Information processing method and device

Abstract

The invention discloses an information processing method and device, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring sharing information of a user; identifying private data in the shared information, wherein the private data in the shared information is data associated with a user identity; based on the context information and the source of the sharing information, determining the theme of the sharing information; determining a processing strategy for processing the private data in the shared information according to the correlation between the theme of the shared information and the private data in the shared information; and processing private data in the shared information based on the processing strategy to obtain target shared information.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and specifically relates to an information processing method and device. Background Art

[0002] With the prevalence of electronic devices and social media, users are generating and sharing more and more content in their daily lives and work, and this content also involves an increasing amount of user private data. For example, when users upload pictures and videos on social media, they may inadvertently disclose sensitive information such as personal addresses and phone numbers. Once this sensitive information is obtained by others, it can lead to the leakage of user private data and cause significant inconvenience to users. Summary of the Invention

[0003] The purpose of the embodiments of the present application is to provide an information processing method and device that can identify whether the content to be shared by a user contains private data, and if the content to be shared by the user contains private data, can process the private data accordingly to ensure the security of the user's private data.

[0004] In a first aspect, an embodiment of the present application provides an information processing method, the method comprising:

[0005] Receive sharing information uploaded by users;

[0006] Identifying private data in the shared information, where the private data in the shared information is data associated with the user's identity;

[0007] Determining a subject of the shared information based on context information and a source of the shared information;

[0008] determining, based on the correlation between the subject of the shared information and the private data in the shared information, a processing strategy for processing the private data in the shared information;

[0009] The private data in the shared information is processed based on the processing strategy to obtain target shared information.

[0010] In a second aspect, an embodiment of the present application provides an information processing device, the device comprising:

[0011] The first acquisition module is used to receive sharing information uploaded by users;

[0012] A first identification module is used to identify private data in the shared information, where the private data in the shared information is data associated with the user identity;

[0013] A first determining module, configured to determine a subject of the shared information based on context information and a source of the shared information;

[0014] a second determining module, configured to determine a processing strategy for processing the private data in the shared information based on the correlation between the subject of the shared information and the private data in the shared information;

[0015] The third determining module is configured to process the private data in the shared information based on the processing strategy to obtain target shared information.

[0016] In a third aspect, an embodiment of the present application provides an electronic device comprising a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the method described in the first aspect are implemented.

[0017] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0018] In a fifth aspect, an embodiment of the present application provides a chip, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the method described in the first aspect.

[0019] In a sixth aspect, an embodiment of the present application provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the method described in the first aspect.

[0020] In an embodiment of the present application, when the user's shared information is obtained, the private data in the shared information can be identified, and the subject of the shared information can be identified based on the context information and source of the shared information. In this way, through the solution of the embodiment of the present application, it is possible to identify whether the shared information to be shared by the user contains private data, and when the shared information contains private data, it is possible to determine the processing strategy for processing the private data in the shared information based on the correlation between the subject of the shared information and the private data in the shared information, and then the private data in the shared information can be processed based on the processing strategy to obtain the target shared information. In this way, the obtained target shared information has already processed the private data in the shared information, ensuring the security of the user's private data. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a flowchart of an information processing method provided by some embodiments of the present application;

[0022] Figure 2 This is one of the prompt information display schematic diagrams provided in some embodiments of the present application;

[0023] Figure 3 This is the second schematic diagram of prompt information display provided by some embodiments of the present application;

[0024] Figure 4 This is the third schematic diagram of prompt information display provided by some embodiments of the present application;

[0025] Figure 5 This is the fourth schematic diagram of prompt information display provided by some embodiments of the present application;

[0026] Figure 6 is a schematic structural diagram of an information processing device shown in some embodiments of the present application;

[0027] Figure 7 is a schematic structural diagram of an electronic device shown in some embodiments of the present application;

[0028] Figure 8 It is a schematic diagram of the hardware structure of an electronic device shown in some embodiments of the present application. DETAILED DESCRIPTION

[0029] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0030] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of a class, and do not limit the number of objects; for example, the first object can be one or N. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0031] The following explains the terms involved in the embodiments of the present invention.

[0032] Multimodal information: information in multiple modes, including but not limited to images, text, video, audio, and other modalities.

[0033] Artificial Intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.

[0034] Large Language Model (LLM), also known as large model, is an advanced artificial intelligence algorithm trained on large amounts of data.

[0035] Semantic relatedness is a quantitative measure of the degree to which two things, such as two pieces of text (words, phrases, or sentences), are closely related in terms of meaning. Specifically, it measures whether the content of the two things is related in terms of logic, context, or knowledge system.

