expense of the accuracy of the request information. These are either based on the trustworthiness of the service provider or have a significant impact on the performance of the response information of the request information. Therefore, a method to prevent data from being used for other purposes and to ensure that the original response information is obtained is necessary.

[0125] The following examples illustrate the existing problems of several existing technologies.

[0126] Example 1: The paper "Privacy-Preserving Prompt Tuning for Large Language Model Services" proposes a method called RAPT (privacy-preserving prompt tuning). It uses local differential privacy and user-specific tuning on the server to prevent intruders from obtaining private information locally and in the cloud through embedding invertion attacks and attribute inference attacks.

[0127] The disadvantages of this method are that removing information may reduce the accuracy on the differential privacy side, and the framework assumes that the service provider is reliable, which cannot play a role in privacy protection in our setting.

[0128] Example 2: Replace the user's privacy and other sensitive information with general entity information (such as name, birthday, etc.) and then ask questions to avoid privacy leakage.

[0129] The advantage of this method is that it can indeed avoid privacy leaks, but too much entity masking will greatly reduce the accuracy (for example, when providing birthdays to calculate certain dates, masking the birthday will make it completely impossible to process).

[0130] In order to solve the above technical problems, a trusted unit or device obtains false request information based on the real request information input by the user or the real response information corresponding to the real request information, and uses the false request information to confuse the real request information, thereby using the false request information to confuse the model, thereby improving the user's privacy protection.

[0131] First, the system architecture to which the method provided in the embodiment of the present application is applicable is described.

[0132] The first one is the system architecture shown in Figure 1A.

[0133] In the system architecture shown in Figure 1A, if the first unit 102 is a trusted unit, the first unit 102 can process the real request information input by the user 101 to obtain multiple false request information, and then send the real request information and the multiple false request information to the second unit 103. The second unit 103 infers the real request information and the multiple false request information through a large model to obtain multiple response information.

[0134] In this case, for the second unit 103, the request information received by the second unit 103 includes multiple false request information in addition to the real request information, so the second unit 103 cannot clearly determine which request information received is the real request information, thereby improving user privacy protection.

[0135] The second is the system architecture shown in Figure 1B.

[0136] The system architecture shown in Figure 1B includes: user 101, first unit 104, third unit 105, and second unit 106. Third unit 105 cannot communicate directly with second unit 106 and must use first unit 104 as an intermediary. Compared to the system architecture in Figure 1A, a trusted unit is added: third unit 105. First unit 104 obtains the real request information input by user 101 and sends the real request information to third unit 105. Third unit 105 processes the real request information to obtain multiple false request information and returns the multiple false request information to first unit 104. First unit 104 then sends the real request information and the multiple false request information to second unit 106. Second unit 106 then uses the large model to infer the real request information and the multiple false request information to obtain multiple response information and returns the multiple response information to first unit 104. The first unit 104 may directly display the multiple response messages or the real response messages to the user 101 , or perform certain processing (such as screening, rendering, format conversion, etc.) on the multiple response messages or the real response messages before presenting them to the user 101 .

[0137] In this case, the trusted third unit 105 obfuscates the real request information. For the second unit 106, the request information received by the second unit 106 includes multiple false request information in addition to the real request information. Therefore, the second unit 106 cannot clearly determine which request information received is the real request information, thereby improving the user's privacy protection.

[0138] The third type is the system architecture shown in Figure 1C.

[0139] In the system architecture shown in Figure 1C, the system architecture includes: user 101, third unit 107, first unit 108, and second unit 109. First unit 108 and second unit 109 are in the same cloud (as shown in Figure 1C). In this case, third unit 107 obtains the real request information input by the user and sends the real request information to first unit 108. After first unit 108 processes the real request information to obtain multiple false request information, it can directly send the real request information and the multiple false request information to second unit 109. Second unit 109 uses a large model to infer the real request information and the multiple false request information to obtain multiple response information, and then returns the multiple response information to first unit 108. First unit 108 can directly return the multiple response information to third unit 107. Third unit 107 can directly present the multiple response information to user 101, or it can filter out the real response information from the multiple response information and present it to user 101. Of course, the first unit 108 may also filter out the real response information from the multiple response information and send the real response information to the third unit 107, so that the third unit 107 presents the real response information to the user 101. That is, the step of filtering the real response information may be performed by the third unit 107 or by the first unit 108, and the specific details are not limited here.

[0140] It is understood that the aforementioned request information or data may refer to text, images, audio, video, etc. Furthermore, there is no limitation on the number of users and devices in the system architecture shown in Figures 1A to 1C , i.e., the number of users, first units, and third units may be greater. Furthermore, the system architectures shown in Figures 1A to 1C are merely examples. In actual applications, the methods provided in the embodiments of the present application may also be applied to other architectures, which are not specifically limited here.

[0141] It is understandable that the units in the system architecture shown in Figures 1A to 1C are only examples in which the units do not belong to different physical devices. In actual applications, the units in the system architecture shown in Figures 1A to 1C can each belong to an independent physical device, or two units can belong to the same physical device, etc., and the specific details are not limited here. For example, the first unit is deployed on the first device, the second unit is deployed on the second device, and the third unit is deployed on the third device. For another example, the first unit is deployed on the first device, and the second unit and the third unit are deployed on the same physical device or platform. For another example, the second unit is a plug-in for the first device (such as a pluggable component such as a U shield or a U disk).

[0142] In the embodiment of the present application, the first unit in the system architecture shown in Figures 1A and 1B or the third unit in the system architecture shown in Figure 1C can be a terminal device or question answering device that provides services to user 101. The terminal device can be deployed on land, including indoors or outdoors, handheld, wearable, or vehicle-mounted; it can also be deployed on the water (such as a ship); it can also be deployed in the air (such as an airplane, a balloon, and a satellite). The terminal device can be a mobile phone (such as a foldable phone, a non-foldable phone), a tablet computer (Pad), a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control, a vehicle-mounted terminal device, a wireless terminal in self-driving, a wireless terminal in remote medical, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, a wearable terminal device, etc. The embodiments of the present application do not limit the application scenarios. Terminal equipment may also be sometimes referred to as terminal, user equipment (UE), access terminal equipment, vehicle-mounted terminal, industrial control terminal, UE unit, UE station, mobile station, mobile station, remote station, remote terminal equipment, mobile device, UE agent, or UE device. Terminal equipment may also be fixed or mobile.

[0143] The second unit in the embodiment of the present application is an untrusted unit, which can be a device or server that processes data through a neural network. For example, the second unit can be a cloud server, a network server, an application server, a management server, a wireless controller, or other device or server with data processing capabilities.

[0144] The first and third units in the embodiments of the present application are trusted units, devices or servers that can obfuscate the actual request information. For example, the third unit in the system architecture shown in FIG1B can be a proxy device (agent), cloud server, network server, application server, management server, wireless controller, or other device or server that can obfuscate the actual request information.

[0145] The data processing method provided in the embodiment of the present application is described below in conjunction with the system architecture of Figures 1A to 1C above.

[0146] Please refer to Figure 2, which is a flow chart of a data processing method provided in an embodiment of the present application. The method may include steps 201 to 209. Steps 201 to 209 are described in detail below. The method shown in Figure 2 can be applied to any of the system architectures shown in Figures 1A to 1C above.

[0147] Step 201: The first unit receives first request information input by a user.

[0148] The first unit receives a first request message input by a user. The first request message in the embodiment of the present application can also be understood as request message input by the user, specifically a question (also referred to as a question) input / selected by the user, a text processing request (for example, a summary analysis request) input / selected by the user, a translation request input / selected by the user, etc., which is not specifically limited here. In addition, in the embodiment of the present application, the request information (for example, the first request message, the second request message, etc.) can be carried in a text, image, voice, etc., which is not specifically limited here.