[0036] Interface: refers to the graphical interaction layer that users see through the screen of an electronic device. Also known as the "user interface (UI)", it is the medium interface for interaction and information exchange between applications or operating systems and users. It realizes the conversion between the internal form of information and the form acceptable to users. The user interface is source code written in a specific computer language such as Java and XML. The interface source code is parsed and rendered on the electronic device and finally presented as content that the user can recognize. The commonly used form of user interface is the graphical user interface (GUI), which refers to a user interface related to computer operations that is displayed in a graphical way. It can be visual interface elements such as text, icons, buttons, menus, tabs, text boxes, dialog boxes, status bars, navigation bars, widgets (Web widgets, Widgets) displayed on the display screen of an electronic device.

[0037] Controls are graphical elements that users can directly manipulate or perceive during interaction. They are used to receive user input, trigger functions, or display real-time information. They serve as a bridge between users and device or application functions, delivering instructions and providing status feedback through visual means.

[0038] The technical solution of the embodiment of the present application can be applied to scenarios where, under the existing authority management mechanism, the information shared by users may also contain the user's private data, and the user wants to determine whether the information shared by the user contains private data under the existing authority management mechanism, and to process the private data when the shared information contains private data. For example, a user wants to share a hat that he bought on social media and has signed the privacy protection agreement of the social media platform, so he uploads the order information of the hat he bought on the social media, and the order information also includes the user's address and telephone number. For another example, a user wants to consult about his own illness on a public platform, specifically what he should pay attention to in his diet, life, etc. in his daily life, and what medicines he needs to prepare on a daily basis, so he uploads his medical record information on the public platform, and the medical record information records that the user suffers from asthma.

[0039] It should be noted that, generally speaking, when users upload information on social media, they must sign a corresponding privacy agreement, that is, the social media platform has already provided some reasonable protection for user privacy. The solution of the embodiment of this application is applied to how to further reasonably protect the privacy data in the shared information uploaded by users under the existing permission management mechanism.

[0040] The information processing method provided in the embodiments of the present application is described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0041] Figure 1 This is a flow chart of an information processing method provided in an embodiment of the present application. The execution subject of the information processing method can be an electronic device, which can be but is not limited to a personal computer (PC), a smart phone, a tablet computer or a personal digital assistant (PDA).

[0042] like Figure 1 As shown, the information processing method provided in the embodiment of the present application may include steps 110 to 150.

[0043] Step 110: Obtain the user's sharing information.

[0044] The shared information may be information uploaded by the user to be shared. For example, in the above example, the order information of the hat uploaded by the user and the medical record information uploaded by the user are the shared information.

[0045] Step 120: Identify private data in the shared information.

[0046] The private data may be data associated with the user's identity. For example, in the above example, the user's address, phone number, and the fact that the user suffers from asthma are private data of the user.

[0047] In some embodiments of the present application, after obtaining the shared information of the user, the shared information can be identified to obtain the private data in the shared information.

[0048] Step 130: Determine the subject of the shared information based on the context information and source of the shared information.

[0049] Among them, the context information of the shared information can be some information sent before and / or after the user uploads the shared information. For example, in the above example, after uploading the order information of the hat he purchased, the user also sent other information on social media, such as "This hat is made of ice silk, very cool, and very suitable for wearing in summer." Then the information "This hat is made of ice silk, very cool, and very suitable for wearing in summer" belongs to the context information of the shared information "hat order information." For another example, in the above example, after uploading his medical record information, the user also sent the information "What should I pay attention to in diet, life, etc. in daily life, and what medicines do I need to prepare on a daily basis." Then the context information of the shared information "medical record information" is "What should I pay attention to in diet, life, etc. in daily life, and what medicines do I need to prepare on a daily basis."

[0050] The source of the shared information can be the source of the shared information. For example, in the above example, the user uploaded the order information of the hat he bought, and the order information came from the shopping application. For example, the user uploaded his medical record information, and the medical record information came from the medical record provided by the hospital.

[0051] The subject of shared information can be used to represent the specific content the user wants to share. For example, in the example above, the user uploaded order information for a hat, and the content the user wants to share is the hat they purchased, so the subject of the shared information is "Sharing Good Things." Another example is the user uploaded their medical history information, and the user wants to seek medical advice, specifically what to pay attention to in their daily diet and lifestyle, as well as what medicines they need to have on hand, so the subject of the shared information is "Medical Consultation."

[0052] In some embodiments of the present application, the subject of the shared information may be determined based on the context information and source of the shared information.

[0053] For example, in the above example, the user uploaded the order information of a hat that he or she purchased. Based on the contextual information of the order information, "This hat is made of ice silk, which is very cool and suitable for wearing in summer," and the source of the order information, it can be known that the subject of the order information uploaded by the user is to share the hat purchased from a shopping application.

[0054] For example, in the above example, the user uploaded his or her medical record information. According to the context information of the medical record information "What to pay attention to in diet, life, etc. in daily life, and what medicines need to be prepared daily" and the source of the medical record information, it can be known that the user uploaded the medical record information to consult about his or her own illness. Specifically, he or she wants to ask about his or her current illness, what he or she should pay attention to in daily life, and what medicines need to be prepared daily in case of emergency.

[0055] In an embodiment of the present application, the user's intention to share information can be known based on the context information and source of the shared information, so that the subject of the shared information can be determined, thereby improving the accuracy of determining the subject of the shared information.

[0056] Step 140: Determine a processing strategy for processing the private data in the shared information based on the correlation between the subject of the shared information and the private data in the shared information.

[0057] The processing strategy may be a strategy for processing private data in shared information.

[0058] In some embodiments of the present application, the correlation between the subject of the shared information and the private data in the shared information can be used to characterize the degree of correlation between the subject of the shared information and the private data in the shared information. Specifically, the correlation between the subject of the shared information and the private data in the shared information can be determined by an algorithm that calculates the degree of correlation between the subject of the shared information and the private data in the shared information. For example, the correlation between the subject of the shared information and the private data in the shared information can be determined by calculating the cosine similarity between the subject of the shared information and the private data in the shared information. Alternatively, the correlation between the subject of the shared information and the private data in the shared information can be determined by calculating the Euclidean distance between the subject of the shared information and the private data in the shared information. The specific method for determining the correlation between the subject of the shared information and the private data in the shared information can be selected according to user needs and is not limited in the embodiments of the present application.

[0059] In some embodiments of the present application, a processing strategy for handling the private data in the shared information may be determined based on the correlation between the subject of the shared information and the private data in the shared information. Specifically, different processing strategies may be used to handle the private data in the shared information based on the different correlations between the subject of the shared information and the private data in the shared information.

[0060] In some embodiments of the present application, in order to protect the user's private data and improve the flexibility of processing private data in shared information, step 130 may specifically include:

[0061] When the correlation between the subject of the shared information and the private data in the shared information is less than a first threshold, determining that a processing strategy for processing the private data in the shared information is to delete the private data from the shared information;

[0062] When the correlation between the subject of the shared information and the private data in the shared information is greater than or equal to a first threshold, a processing strategy for processing the private data in the shared information is determined according to the semantic correlation between the shared information and the private data in the shared information.

[0063] Among them, the first threshold can be a pre-set threshold of the similarity between the subject of the shared information and the private data in the shared information. The first threshold can be, for example, 50%-70%, for example, it can be 60%. The specific value of the first threshold can be selected according to user needs and is not limited in the embodiments of this application.

[0064] The semantic relevance between shared information and the private data within it can be measured by the degree of association between the shared information and the private data within it. Specifically, it can be measured by whether the private data within the shared information is the core content of the shared information. For example, in the example above, the user's address and phone number are not the core content of the order information. The core content of the order information is the hat the user wants to share. In this case, the semantic relevance between the shared information "order information" and the private data "user's address and phone number" is low. For another example, in the example above, the user's specific illness is the core content of the medical history information. In this case, the semantic relevance between the shared information "medical history information" and the private data "user's specific illness asthma" is high.

[0065] In some embodiments of the present application, the correlation between the subject of the shared information and the private data in the shared information can be first determined. If the correlation between the subject of the shared information and the private data in the shared information is less than a first threshold, it can be determined that the private data in the shared information has little correlation with the subject of the content that the user wants to share, and the processing strategy can be determined to be to delete the private data in the shared information from the shared information.

[0066] Continuing with the above example, let's take the first threshold as 60%, the subject of the order information shared by the user is "Sharing the purchased hat", and the correlation between the user's address and phone number in the order information and the subject "Sharing the purchased hat" is 30%. If the 30% is less than 60%, then the processing strategy can be determined to be to delete the user's address and phone number in the order information.

[0067] In some embodiments of the present application, when the correlation between the subject of the shared information and the private data in the shared information is greater than or equal to a first threshold, a processing strategy for processing the private data in the shared information can be determined based on the semantic correlation between the shared information and the private data in the shared information.