[0149] For ease of understanding, the first request information in the embodiment of the present application can be understood as real request information, the second request information can also be understood as false request information, the first response information can also be understood as real response information, and the second response information can also be understood as false response information.

[0150] In an embodiment of the present application, there are multiple ways for the first unit to obtain the first request information. The way may be that the user directly inputs the first request information into the first unit (for example, keyboard input, voice input, etc.), or the way may be that the user selects in the interface displayed by the first unit (for example, selection, typing input, etc.), or the way may be that the user selects from the database, or the way may be that the information is forwarded by other devices (for example, in Figure 1C, the first unit can receive the first request information forwarded by the third unit), etc., and the specific details are not limited here.

[0151] In a possible implementation, the user may directly input the first request information to the first unit through an external device (such as a USB flash drive, a keyboard, a mouse, etc.).

[0152] In another possible implementation, the first unit may determine the first request information based on a user operation. For example, the first unit may display an interface to the user, the interface including multiple options, and then determine the first request information based on the user's operation on the multiple options (e.g., a click selection operation, a voice operation, etc.).

[0153] Example 1, taking the case where the first request information is a question and the carrier method is text, the first request information is: What are the symptoms of stomach problems? In this example, the example of the first unit obtaining the first request information can be shown in Figures 3A to 3C. The first unit first displays the first interface shown in Figure 3A to the user, and the 301 area in the first interface is for the user to enter the request information. After the user enters the request information in area 301, as shown in Figure 3B, the user can click Send 302 to transmit the request information to the first unit. After receiving the request information entered by the user, the first unit can display the second interface as shown in Figure 3C. The second interface includes the request information entered in the user window and the prompts of the assistant window during processing. It can be understood that Figure 3C may also not include the prompts of the assistant window during processing, and the specific details are not limited here.

[0154] Example 2: The first request information is: How should I lose weight if I weigh 200 pounds?

[0155] Step 202: The first unit sends a first request message to the second unit.

[0156] After obtaining the first request information, the first unit may send the first request information to the second unit. Correspondingly, the second unit receives the first request information sent by the first unit.

[0157] In step 203, the second unit obtains first response information through the neural network.

[0158] After the second unit obtains the first request information, it obtains the first response information through the neural network. For example, if the first request information is a question, the first response information can also be understood as an answer.

[0159] For ease of understanding, the above-mentioned first response information can be understood as true response information.

[0160] The neural network in the embodiments of the present application can be a convolutional neural network (CNN), a feedforward neural network (FNN), a recursive neural network (RNN) (such as a long short-term memory network, a gate-controlled recurrent unit, an attention network, etc.), Transformers, a generative adversarial network (GAN), LLM, etc. The embodiments of the present application do not limit the specific structure, type, and training method of the neural network.

[0161] Optionally, the second unit inputs the first request information into the neural network to obtain first response information.

[0162] Step 204: The second unit sends a first response message to the first unit.

[0163] After obtaining the first response information, the second unit sends the first response information to the first unit. Correspondingly, the first unit receives the first response information sent by the second unit.

[0164] Step 205: The first unit obtains second request information based on the first request information or the first response information.

[0165] In the embodiment of the present application, the number of second request information may be one or more. It is understandable that in order to improve the obfuscation effect, the number of second request information is usually multiple, and the following description will also be made using multiple second request information as an example.

[0166] The second request information in the embodiment of the present application is used to confuse the first request information, or it can be understood that the first request information is the real request information input by the user, and the second request information is a false request information constructed based on the real request information or the real response information corresponding to the real request information.

[0167] Optionally, the specific situation of the second request information is similar to the first request information. The second request information can specifically be a question (also called a problem), a text processing request (for example, a summary and analysis request), a translation request, etc., which is not specifically limited here.

[0168] Generally speaking, the second request information has the same or similar tasks as the first request information, or the second request information has overlapping parts with the first request information. For example, the first request information is: What are the symptoms of stomach disease? The second request information includes what are the symptoms of liver disease? The first request information in this example has similar tasks to the second request information (for example, the task is to ask about symptoms). For another example, the first request information is: What are the symptoms of stomach disease? The second request information includes which hospitals are suitable for treating stomach disease? The first request information in this example has similar overlapping parts to the second request information (for example, both are questions about stomach disease).

[0169] There are multiple situations in this step, which are described below.

[0170] In a first method, the first unit obtains a plurality of second request information based on the first request information.

[0171] This situation can be understood as follows: in this embodiment, the first request message and multiple second request messages are carried in the same message, and the first response message and multiple second response messages are carried in the same message. In other words, it can be understood that the first unit can simultaneously send the first request message and multiple second request messages to the second unit. The second unit can simultaneously send the first response message and multiple second response messages to the first unit.

[0172] In an embodiment of the present application, the first unit may obtain multiple second request information based on the first request information and the keyword. The first unit may also obtain multiple second request information based on the first request information and a preset rule. The first unit may also send the first request information to other units and receive multiple second request information fed back by other units. The first unit may also obtain multiple second request information based on the first request information and user operations, etc., which are not limited here. The following is an exemplary description using the example of the first unit obtaining multiple second request information based on the first request information and the keyword.

[0173] In the embodiment of the present application, there are many ways for the first unit to determine the keyword. It can be determined through the user's selection operation, or it can be determined through the first preset rule, or it can be determined by other devices forwarding the keyword determined by the user, or it can be determined by sending the first request information to other devices (such as the third unit, etc.), and the other devices determine the keyword and return it to the first unit (for example, in Figure 1C, the first unit can receive the keyword forwarded by the third unit), etc., and the specific details are not limited here.

[0174] Among them, the above-mentioned first preset rule can be related to at least one of the following: name, address, place of origin, job, company name, number, date, sentence components (such as subject, predicate, object, attributive, etc.), units of magnitude, nouns, verbs, adjectives, adverbs indicating degree, colors, sports events, disease names, etc., which involve user privacy, and are not limited here.

[0175] Optionally, the keyword is a word in the first request information (in this case, it may also be referred to as the first keyword). After the first unit obtains the first request information, it may first determine the first keyword in the first request information, and then obtain multiple second request information based on the first keyword and the first request information.

[0176] Exemplarily, continuing with the examples of the aforementioned Figures 3A to 3C, and taking the first keyword as an example of a word in the first request information, as shown in Figure 4A. After the user inputs the request information, the first unit displays a third interface. The third page includes a user window and an assistant window. The assistant window is used to determine the first keyword in the first request information through interaction with the user. For example, as shown in the assistant window of Figure 4A, "Please indicate the first keyword in the request information by clicking or entering a serial number, etc.: 1. Stomach disease 2. Symptoms...". Further, as shown in Figure 4B, the first unit responds to the user's click operation 401 to determine that the first keyword in the first request information includes "stomach disease" and "symptoms" (not shown in the figure).

[0177] In addition, in the embodiment of the present application, there is no limitation on the number of first keywords, which can be one or more.

[0178] In an embodiment of the present application, there are many ways for the first unit to obtain multiple second request information based on the first request information and the first keyword. It can be obtained through user operations, or through a second preset rule, or by sending the first request information and the first keyword to other devices (such as a third unit, etc.), and the other devices determine multiple second request information based on the first request information and the first keyword and return them to the first unit (for example, in Figure 1C, the first unit sends the first request information and the first keyword to the third unit, and the third unit can determine multiple second request information based on the first request information and the first keyword, and send multiple second request information to the first unit), etc., and the specific details are not limited here.

[0179] In one possible implementation, the first unit first determines a plurality of first replacement characters based on a second preset rule and the first keyword; then replaces the first keyword in the first request information with the plurality of first replacement characters to obtain a plurality of second request information. The second preset rule is associated with at least one of the following: synonyms, similar words, shuffling, multiplication by a random number (for numbers), replacement characters related to the first keyword, antonyms, etc.

[0180] Since the purpose of the embodiment of the present application is to obfuscate the real request information, in addition to the above-mentioned second preset rule, the obfuscation method can also be table lookup, model generation, manual input, analogical reasoning, mathematical solution, etc.

[0181] For example, if the first request information involves a numeric sequence such as an identification number, a bank card number, or a postal code, and the first keyword includes the numeric sequence, determining the multiple first replacement characters based on the second preset rule and the first keyword may include randomly shuffling the numbers in the numeric sequence or multiplying them by a random number to obtain the first replacement characters. For another example, if the first keyword includes a user's name, address, or place of origin, determining the multiple first replacement characters based on the second preset rule and the first keyword may include randomly replacing characters in the first keyword (such as modifying the surname, address, or place of origin).

[0182] For example, continuing with the example 1 above, the first request information is: What are the symptoms of stomach disease? The first keywords include: "stomach disease" and "symptoms". The first unit determines that the replacement words for "stomach disease" include "liver disease" and "kidney disease" through similar words. The first unit determines that the replacement words for "symptoms" include "treatment methods" and "hospital for treatment" through replacement words related to the first keyword. Therefore, multiple second request information obtained by bringing the replacement words into the first request information to replace the corresponding first keywords include: "What are the symptoms of kidney disease?", "What are the symptoms of liver disease?", "What are the treatment methods for liver disease?" and "What are the hospitals for gastric disease?".

[0183] In another possible implementation, the first unit sends a first request message and a first keyword to the third unit, and the third unit generates multiple second request messages based on the first request message and the first keyword. The first unit then receives the multiple second request messages sent by the third unit. Alternatively, the first unit can directly send the first request message to the third unit, and the third unit can determine the first keyword of the first request message, obtain multiple second request messages based on the first keyword, and return the multiple second request messages to the first unit.

[0184] Second, the first unit obtains multiple second request information based on the first response information.

[0185] This scenario can be understood as follows: in this embodiment, the first request message and multiple second request messages are carried in different messages, and the first response message and multiple second response messages are carried in different messages. In other words, the first unit can first send the first request message to the second unit, receive the first response message, then send multiple second request messages to the second unit, and receive multiple second response messages.

[0186] After receiving the first request, the first unit sends the first request to the second unit. The second unit receives the first response through the neural network and sends the first response to the first unit. The first unit then obtains multiple third responses based on the first response and then reversely infers multiple second request messages based on the multiple third responses.

[0187] Optionally, the first unit may determine the second keyword in the first response message and obtain multiple third response messages based on the second keyword in the first response message. The first unit may also send the first response message to the third unit, which generates multiple third response messages based on the first response message and returns the third response messages to the first unit. The method of obtaining multiple third response messages based on the second keyword is similar to the method of obtaining multiple second request messages based on the first keyword, and will not be repeated here.

[0188] Of course, the first unit may also directly reverse deduce the multiple third response messages to obtain the multiple second request messages, or may send the multiple third response messages to the third unit, which then reverse deduce the multiple third response messages to obtain the multiple second request messages and return the multiple second request messages to the first unit. Alternatively, the first unit may send the first response message to the third unit, which then obtains the multiple second request messages based on the first response message and then returns the multiple second request messages to the first unit.

[0189] The above-mentioned reverse inference process can be carried out by the user, the text generation network, preset rules, etc., and the specific details are not limited here. For example, take the example of the first unit obtaining the second request information corresponding to the third response information through the text generation network. The text generation network can be trained with the training data as input and the loss function value less than a threshold as the goal. The loss function is used to represent the difference between the output of the text generation network and the label of the training data.

[0190] Example 2: The first request is: How should I lose weight if I weigh 200 pounds? The second unit responds with the following first response based on the first request: Eat less and exercise more. The first or third unit can determine, using synonyms and antonyms, that the second keywords in "Eat less and exercise more" include "drink more" and "rest more." They can also determine that the replacement for "Eat less" includes "drink more." They can also determine that the replacement for "Exercise more" includes "rest more." By replacing the replacement keywords in the first response with the corresponding second keywords, the resulting multiple second responses include: "Drink more and exercise more," "Drink more and rest more," and "Drink less and rest more." The second response, "Drink more and exercise more," can be inferred to yield the second request, "What precautions should I take for kidney stones?" The first unit infers the second response, "Drink more and rest more," to yield the second request, "How should I recuperate after surgery?" The first unit infers the second response, "Drink less and rest more," to yield the second request, "What should I do if I often drink coffee and can't sleep at night?"

[0191] Step 206: The first unit sends multiple second request information to the second unit.

[0192] After receiving multiple second request messages, the first unit can send multiple second request messages to the second unit. In return, the second unit receives the multiple second request messages sent by the first unit. These multiple request messages are used to obfuscate the first request message, making it difficult for the second unit to identify the true request message, thereby enhancing user privacy.

[0193] In the embodiments of the present application, the use of fake request information to obfuscate real request information can also be understood as using fake request information to obscure real request information. Alternatively, by mixing fake request information with real request information, untrusted units are unable to clearly identify the real request information within the mixed request information. This allows the real request information to be protected by fake request information, thereby reducing user privacy leaks in the real request information.

[0194] In step 207 , the second unit obtains a plurality of second response information through the neural network.

[0195] After the second unit obtains the plurality of second request messages, it obtains the plurality of second response messages through the neural network, where the plurality of second response messages correspond to the plurality of second request messages.

[0196] For ease of understanding, the aforementioned multiple second response messages can be understood as multiple false response messages.

[0197] The neural network in the embodiments of the present application can be a convolutional neural network (CNN), a feedforward neural network (FNN), a recursive neural network (RNN) (such as a long short-term memory network, a gate-controlled recurrent unit, an attention network, etc.), Transformers, a generative adversarial network (GAN), LLM, etc. The embodiments of the present application do not limit the specific structure, type, and training method of the neural network.

[0198] Optionally, the second unit inputs multiple second request information into the neural network to obtain multiple second request information. It is understandable that the input can be divided into multiple times or input once, and the specific details are not limited here.

[0199] Step 208: The second unit sends a plurality of second response messages to the first unit.

[0200] After obtaining the plurality of second response messages, the second unit sends the plurality of second response messages to the first unit. Correspondingly, the first unit receives the plurality of second response messages sent by the second unit.

[0201] Step 209: The first unit presents response information.

[0202] After receiving the first response information and multiple second response information sent by the second unit, the first unit may present response information to the user, where the response information includes the first response information, or includes multiple second response information and the first response information.

[0203] In a possible implementation, the first unit directly presents a plurality of response information to the user, where the plurality of response information includes a first response information and a plurality of second response information.

[0204] Optionally, the first unit may further present indication information to the user, where the indication information is used to indicate the position of the first response information among the plurality of response information, so that the user can clearly identify the real response information.

[0205] It is understood that there are various ways for the first unit to determine the position of the correct response information among the multiple response messages. For example, when the first unit sends the first request message and multiple second request messages to the second unit, the first unit may record the position of the first request message, thereby determining the position of the first response message among the multiple response messages. Alternatively, when the first unit sends the first request message and multiple second request messages to the second unit, the first unit may attach an identifier to each request message to facilitate subsequent determination of the position of the correct response information based on the identifier, etc. The specifics are not limited here.

[0206] In another possible implementation, the first unit performs certain processing (such as screening, rendering, format conversion, etc.) on the multiple response information and then presents them to the user.