[0068] Continuing to refer to another example above, taking the first threshold as 60%, the theme of the medical record information shared by the user is "medical consultation", and the correlation between the user's disease in the medical record information and the theme "medical consultation" is 80%. If 80% is greater than 60%, the semantic correlation between the shared information and the private data can be further calculated, and then the processing strategy for the private data in the shared information can be determined based on the semantic correlation between the shared information and the private data in the shared information.

[0069] In an embodiment of the present application, if the correlation between the subject of the shared information and the private data in the shared information is less than a first threshold, the private data can be deleted from the shared information, thereby protecting the user's private data without affecting the user's shared content. If the correlation between the subject of the shared information and the private data in the shared information is greater than or equal to the first threshold, a processing strategy for handling the private data in the shared information can be further determined based on the semantic correlation between the shared information and the private data in the shared information. In this way, different processing strategies for handling the private data in the shared information can be determined based on different semantic correlations between the shared information and the private data in the shared information, thereby increasing the flexibility of handling the private data in the shared information.

[0070] In some embodiments of the present application, in order to enhance the user's experience in sharing content, the processing strategy for processing the private data in the shared information based on the semantic relevance between the shared information and the private data in the shared information may specifically include:

[0071] When the semantic relevance between the shared information and the private data in the shared information is greater than a second threshold, determining that the processing strategy for processing the private data in the shared information is to retain the private data in the shared information;

[0072] When the semantic relevance between the shared information and the private data in the shared information is less than or equal to the second threshold, the processing strategy for processing the private data in the shared information is determined to be to blur the private data in the shared information.

[0073] Among them, the second threshold can be a pre-set threshold of the semantic relevance between the shared information and the private data in the shared information. The value of the second threshold can be 70%-90%. For example, the second threshold can be 80%. The specific value of the second threshold can be selected according to user needs and is not limited in the embodiments of this application.

[0074] Obfuscating private data in shared information may involve obfuscating the private data in the shared information. Specifically, the private data in the shared information may be replaced with semantically equivalent obfuscated data. For example, in the above example, if the user does not want to expose his or her true illness, the disease name "asthma" in the medical record information may be replaced with the specific symptoms of asthma.

[0075] In some embodiments of the present application, when the semantic relevance between the shared information and the private data in the shared information is greater than a second threshold, it indicates that the private data in the shared information is important to the shared information, and the processing strategy for the private data in the shared information can be determined to be to retain the private data in the shared information.

[0076] Continuing to refer to the second example above, with the second threshold being 80%, and the semantic correlation between the user's specific disease "asthma" and the user's "medical record information" being 85%, it can be determined that the user's specific disease is very important for the user's medical consultation, and the processing strategy for the user's specific disease "asthma" can be determined to be to retain the information.

[0077] In some embodiments of the present application, when the semantic relevance between the shared information and the private data in the shared information is less than or equal to a second threshold, it indicates that the private data in the shared information is also important to the shared information, but the private data may not be specifically limited. In this way, the processing strategy for the private data in the shared information is determined to be to blur the private data in the shared information.

[0078] Continuing to refer to the second example above, with the second threshold being 80%, and the semantic correlation between the user's specific disease "asthma" and the user's "medical record information" being 75%, it can be determined that the user's specific disease is very important for the user's medical consultation, but the user may not specifically limit the specific disease, then the processing strategy for "asthma" is determined to be to fuzzy "asthma", for example, "asthma" can be fuzzy processed into the specific symptoms of asthma.

[0079] In an embodiment of the present application, when the semantic relevance between the shared information and the private data in the shared information is greater than a second threshold, the processing strategy for the private data in the shared information is determined to be to retain the private data in the shared information. This ensures that others can understand the user's shared information well so that they can provide accurate feedback to the user, such as providing accurate medical consultation advice. When the semantic relevance between the shared information and the private data in the shared information is less than or equal to the second threshold, the processing strategy for the private data in the shared information is determined to be to replace the private data in the shared information with semantically equivalent fuzzified data. This ensures the security of the user's private data while facilitating others to provide accurate feedback to the user based on the replaced semantically equivalent fuzzified data, thereby improving the user's sharing experience of sharing content.

[0080] Step 150: Process the private data in the shared information based on the processing strategy to obtain target shared information.

[0081] The target shared information may be shared information obtained by processing the private data in the shared information based on the processing strategy.

[0082] In some embodiments of the present application, in order to meet the user's personalized needs for processing private data in shared information, before step 150, the above method may further include:

[0083] Display prompt information;

[0084] Step 150 may specifically include:

[0085] In response to a first input of the user for at least one processing strategy candidate, the private data in the shared information is processed according to the processing strategy corresponding to the processing strategy candidate selected by the first input to obtain target shared information.

[0086] Among them, the prompt information can be a processing strategy for prompting the user to process the private data in the shared information, that is, the prompt information can include at least one processing strategy candidate, for example, at least one processing strategy candidate can include: deleting the private data in the shared information, retaining the private data, and blurring the private data.

[0087] It should be noted that the prompt information can be displayed in the form of a pop-up window. In addition, a prompt light, prompt sound, etc. can also be added. The specific display form of the prompt information is not limited in the embodiment of this application.

[0088] The first input may be a user input of at least one processing strategy candidate. The first input is used to process the private data in the shared information according to the processing strategy corresponding to the processing strategy candidate selected by the first input to obtain the target shared information. The first input may be a first operation. For example, the first input includes but is not limited to: a user touch input of at least one processing strategy candidate using a touch device such as a finger or a stylus, or a voice command input by the user, or a specific gesture input by the user, or other feasible input, which can be determined according to actual usage needs and is not limited in the embodiment of the present invention. The specific gesture in the embodiment of the present application may be any one of a single-click gesture, a sliding gesture, a drag gesture, a pressure recognition gesture, a long-press gesture, an area change gesture, a double-press gesture, and a double-click gesture; the click input in the embodiment of the present application may be a single-click input, a double-click input, or any number of click inputs, etc., and may also be a long-press input or a short-press input. For example, the first input may be a user touch input of at least one processing strategy candidate. For example, the first input may be a user click input of at least one processing strategy candidate.

[0089] In some embodiments of the present application, after obtaining a processing strategy for processing private data in shared information, a prompt message containing at least one processing strategy candidate item may be displayed. Then, in response to a user's first input of at least one processing strategy candidate item, the private data in the shared information may be processed according to the processing strategy corresponding to the processing strategy candidate item selected by the user to obtain the target shared information.

[0090] It should be noted that the prompt information may also include the correlation between the subject of the shared information and the private data in the shared information, as well as the semantic correlation between the shared information and the private data in the shared information. This allows users to intuitively understand the correlation between the subject of the shared information and the private data in the shared information, as well as the semantic correlation between the shared information and the private data in the shared information.

[0091] Continuing with the first example above, taking the pop-up window as an example, if the subject of the order information shared by the user is "sharing the purchased hat", and the correlation between the user's address and phone number in the order information and the subject "sharing the purchased hat" is less than the first threshold, then a pop-up window may be displayed. Figure 2The pop-up interface 20 shown includes information 21 "The order information you shared contains private data such as address and phone number, and the private data has little relevance to the topic you shared. Please select the corresponding processing strategy", as well as processing strategy candidates: "Delete private data" candidate control 22, "Retain private data" candidate control 23 and "Blur private data" candidate control 24. If the user clicks the "Delete private data" candidate control 22, the address and phone number can be deleted from the order information.

[0092] Continuing with the second example above, taking the pop-up window as an example, the theme of the medical record information shared by the user is "condition consultation", the correlation between the user's disease in the medical record information and the theme "condition consultation" is greater than the first threshold, and the semantic correlation between the user's specific disease "asthma" and the user's "medical record information" is greater than the second threshold, then the following pop-up window may be displayed: Figure 3 The pop-up interface 30 shown includes information 31 "The medical record information you shared contains a specific disease name, and the disease name is the core content of the medical record information. Please select the corresponding processing strategy", as well as processing strategy candidates: "Delete private data" candidate control 32, "Retain private data" candidate control 33 and "Blur private data" candidate control 34. If the user wants to retain his or her disease name in the medical record information so that he or she can get more accurate consulting advice, the user clicks the "Retain private data" candidate control 33, and the specific disease name in the medical record information can be retained.

[0093] Continuing with the second example above, taking the pop-up window as an example, the theme of the medical record information shared by the user is "condition consultation", the correlation between the user's disease in the medical record information and the theme "condition consultation" is greater than the first threshold, and the semantic correlation between the user's specific disease "asthma" and the user's "medical record information" is less than the second threshold, then the following pop-up window may be displayed: Figure 3 The pop-up interface 30 shown includes information 31 "The medical record information you shared contains a specific disease name, and the disease name is the core content of the medical record information. Please select the corresponding processing strategy", as well as processing strategy candidates: "Delete private data" candidate control 32, "Retain private data" candidate control 33 and "Blur private data" candidate control 34. If the user wants to hide the name of his or her disease in the medical record information and wants to replace the specific disease name with the specific symptoms of the disease to protect his or her private data, the user clicks on the "Blur private data" candidate control 34, and the specific disease name "asthma" in the medical record information can be blurred to "paroxysmal attacks of wheezing, chest tightness, shortness of breath or coughing, symptoms that occur or worsen at night and early morning".