[0207] In addition, the presentation in the embodiments of the present application may include at least one of the following: display, voice playback, etc. For example, the first unit may display the response information to the user, or may present the response information to the user through voice broadcast, etc. The present application does not limit the specific presentation method.

[0208] It should be noted that there is no time sequence restriction for each step in the embodiments of the present application, which is illustrated below with examples.

[0209] In one possible implementation, step 202 and step 206 are the same step (or the first request message in step 202 and the multiple second request messages in step 206 are carried in the same message), step 203 and step 207 are the same step, and step 204 and step 208 are the same step (or the first response message in step 204 and the multiple second response messages in step 208 are carried in the same message). This means that the first unit can simultaneously send the first request message and the multiple second request messages to the second unit. The second unit can simultaneously send the first response message and the multiple second response messages to the first unit. In this case, the embodiment shown in FIG. 2 can be described as the embodiment shown in FIG. 5. That is, the method shown in FIG. 2 can be equivalent to the following steps 501 to 506. Step 501: The first unit receives the first request message input by the user. Step 502: The first unit obtains multiple second request messages based on the first request message. Step 503: The first unit sends the first request message and the multiple second request messages to the second unit. Step 504: The second unit obtains multiple response messages through a neural network. In step 505, the second unit sends multiple response messages to the first unit. In step 506, the first unit presents the response messages. For details about FIG. 5 , please refer to the above description and will not be repeated here.

[0210] In another possible implementation, step 202 and step 206 are different steps (or understood as the first request information in step 202 and the multiple second request information in step 206 are carried in different messages), step 203 and step 207 are different steps, and step 204 and step 208 are different steps (or understood as the first response information in step 204 and the multiple second response information in step 208 are carried in different messages). That is, it can be understood that the first unit can first send the first request information to the second unit and receive the first response information. Then send multiple second request information to the second unit. Receive multiple second response information. The embodiment shown in Figure 2 in this case can be described as the embodiment shown in Figure 6 or Figure 7. That is, the method of the embodiment shown in Figure 2 can be equivalent to the following embodiment shown in Figure 6 or Figure 7.

[0211] In an embodiment of the present application, on the one hand, multiple false request information corresponding to the real request information is obtained through a trusted unit (the first unit or the third unit), and the first unit can use multiple false request information to confuse the real request information, so that the untrusted unit cannot clearly identify the real request information, thereby improving the user's privacy protection. On the other hand, the real answer is first obtained through the real request information, and then the real answer is confused to obtain multiple false answers, so that the multiple false answers can be reversely inferred to obtain multiple false request information. Because under normal circumstances, the second unit retrieves the log and other methods within a certain time period, as long as the second unit infers that the time interval between the real request information and the false request information is less than the above time period. In terms of the manifestation of the log, the first unit can confuse the real request information through multiple false request information, thereby improving the user's privacy protection.

[0212] It can be understood that, in one possible implementation, the embodiment shown in Figure 2 is applicable to the scenario shown in Figure 1A above, and the first unit in the embodiment shown in Figure 2 refers to the first unit in Figure 1A above, and the second unit in the embodiment shown in Figure 2 refers to the second unit in Figure 1A above.

[0213] In another possible implementation, the embodiment shown in Figure 2 is applicable to the scenario shown in Figure 1B above. The first unit in the embodiment shown in Figure 2 refers to the first unit in Figure 1B above, and the second unit in the embodiment shown in Figure 2 refers to the second unit in Figure 1B above.

[0214] In another possible implementation, the embodiment shown in FIG2 is applicable to the scenario shown in FIG1C above, and the first unit in the embodiment shown in FIG2 refers to the first unit in FIG1C above, and the second unit in the embodiment shown in FIG2 refers to the second unit in FIG1C above. In this case, the first unit in the embodiment shown in FIG2 obtains the first request information by receiving the information sent by other devices (such as the third unit), and after the first unit in the embodiment shown in FIG2 obtains multiple response information, it sends multiple response information or the first response information to the other devices (such as the third unit).

[0215] Please refer to Figure 6, which is another flowchart of the data processing method provided by an embodiment of the present application. The method may include steps 601 to 609. Steps 601 to 609 are described in detail below. The method shown in Figure 6 can be applied to the system architecture shown in Figure 1B above.

[0216] Step 601: The first unit receives first request information input by a user.

[0217] For step 601 in this embodiment, reference may be made to the description of step 201 in the embodiment shown in FIG. 2 , and details thereof will not be repeated here.

[0218] Step 602: The first unit sends first request information to the third unit.

[0219] After obtaining the first request information, the first unit sends the first request information to the third unit. Correspondingly, the third unit receives the first request information sent by the first unit.

[0220] Step 603: The third unit determines the first keyword in the first request information.

[0221] Step 604: The third unit obtains a plurality of second request information based on the first keyword and the first request information.

[0222] Step 603 and step 604 in this embodiment may refer to the description of step 205 in the embodiment shown in FIG. 2 , and will not be repeated here.

[0223] Step 605: The third unit sends multiple second request information to the first unit.

[0224] After obtaining the multiple second request information, the third unit may send the multiple second request information to the first unit. Correspondingly, the first unit receives the multiple second request information sent by the third unit.

[0225] It is understandable that the third unit may also send the first request information and multiple second request information to the first unit. Correspondingly, the first unit receives the first request information and multiple second request information sent by the third unit.

[0226] Step 606: The first unit sends a first request message and a plurality of second request messages to the second unit.

[0227] In step 607, the second unit obtains a plurality of response information through the neural network.

[0228] Step 608: The second unit sends multiple response messages to the first unit.

[0229] Step 609: The first unit presents response information.

[0230] Steps 606 to 609 in this embodiment may refer to the description of steps 202, 204, 206, 208 and 209 in the embodiment shown in FIG. 2 , and are not repeated here.

[0231] In an embodiment of the present application, multiple false request information corresponding to the real request information is obtained through a third-party device (i.e., the third unit) of the trusted unit. The first unit can use multiple false request information to confuse the real request information, so that the untrusted unit cannot clearly identify the real request information, thereby improving the user's privacy protection.

[0232] Please refer to Figure 7, which is another flowchart of the data processing method provided by an embodiment of the present application. The method may include steps 701 to 709. Steps 701 to 709 are described in detail below. The method shown in Figure 7 can be applied to the system architecture shown in Figure 1C above.

[0233] Step 701: The first unit receives first request information input by a user.

[0234] For step 701 in this embodiment, reference may be made to the description of step 201 in the embodiment shown in FIG. 2 , and details thereof will not be repeated here.

[0235] Step 702: The first unit sends first request information to the third unit.

[0236] After obtaining the first request information, the first unit sends the first request information to the third unit. Correspondingly, the third unit receives the first request information sent by the first unit.

[0237] Step 703: The third unit determines the first keyword in the first request information.

[0238] Step 704: The third unit obtains a plurality of second request information based on the first keyword and the first request information.

[0239] Step 703 and step 704 in this embodiment may refer to the description of step 205 in the embodiment shown in FIG. 2 , and will not be repeated here.

[0240] Step 705: The third unit sends a first request message and a plurality of second request messages to the second unit.

[0241] After obtaining the plurality of second request information, the third unit may send the first request information and the plurality of second request information to the second unit. Correspondingly, the first unit receives the plurality of second request information sent by the third unit.

[0242] The third unit in this embodiment can communicate directly with the second unit.

[0243] In step 706, the second unit obtains a plurality of response information through the neural network.

[0244] For step 706 in this embodiment, reference may be made to the description of step 203 and step 207 in the embodiment shown in FIG. 2 , and details thereof will not be repeated here.

[0245] Step 707: The second unit sends multiple response messages to the third unit.

[0246] After the second unit obtains the multiple response messages, it can send the multiple response messages to the third unit. Correspondingly, the third unit receives the multiple response messages sent by the second unit.