[0094] In the above example, regardless of whether the correlation between the subject of the shared information and the private data in the shared information is greater than a first threshold, and whether the semantic correlation between the shared information and the private data in the shared information is greater than a second threshold, three processing strategy candidates are provided in the prompt information for the user to choose. In an embodiment of the present application, it is also possible to provide only one processing strategy candidate based on whether the correlation between the subject of the shared information and the private data in the shared information is greater than the first threshold, and whether the semantic correlation between the shared information and the private data in the shared information is greater than the second threshold, and ask the user whether to select the given processing strategy candidate. If the given processing strategy candidate is selected, the private data in the shared information can be directly processed based on the processing strategy corresponding to the processing strategy candidate. If the user determines not to select the given processing strategy candidate, the other two processing strategy candidates can be displayed for the user to choose.

[0095] For example, when the correlation between the subject of the shared information and the private data in the shared information is less than a first threshold, a prompt message may be directly displayed, and the prompt message may be as follows: Figure 4 The pop-up window interface 40 shown in FIG. 4 includes a message 41 “The correlation between the subject of the shared information and the private data is less than a first threshold, do you want to delete the private data?”, an “OK” control 42, and a “Cancel” control 43. If the user selects the “OK” control 42, the private data in the shared information can be directly deleted to obtain the target shared information. If the user selects the “Cancel” control 43, it means that the user does not want to delete the private data, and the following information can be displayed: Figure 5 The pop-up interface 50 shown may include two candidate options, "Preserve Private Data" candidate option control 51 and "Blur Private Data" candidate option control 52, for the user to choose. Based on the user's choice, the corresponding processing strategy may be used to process the private data in the shared information to obtain the target shared information.

[0096] In other embodiments, when the correlation between the subject of the shared information and the private data in the shared information is less than a first threshold, it means that the user did not intend to share his or her private data, but the user did not notice that he or she had shared the private data. Therefore, the prompt message may not be displayed at this time, that is, the user does not need to select a corresponding processing strategy, but can directly adopt the corresponding processing strategy to process the private data in the shared information. In other words, when the correlation between the subject of the shared information and the private data in the shared information is less than a first threshold, the private data in the shared information can be directly deleted from the shared information without displaying a prompt message.

[0097] In an embodiment of the present application, by displaying prompt information including at least one processing strategy candidate, and then responding to the user's first input of at least one processing strategy candidate, the private data in the shared information can be processed according to the processing strategy corresponding to the processing strategy candidate selected by the first input to obtain the target shared information. In this way, the private data in the shared information can be processed according to the processing strategy selected by the user based on the user's needs, thereby meeting the user's personalized needs for processing the private data in the shared information.

[0098] It should be noted that the process of steps 120 to 150 is performed after the user has uploaded the sharing information and before the sharing information is displayed on the sharing platform. That is, the sharing information uploaded by the user and seen by other users is the information after the privacy data in the sharing information has been processed, that is, the target sharing information. In other words, after receiving the sharing information uploaded by the user, the sharing platform first performs the process of steps 120 to 140 above, and after obtaining the target sharing information, the target sharing information is displayed on the sharing platform. The information seen by other users on the sharing platform is the target sharing information. For example, in the first example above, after the user uploads the order information on the social media, after performing the process of steps 120 to 140 above, the user's address and telephone number are deleted from the order information. Then, the order information uploaded by the user displayed on the social media is the order information with the user's address and telephone number deleted.

[0099] In some embodiments of the present application, the above steps 120 to 140 may specifically include:

[0100] Based on the first multimodal large model, private data in the shared information is identified, and based on the context information and source of the shared information, the subject of the shared information is determined, and based on the correlation between the subject of the shared information and the private data in the shared information, a processing strategy for processing the private data in the shared information is determined.

[0101] The first multimodal large model can be a large model for identifying private data in shared information, determining the subject of the shared information based on the context information and source of the shared information, and determining a processing strategy for processing the private data in the shared information based on the correlation between the subject of the shared information and the private data in the shared information. The first multimodal large model can be a multimodal large model obtained by fine-tuning an existing open source multimodal large model, which is used to identify shared information, obtain private data in the shared information, determine the subject of the shared information based on the context information and source of the shared information, and determine a processing strategy for processing the private data in the shared information based on the correlation between the subject of the shared information and the private data in the shared information. The first multimodal large model can be, for example, a Vision-Language Multimodal Large Model (CogVLM) or an Omnimodal Large Multi-task Model (OmniLMM).

[0102] In an embodiment of the present application, private data in shared information is identified through a first multimodal large model, and the subject of the shared information is determined based on the contextual information and source of the shared information, and a processing strategy for processing the private data in the shared information is determined based on the correlation between the subject of the shared information and the private data in the shared information. In this way, there is no need for users to manually identify the subject of the shared information and the private data in the shared information, and calculate the correlation between the subject of the shared information and the private data in the shared information to determine the processing strategy for processing the private data in the shared information. This improves the efficiency and accuracy of determining whether the shared information contains private data, and when the shared information contains private data, determining the processing strategy for processing the private data in the shared information.

[0103] In some embodiments of the present application, before identifying the private data in the shared information based on the first multimodal macro model, determining the subject of the shared information based on the contextual information and source of the shared information, and determining a processing strategy for the private data in the shared information based on the correlation between the subject of the shared information and the private data in the shared information, the aforementioned method may further include:

[0104] Obtain a training sample set;

[0105] For each set of training samples, the training samples are input into the second multimodal large model, and a prediction processing strategy for processing the sample privacy data in the training samples is output;

[0106] According to the prediction processing strategy and the sample processing strategy in the training samples, the second multimodal large model is trained to obtain the first multimodal large model.

[0107] The training sample set may be a collection of training samples used to train the second multimodal large model. The training sample set may include multiple groups of training samples, each group of training samples may include sample sharing information, sample privacy data in the sample sharing information, and a sample processing strategy for processing the sample privacy data.

[0108] The sample sharing information may be sharing information uploaded by the user some time before, such as information uploaded by the user within one month before the current time.

[0109] Sample privacy data may be data related to the user's identity involved in the sample sharing information, such as the user's address, telephone number, ID number, specific disease, and other information.

[0110] The sample processing strategy may be a pre-labeled processing strategy for processing sample privacy data.

[0111] The second multimodal large model can be a selected open source multimodal large model. After the second multimodal large model is trained using the training sample set, the first multimodal large model can be obtained.

[0112] The prediction processing strategy may be a processing strategy for processing sample privacy data in the training sample after the training sample is input into the second multimodal large model.

[0113] In some embodiments of the present application, for each group of training samples in the acquired training sample set, the training samples are input into the second multimodal large model, and a prediction processing strategy for processing the sample privacy data in the training samples can be output. Then, based on the prediction processing strategy and the sample processing strategy in the training samples, the loss function value of the second multimodal large model can be obtained. When the loss function value meets the preset training stop condition, the training of the second multimodal large model can be stopped. When the loss function value does not meet the preset training stop condition, the model parameters of the second multimodal large model are adjusted, and then the second multimodal large model is continued to be trained using the training samples until the loss function value meets the preset training stop condition, and the first multimodal large model is obtained.

[0114] The above-mentioned preset training stop condition can be a pre-set stop condition for training the second multimodal large model. For example, the preset training stop condition can be that the loss function value is less than a certain threshold. The specific threshold can be set according to user needs and is not limited in the embodiments of this application.

[0115] In an embodiment of the present application, a first multimodal large model is obtained by training the second multimodal large model with the acquired training sample set, so as to facilitate the identification of the subject of shared information and the privacy data in the shared information based on the first multimodal large model, and determine the processing strategy for processing the privacy data based on the correlation between the subject and the privacy data, thereby improving the efficiency and accuracy of determining whether the shared information contains privacy data, and determining the processing strategy for processing the privacy data when the shared information contains privacy data.

[0116] It should be noted that after obtaining the first multimodal large model, the first multimodal large model can be deployed in the electronic device held by the user. In this way, after detecting that the user has uploaded shared information, it can be directly processed based on the first multimodal large model to obtain a processing strategy for processing the privacy data in the shared information.

[0117] In some embodiments of the present application, obtaining a training sample set may specifically include:

[0118] Obtaining first sample sharing information of the user within a first time period;

[0119] Extracting the user's first sample private data from the first sample sharing information;

[0120] Extracting second sample private data of the user from a page containing the user's private data in an electronic device held by the user;

[0121] The first sample private data and the second sample private data are used as sample private data.

[0122] The first time period may be a period before the current time. For example, if the current time is 2025.6.6, the first time period may be one month before the current time, that is, the first time period may be 2025.5.6-2025.6.6.