[0247] Step 708: The third unit sends a plurality of response messages or a first response message to the first unit.

[0248] After receiving the multiple response messages sent by the second unit, the third unit may send multiple response messages or the first response message to the first unit. Correspondingly, the first unit receives the multiple response messages or the first response message sent by the third unit.

[0249] In a possible implementation, after obtaining the multiple response messages, the third unit directly forwards the multiple response messages to the first unit.

[0250] In another possible implementation, after obtaining the multiple response messages, the third unit performs certain processing (such as screening, rendering, format conversion, etc.) on the multiple response messages, and then sends the processed response messages to the first unit.

[0251] Step 709: The first unit presents response information.

[0252] For step 709 in this embodiment, reference may be made to the description of step 209 in the embodiment shown in FIG. 2 , and details thereof will not be repeated here.

[0253] In an embodiment of the present application, multiple false request information corresponding to the real request information is obtained through a trusted unit or device (i.e., the third unit). The first unit can use multiple false request information to confuse the real request information, so that the untrusted unit cannot clearly identify the real request information, thereby improving the user's privacy protection.

[0254] The embodiments shown in Figures 6 and 7 above describe a method for directly replacing keywords in a real request message to obtain multiple fake request messages. The following describes a method for replacing keywords in a real response message to obtain multiple fake answers, and then inferring multiple fake request messages based on the multiple fake answers.

[0255] Please refer to Figure 8, which is another flowchart of a data processing method provided in an embodiment of the present application. The method may include steps 801 to 811. Steps 801 to 811 are described in detail below. The method shown in Figure 8 can be applied to any of the system architectures shown in Figures 1A to 1C above.

[0256] Step 801: The first unit receives first request information input by a user.

[0257] For step 801 in this embodiment, reference may be made to the description of step 201 in the embodiment shown in FIG. 2 , and details thereof will not be repeated here.

[0258] For example, the first request information is: How should I lose weight if I weigh 200 kilograms?

[0259] Step 802: The first unit sends first request information to the second unit.

[0260] After obtaining the first request information, the first unit sends the first request information to the second unit. Correspondingly, the second unit receives the first request information sent by the first unit.

[0261] Step 803: The second unit obtains first response information through the neural network.

[0262] After receiving the first request information, the second unit obtains first response information through the neural network.

[0263] Optionally, the second unit inputs the first request information into the neural network to obtain first response information.

[0264] The neural network, the first request information, and the first response information in this embodiment can refer to the description in the embodiment shown in FIG2 above, and will not be repeated here.

[0265] For example, continuing the example of the first request information above, the first response information is: eat less and exercise more.

[0266] Step 804: The second unit sends a first response message to the first unit.

[0267] After obtaining the first response information, the second unit sends the first response information to the first unit. Correspondingly, the first unit receives the first response information sent by the second unit.

[0268] Optionally, after obtaining the first response information, the first unit may present the first response information to the user.

[0269] Step 805: The first unit determines the second keyword in the first response information.

[0270] After obtaining the first response information, the first unit determines a second keyword in the first response information.

[0271] In this embodiment, there are multiple ways for the first unit to determine the second keyword in the first response information. It can be determined through the user's selection operation, or through a third preset rule, or by sending the first response information to other devices (such as a third unit, etc.), and having other devices determine the second keyword and return it to the first unit, etc. The specific methods are not limited here.

[0272] The third preset rule is similar to the first preset rule used to determine the first keyword in the first request information in the embodiment shown in FIG. 2 , and is not limited here.

[0273] Exemplarily, continuing the example of the first request information and the first response information, the first unit may determine that the second keyword in "eat less and exercise more" includes "drink more" and "rest more" through similar words and antonyms.

[0274] Step 806: The first unit obtains a plurality of second response information based on the second keyword and the first response information.

[0275] After the first unit obtains the keyword, it may obtain a plurality of second response information based on the keyword and the first response information.

[0276] In an embodiment of the present application, there are many ways for the first unit to obtain multiple second response messages, which can be obtained through user operations, or through a fourth preset rule, or by sending the first response message and the second keyword to other devices (such as the third unit, etc.), and the other devices determining multiple second response messages based on the first response message and the second keyword and returning them to the first unit, etc. The specific methods are not limited here.

[0277] The fourth preset rule is similar to the second preset rule used to obtain multiple second request information in the embodiment shown in FIG. 2 , and is not limited here.

[0278] In a possible implementation, the first unit first determines a plurality of replacement characters based on a fourth preset rule and the second keyword; and then replaces the second keyword in the first response message with the plurality of replacement characters to obtain a plurality of second response messages.

[0279] For example, continuing with the above example of the first request message, the first response message, and the second keyword, the first unit determines that the replacement word for "eat less" includes "drink more." Also, the replacement word for "exercise more" includes "rest more." Thus, by inserting the replacement words into the first response message and replacing the corresponding second keywords, multiple second response messages obtained include: "drink more, exercise more," "drink more, rest more," and "drink less, rest more," etc.

[0280] In another possible implementation, the first unit sends the first response message and the second keyword to the third unit, and the third unit generates multiple second response messages based on the first response message and the second keyword; the first unit receives the multiple second response messages sent by the third unit. Of course, the first unit can also directly send the first response message to the third unit, and the third unit determines the second keyword of the first response message, obtains multiple second response messages based on the second keyword, and returns the multiple second response messages to the first unit.

[0281] Step 807: The first unit obtains multiple second request information based on the multiple second response information.

[0282] After obtaining the plurality of second response information, the first unit may perform reverse deduction based on the plurality of second response information to obtain the plurality of second request information.

[0283] The above-mentioned reverse inference process can be carried out by the user, the text generation network, preset rules, etc., and the specific details are not limited here. For example, take the example of the first unit obtaining the second request information corresponding to the second response information through the text generation network. The text generation network can be trained with training data as input and the value of the loss function being less than a threshold as the goal. The loss function is used to represent the difference between the output of the text generation network and the label of the training data.

[0284] In addition, in an embodiment of the present application, there are multiple ways for the first unit to obtain multiple second request information. It can be obtained through user operations, or through the fifth preset rule, or by sending multiple second response information to other devices (such as the third unit, etc.), and the other devices determine multiple second request information based on the multiple second response information and return it to the first unit, etc. The specific methods are not limited here.

[0285] For example, continuing the example of multiple second response messages, the first unit reversely infers the second response message "Drink more and exercise more" to obtain the second request message "What should I pay attention to when I have kidney stones?" The first unit reversely infers the second response message "Drink more and rest more" to obtain the second request message "How should I recuperate after surgery?" The first unit reversely infers the second response message "Drink less and rest more" to obtain the second request message "What should I do if I often drink coffee and can't sleep at night?"

[0286] Step 808: The first unit sends multiple second request information to the second unit.

[0287] After acquiring the plurality of second request information, the first unit sends the plurality of second request information to the second unit. Correspondingly, the second unit receives the plurality of second request information sent by the first unit.

[0288] In step 809 , the second unit obtains a plurality of second response information through the neural network.

[0289] After the second unit obtains a plurality of second request information, it obtains a plurality of second response information through the neural network.

[0290] For example, continuing with the example of multiple second request messages above, the second request message "What should I pay attention to when I have kidney stones?" corresponds to the second response message "Drink more water and exercise more." The second request message "How should I recuperate after surgery?" corresponds to the second response message "Take medicine as directed by the doctor and get enough rest." The second request message "What should I do if I often drink coffee and can't sleep at night?" corresponds to the second response message "Drink less coffee and get more rest."

[0291] In step 810 , the second unit sends a plurality of second response messages to the first unit.

[0292] After obtaining the plurality of second response messages, the second unit may send the plurality of second response messages to the first unit. Correspondingly, the first unit receives the plurality of second response messages sent by the second unit.

[0293] Step 811: The first unit presents response information.

[0294] For step 811 in this embodiment, reference may be made to the description of step 209 in the embodiment shown in FIG. 2 , and details thereof will not be repeated here.

[0295] In this embodiment, the real answer is first obtained from the real request information, and then the real answer is obfuscated to obtain multiple false answers. This allows the multiple false answers to be reversed to obtain multiple false request information. Generally, the second unit retrieves logs or other methods within a certain time period. As long as the time interval between the real request information and the false request information inferred by the second unit is less than the aforementioned time period, the first unit can obfuscate the real request information with multiple false request information, thereby enhancing user privacy protection.

[0296] Next, let's take the case where the request information is a question and the processing module implements the data processing function through LLM as an example (i.e., the request information is a question and the response information is the answer or reply corresponding to the question).

[0297] Please refer to FIG9 , which is another flowchart of the data processing method provided in an embodiment of the present application.

[0298] Step 1: First, the user inputs a question, and then the question is decomposed into a series of sub-questions. The large model processes the data of these sub-questions separately to obtain corresponding multiple sub-answers.

[0299] Step 2: For each of the sub-answers obtained, we can look for words of the same category (such as synonyms, antonyms, and numbers and other information can be replaced or randomly shuffled, etc.), and then randomly combine these sub-answers to obtain multiple false answers, and reversely infer multiple false answers to obtain multiple false questions.

[0300] Step 3, obfuscation and verification: confuse the LLM with multiple fake questions, initiate information retrieval to the LLM, and verify the degree of obfuscation.

[0301] The method provided in the embodiments of the present application is described.

[0302] Please refer to Figure 10, which is another flow chart of the data processing method provided in the embodiment of the present application. The method is applied to the encoding processing module, which can be a program that automatically processes natural language or other types, and the specific details are not limited here.

[0303] A question is obtained and entered into the LLM, which then generates an answer. The question is then fed into the encoding processing module, located on the user side. This module first identifies words in the question that may be related to user privacy (this can be automatically identified by the encoder or manually selected by the user). These words (also known as keywords) are then modified (including but not limited to replacing them with synonyms or similar words, randomly shuffling or changing information such as numbers), and a series of obfuscated questions is generated. For each generated question, the LLM is required to generate an answer. The false answers are mixed with the previously correct answers to confuse the model.

[0304] For example, the question is "What are the symptoms of stomach problems?", and the keywords include "stomach problems" and "symptoms." Several confounding questions are generated, including: "What are the symptoms of stomach problems?", "What are the symptoms of kidney problems?", "What are the symptoms of liver disease?", "What are the treatments for liver disease?", and "What are the treatments for stomach problems?" The final set of questions includes: "What are the treatments for liver disease?", which gives three incorrect answers, "What are the symptoms of stomach problems?", which gives one correct answer, and "What hospitals are recommended for kidney disease?", which gives two random answers.

[0305] Please refer to Figure 11, which is another flow chart of the data processing method provided in an embodiment of the present application. This method is applied to the encoding processing module and the decoding processing module; both can be programs that automatically process natural language or other types, and the specific details are not limited here.

[0306] The question is input into the encoding processing module, which is located on the user side. It will first identify the words in the question that may be related to user privacy (this can be automatically identified by the encoder or manually selected by the user), modify these words (including but not limited to replacing them with synonyms / similar words, randomly scrambling / changing information such as numbers, etc.), and generate a series of obfuscated questions.

[0307] For each generated question, the LLM is required to generate several answers and agree on a certain position in the prompt through commands, specifying the answer at that position as the correct answer and the rest as incorrect answers; the LLM performs reasoning and generates a series of answers.

[0308] The corresponding answer generated by the large model is input into the decoding processing module (which is also located on the user side). According to the above-mentioned agreed position, the correct answer to the real question is extracted and presented to the user.

[0309] For example, the question is "What are the symptoms of stomach problems?", and the keywords include "stomach problems" and "symptoms." Several confounding questions are generated, including: "What are the symptoms of stomach problems?", "What are the symptoms of kidney problems?", "What are the symptoms of liver disease?", "What are the treatments for liver disease?", and "What are the treatments for stomach problems?" The final set of questions includes: "What are the treatments for liver disease?", which gives three incorrect answers, "What are the symptoms of stomach problems?", which gives one correct answer, and "What hospitals are recommended for kidney disease?", which gives two random answers.

[0310] It can be seen that compared with the embodiment shown in FIG10 , this method adds a decoding processing module, but the correct question and answer will no longer appear first, which is conducive to further protection of privacy.

[0311] In the embodiments of this application, on the one hand, privacy protection is achieved by multiply obfuscating questions. For example, if a user asks a question in the interactive interface, multiple questions will be asked in privacy mode. There are no specific restrictions on the method of generating obfuscated questions to better protect privacy: random, table lookup, model generation, manual input, analogical reasoning, mathematical solution, and other methods can all generate obfuscated questions. On the other hand, an algorithmic process generates obfuscated questions through prompts. For example, if a user asks a question in the interactive interface, a set of prompts will be provided in privacy mode. There are no restrictions on the specific text format of the prompts, and any prompt that can generate a false question is acceptable.

[0312] The present invention hides real questions and answers among a large number of related but different questions and answers (i.e., false questions and false answers) in an obfuscating manner.

[0313] For untrusted LLM providers whose main purpose is to access private data, this method can circumvent the automated crawling scripts' crawling and screening of real questions and real answers, thus protecting privacy.

[0314] For untrusted LLM providers who use user Q&A data as model training data, a large number of conflicting questions and answers will reduce the accuracy of model training with opposite gradients, thereby preventing users' private data from appearing in other inferences after training and protecting user privacy.

[0315] The data processing method in the embodiment of the present application is described above, and the device in the embodiment of the present application is described below. Referring to FIG12 , an embodiment of the data processing device in the embodiment of the present application includes: a transceiver unit 1201 and a processing unit 1202 .

[0316] In one possible implementation, the data processing device shown in FIG12 is the first device in the embodiments shown in FIG1A to FIG11 , and the functions of each unit are as follows:

[0317] The transceiver unit 1201 is configured to send first request information input by a user to the second unit;

[0318] The transceiver unit 1201 is further configured to receive a first response message corresponding to the first request message sent by the second unit;

[0319] The transceiver unit 1201 is further configured to send a second request message to the second unit, where the second request message is used to obfuscate the first request message;

[0320] The transceiver unit 1201 is further configured to receive second response information corresponding to the second request information sent by the second unit.

[0321] Optionally, the first device further includes: a processing unit 1202, configured to obtain second request information based on the first request information.

[0322] Optionally, the processing unit 1202 is specifically configured to determine a first keyword in the first request information; the processing unit 1202 is specifically configured to obtain the second request information based on the first keyword and the first request information.

[0323] Optionally, the processing unit 1202 is specifically configured to determine a first replacement word corresponding to the first keyword; the processing unit 1202 is specifically configured to replace the first keyword in the first request information with the first replacement word to obtain the second request information.

[0324] Optionally, the processing unit 1202 is specifically configured to send the first keyword and the first request information to the third unit; the processing unit 1202 is specifically configured to receive the second request information sent by the third unit.

[0325] Optionally, the processing unit 1202 is specifically configured to determine a first keyword based on a first operation of the user or a first preset rule.

[0326] Optionally, the processing unit 1202 is specifically configured to send first request information to the third unit; the processing unit 1202 is specifically configured to receive second request information sent by the third unit.

[0327] Optionally, the first device further includes: a processing unit 1202, configured to generate second request information based on the first response information.

[0328] Optionally, the processing unit 1202 is specifically configured to obtain third response information based on the first response information; the processing unit 1202 is specifically configured to obtain second request information based on the third response information.

[0329] Optionally, processing unit 1202 is specifically used to determine the second keyword in the first response information; processing unit 1202 is specifically used to determine the second replacement word corresponding to the second keyword; processing unit 1202 is specifically used to replace the second keyword in the first response information with the second replacement word to obtain a third response information.

[0330] Optionally, the first device further includes: a presenting unit 1203, configured to present multiple response information or first response information to the user, where the multiple response information includes the first response information and the second response information.

[0331] Optionally, the transceiver unit 1201 is further used to receive the first request information sent by the third unit; the transceiver unit 1201 is further used to send multiple response information or first response information to the third unit, and the multiple response information includes the first response information and the second response information.

[0332] Optionally, the first device mentioned above is a question answering device.

[0333] Optionally, the first request information includes at least one of the following: a question, a text processing request, or a translation request.

[0334] In this embodiment, the operations performed by each unit in the data processing device are similar to the description of the first unit in the embodiments shown in Figures 1A to 11 above, and will not be repeated here.

[0335] In this embodiment, false request information is obtained through a trusted unit or device (first unit or third unit), and the processing unit 1202 uses the false request information to confuse the real request information, so that the untrusted unit cannot clearly identify the real request information, thereby improving user privacy protection.

[0336] In another possible implementation, the data processing device shown in FIG12 is the third device in the embodiments shown in FIG1A to FIG11 , and the functions of each unit are as follows:

[0337] The transceiver unit 1201 is configured to receive a first request message sent by the first unit or a first response message corresponding to the first request message;

[0338] The transceiver unit 1201 is further configured to send a second request message to the first unit based on the first request message or the first response message, where the second request message is used to obfuscate the first request message.

[0339] Optionally, the third device is deployed on a network server, and the first unit is deployed on a terminal device.

[0340] Optionally, the transceiver unit 1201 is specifically configured to obtain the second request information based on the first request information or the first response information; the transceiver unit 1201 is specifically configured to send the second request information to the first unit.

[0341] In this embodiment, the operations performed by each unit in the data processing device are similar to the description of the third unit in the embodiments shown in Figures 1A to 11 above, and will not be repeated here.

[0342] In this embodiment, the transceiver unit 1201 in the trusted unit or device (third device) sends the second request information to the first unit based on the first request information or the first response information, so that the first unit can use the false request information to confuse the real request information, thereby improving the user's privacy protection.

[0343] In another possible implementation, the data processing device shown in FIG12 is the third device in the embodiments shown in FIG1A to FIG11 , and the functions of each unit are as follows:

[0344] The transceiver unit 1201 is configured to receive the second response information sent by the first unit;

[0345] The processing unit 1202 is configured to obtain second request information based on the second response information;

[0346] The transceiver unit 1201 is further configured to send a second request message to the first unit, where the second request message is used by the second unit to obtain second response message corresponding to the second request message.

[0347] In this embodiment, the operations performed by each unit in the data processing device are similar to the description of the third unit in the embodiments shown in Figures 1A to 11 above, and will not be repeated here.

[0348] In this embodiment, the transceiver unit 1201 reversely infers the false request information through the false response information. Since, in general, the second device retrieves the log or other methods within a certain time period, as long as the time interval between the second device infers the real request information and the false request information is less than the above time period. In terms of the log, the transceiver unit 1201 can use the false request information to confuse the neural network in the untrusted unit (i.e., the second device), thereby improving the user's privacy protection.

[0349] Please refer to Figure 13. This embodiment of the present application provides another data processing device. This data processing device can be the first device in the embodiments shown in Figures 1A to 11. For ease of explanation, only the parts related to the embodiment of the present application are shown. For specific technical details not disclosed, please refer to the method section of the embodiment of the present application. Take the first device as a mobile phone as an example:

[0350] FIG13 is a block diagram illustrating a partial structure of a mobile phone related to the first device provided in an embodiment of the present application. Referring to FIG13 , the mobile phone includes components such as a radio frequency (RF) circuit 1310, a memory 1320, an input unit 1330, a display unit 1340, a sensor 1350, an audio circuit 1360, a wireless fidelity (WiFi) module 1370, a processor 1380, and a power supply 1390. Those skilled in the art will appreciate that the mobile phone structure shown in FIG13 does not limit the mobile phone and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0351] The following is a detailed introduction to the various components of the mobile phone in conjunction with Figure 13:

[0352] The RF circuit 1310 can be used to receive and send signals during information transmission or calls. In particular, after receiving downlink information from the base station, it is sent to the processor 1380 for processing. In addition, the designed uplink data is sent to the base station. Generally, the RF circuit 1310 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (LNA), a duplexer, etc. In addition, the RF circuit 1310 can also communicate with the network and other devices through wireless communication. The above-mentioned wireless communication can use any communication standard or protocol, including but not limited to the global system of mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), long term evolution (LTE), email, short messaging service (SMS), etc.

[0353] The memory 1320 can be used to store software programs and modules. The processor 1380 executes the various functional applications and data processing of the mobile phone by running the software programs and modules stored in the memory 1320. The memory 1320 may mainly include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area may store data created based on the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory 1320 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0354] The input unit 1330 can be used to receive input digital or character information, and to generate key signal input related to the user settings and function control of the mobile phone. Specifically, the input unit 1330 may include a touch panel 1331 and other input devices 1332. The touch panel 1331, also known as a touch screen, can collect user touch operations on or near it (such as operations performed by the user using a finger, stylus, or any other suitable object or accessory on or near the touch panel 1331) and drive the corresponding connection device according to a pre-set program. Optionally, the touch panel 1331 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch direction and detects the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device and converts it into touch point coordinates, which are then sent to the processor 1380. It can also receive commands sent by the processor 1380 and execute them. In addition, the touch panel 1331 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 1331, the input unit 1330 may further include other input devices 1332. Specifically, the other input devices 1332 may include but are not limited to one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a mouse, and an operating stick.

[0355] The display unit 1340 can be used to display information input by the user or information provided to the user and various menus of the mobile phone. The display unit 1340 may include a display panel 1341. Optionally, the display panel 1341 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc. Further, the touch panel 1331 may cover the display panel 1341. When the touch panel 1331 detects a touch operation on or near it, it is transmitted to the processor 1380 to determine the type of touch event. Subsequently, the processor 1380 provides a corresponding visual output on the display panel 1341 according to the type of touch event. Although in Figure 13, the touch panel 1331 and the display panel 1341 are used as two independent components to implement the input and output functions of the mobile phone, in some embodiments, the touch panel 1331 and the display panel 1341 can be integrated to implement the input and output functions of the mobile phone.

[0356] The mobile phone may also include at least one sensor 1350, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 1341 according to the brightness of the ambient light, and the proximity sensor may turn off the display panel 1341 and / or the backlight when the mobile phone is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in all directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors that the mobile phone can also be configured with, such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., they will not be described here.

[0357] The audio circuit 1360, the speaker 1361, and the microphone 1362 can provide an audio interface between the user and the mobile phone. The audio circuit 1360 can transmit the electrical signal converted from the received audio data to the speaker 1361, which is converted into a sound signal for output; on the other hand, the microphone 1362 converts the collected sound signal into an electrical signal, which is received by the audio circuit 1360 and converted into audio data. The audio data is then output to the processor 1380 for processing, and then sent to, for example, another mobile phone through the RF circuit 1310, or the audio data is output to the memory 1320 for further processing. In the embodiment of the present application, the audio circuit 1360, the speaker 1361, and the microphone 1362 can cooperate to present response information to the user, for example, by presenting the response information to the user through voice broadcast.

[0358] WiFi is a short-range wireless transmission technology. A mobile phone can help users send and receive emails, browse the web, and access streaming media through the WiFi module 1370, providing users with wireless broadband Internet access. Although FIG13 shows the WiFi module 1370, it is understood that it is not a required component of a mobile phone.

[0359] Processor 1380 is the control center of the phone, connecting all parts of the phone using various interfaces and circuits. By running or executing software programs and / or modules stored in memory 1320 and accessing data stored in memory 1320, it executes various phone functions and processes data, thereby providing overall monitoring of the phone. Optionally, processor 1380 may include one or more processing units; preferably, processor 1380 may integrate an application processor and a modem processor. The application processor primarily handles the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 1380.

[0360] The mobile phone also includes a power supply 1390 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 1380 through a power management system, thereby managing charging, discharging, and power consumption through the power management system.

[0361] Although not shown, the mobile phone may also include a camera, a Bluetooth module, etc., which will not be described in detail here.

[0362] In the embodiment of the present application, the above-mentioned processor 1380 can perform the function of the first unit in the embodiment shown in Figures 1A to 11 above, which will not be repeated here.

[0363] Please refer to Figure 14, which is a schematic diagram of the structure of another data processing device provided by the present application. The data processing device may be the second device or the third device in the embodiments shown in Figures 1A to 11 above.

[0364] The data processing device may include a processor 1401, a memory 1402, and a communication port 1403. The processor 1401, the memory 1402, and the communication port 1403 are interconnected via a line. The memory 1402 stores program instructions and data.

[0365] The memory 1402 stores program instructions and data corresponding to the steps executed by the data processing device in the corresponding implementation modes shown in FIG. 1A to FIG. 11 .

[0366] The processor 1401 is configured to execute the steps performed by the data processing device in any of the embodiments shown in FIG. 1A to FIG. 11 .

[0367] The communication port 1403 can be used to receive and send data, and to execute the steps related to acquisition, sending, and receiving in any of the embodiments shown in FIG. 1A to FIG. 11 .

[0368] In one implementation, the data processing device may include more or fewer components than those in FIG. 14 . This application is merely an illustrative description and does not limit this.

[0369] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0370] Those skilled in the art will clearly understand that, for the sake of convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0371] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the division of the units is merely a logical functional division, and in actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, or can be an electrical, mechanical or other form of connection.

[0372] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0373] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0374] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or partly contributed to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk, or an optical disk.

[0375] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A data processing method, the method being applied to a first unit, the method comprising: Sending first request information input by the user to the second unit; receiving first response information corresponding to the first request information sent by the second unit; Characterized in that the method further comprises: Sending second request information to the second unit, where the second request information is used to obfuscate the first request information; Receive second response information corresponding to the second request information sent by the second unit.

2. The method according to claim 1, characterized in that The method further comprises: The second request information is acquired based on the first request information.

3. The method according to claim 2, characterized in that The acquiring the second request information based on the first request information includes: Determining a first keyword in the first request information; The second request information is acquired based on the first keyword and the first request information.

4. The method according to claim 3, characterized in that: The acquiring the second request information based on the first keyword and the first request information includes: Determine a first replacement word corresponding to the first keyword; The first keyword in the first request information is replaced by the first replacement word to obtain the second request information.

5. The method according to claim 3, characterized in that: The acquiring the second request information based on the first keyword and the first request information includes: sending the first keyword and the first request information to a third unit; The second request information sent by the third unit is received.

6. The method according to any one of claims 3 to 5, characterized in that The determining the first keyword in the first request information includes: The first keyword is determined based on a first operation of the user or a first preset rule.

7. The method according to claim 2, characterized in that: The acquiring the second request information based on the first request information includes: Sending the first request information to the third unit; The second request information sent by the third unit is received.

8. The method according to claim 1, characterized in that The method further comprises: The second request information is generated based on the first response information.

9. The method according to claim 8, characterized in that The generating the second request information based on the first response information includes: Acquire third response information based on the first response information; The second request information is obtained based on the third response information.

10. The method according to claim 9, characterized in that The acquiring the third response information based on the first response information includes: determining a second keyword in the first response information; Determine a second replacement word corresponding to the second keyword; The second keyword in the first response information is replaced by the second replacement word to obtain the third response information.

11. The method according to any one of claims 1 to 10, characterized in that The method further comprises: A plurality of response messages or the first response message is presented to the user, wherein the plurality of response messages include the first response message and the second response message.

12. The method according to any one of claims 1-4, 8-10, characterized in that: The method further comprises: receiving the first request information sent by the third unit; Sending a plurality of response messages or the first response message to the third unit, wherein the plurality of response messages includes the first response message With the second response information.

13. The method according to any one of claims 1 to 12, characterized in that The first unit is a question answering device.

14. The method according to any one of claims 1 to 13, characterized in that The first request information includes at least one of the following: a question, a text processing request, and a translation request.

15. A data processing method, characterized in that: The method is applied to the third unit, and the method comprises: Receiving a first request message sent by a first unit or a first response message corresponding to the first request message; Sending second request information to the first unit based on the first request information or the first response information, where the second request information is used to obfuscate the first request information.

16. The method according to claim 15, characterized in that The third unit is deployed on a network server, and the first unit is deployed on a terminal device.

17. A data processing method, the method comprising: The first unit sends first request information input by a user to the second unit; The second unit sends first response information corresponding to the first request information to the first unit; The second unit receives second request information sent by the first unit, where the second request information is used to obfuscate the first request information; The first unit receives second response information corresponding to the second request information sent by the second unit.

18. The method according to claim 17, characterized in that The method further comprises: The first unit obtains the second request information based on the first request information or the first response information.

19. The method according to claim 18, characterized in that The method further comprises: The first unit obtains the second request information based on the first response information.

20. A first device, characterized in that: The first device comprises: The transceiver unit is used to send the first request information input by the user to the second unit; The transceiver unit is further configured to receive first response information corresponding to the first request information sent by the second unit; The transceiver unit is further used to send second request information to the second unit, where the second request information is used to obfuscate the first request information; The transceiver unit is further configured to receive second response information corresponding to the second request information sent by the second unit.

21. A third device, characterized in that: The third device comprises: A transceiver unit, configured to receive a first request message sent by the first unit or a first response message corresponding to the first request message; The transceiver unit is further used to send second request information to the first unit based on the first request information or the first response information, where the second request information is used to confuse the first request information.

22. A first device, characterized in that: include: A processor, the processor is coupled to a memory, the memory is used to store programs or instructions, when the program or instructions are executed by the processor, the first device executes the method according to any one of claims 1 to 14.

23. A third device, characterized in that: include: A processor, wherein the processor is coupled to a memory, wherein the memory is used to store a program or an instruction, and when the program or the instruction is executed by the processor, the third device executes the method according to claim 15 or 16.

24. A communication system, characterized in that: The communication system includes: a first device and / or a third device; The first device is used to execute the method according to any one of claims 1 to 14, and the third device is used to execute the method according to claim 15 or 16.

25. A communication system, characterized in that: The communication system comprises: a first unit and a second unit; The first unit is used to send first request information input by a user to the second unit; The second unit is used to send first response information corresponding to the first request information to the first unit; The second unit is further used to receive second request information sent by the first unit, where the second request information is used to obfuscate the first request information; The first unit is further configured to receive second response information corresponding to the second request information sent by the second unit.

26. A computer-readable storage medium, characterized in that: The medium stores instructions, and when the instructions are executed by a computer, the method according to any one of claims 1 to 19 is implemented.

27. A computer program product, characterized in that The method comprises instructions which, when executed on a computer, cause the computer to execute the method according to any one of claims 1 to 19.

Images