[0123] The first sample sharing information may be public information uploaded by the user on social media within the first time period, for example, it may be public information such as pictures, articles, and videos uploaded by the user on social media within the first time period.

[0124] The first sample private data may be private data of the user extracted from the first sample sharing information.

[0125] The page containing the user's private data on the user's electronic device may be a page containing the user's private data, such as the order page of a shopping application, which may contain the user's address, phone number, and other private data. Another example of a page containing the user's private data is the order page of a ticket purchasing application, which may contain the user's phone number, ID number, and other private data.

[0126] The second sample private data may be private data of the user extracted from a page containing the private data of the user in an electronic device owned by the user.

[0127] In some embodiments of the present application, web crawler technology can be used to obtain the first sample sharing information uploaded by the user within a first time period, and then the user's first sample privacy data can be extracted from the first sample sharing information. Specifically, the user's first sample privacy data can be marked from the first sample sharing information using existing marking software and / or manual marking by the user.

[0128] Then, a page containing the user's private data is obtained from the electronic device held by the user, and the user's second sample private data is extracted from the page using existing annotation software and / or manual annotation by the user.

[0129] According to the first sample privacy data and the second sample privacy data extracted above, they can be used as sample privacy data in the training sample set. The sample privacy data here can be divided into general privacy data and personal privacy data. That is, the privacy data obtained on the public platform above can be general privacy data, and the privacy data extracted from the user's personal device is personal privacy data. That is, the first sample privacy data mentioned above is general privacy data, and the second sample privacy data is personal privacy data.

[0130] It should be noted that when using existing annotation software and / or manual annotation by the user to mark the user's first sample private data from the first sample shared information, if the sample shared information is text-based information, text recognition technology can be used to identify the private data therein, such as the user's name, address, ID number, telephone number, etc. If the sample shared information is image-based information, the area of ​​the private data can be framed in the image and the specific data type can be marked, such as name or address. If the sample shared information is video-based information, the video can be analyzed frame by frame to mark possible private data.

[0131] In some embodiments of the present application, for any sample privacy data among the first sample privacy data and the second sample privacy data, the subject of the information containing the sample privacy data can be labeled according to the source of the sample privacy data and the context information of the information containing the sample privacy data. In this way, in the subsequent training process of the second multimodal large model, the corresponding subject can be judged according to the context information and source of the sample privacy data, and the subject can be compared with the labeled subject to train the second multimodal large model.

[0132] The specific training process of the second multimodal large model is consistent with the application process of the first multimodal large model in the above embodiment, and will not be repeated here.

[0133] In an embodiment of the present application, the sample privacy data in the training sample can be obtained by extracting the user's first sample privacy data from the first sample sharing information uploaded by the user within the first time period, and extracting the user's second sample privacy data from the page containing the user's privacy data in the electronic device held by the user. In this way, the sample privacy data is determined from the sharing information on the public platform and the page containing the user's privacy data in the electronic device privately held by the user. In this way, the sample privacy data is obtained from multiple paths, which improves the training samples for training the second multimodal large model, and thereby improves the robustness of the first multimodal large model.

[0134] In some embodiments of the present application, after the user inputs a first input of at least one processing strategy candidate, and processes the private data in the shared information according to the processing strategy corresponding to the processing strategy candidate selected by the first input, to obtain the target shared information, the method may further include:

[0135] Based on the first input, the first multimodal large model is optimized to obtain a third multimodal large model.

[0136] The third multimodal large model may be a multimodal large model obtained by optimizing the first multimodal large model.

[0137] In some embodiments of the present application, after the user completes the first input, the user feedback data can also be regularly analyzed to identify the user's general preferences and dissatisfaction with the processing of privacy data. For example, when the correlation between the subject of the shared information and the privacy data is greater than a first threshold, regardless of whether the semantic relevance between the shared information and the privacy data is greater than a second threshold, most users prefer to choose to blur the privacy data. In this case, the first multimodal large model can be further fine-tuned and optimized so that the first multimodal large model can preferentially recommend blurring.

[0138] In an embodiment of the present application, the first multimodal large model can be optimized based on the first input to obtain a third multimodal large model. In this way, the third multimodal large model can prioritize the processing strategy required by the user, so that the processing strategy recommended by the multimodal large model in the embodiment of the present application is more in line with the user's preferences and meets the user's personalized needs.

[0139] The information processing method provided in the embodiment of the present application can be executed by an information processing device. In the embodiment of the present application, the information processing device provided in the embodiment of the present application is described by taking the information processing device executing the information processing method as an example.

[0140] Figure 6 FIG. 1 is a structural diagram of an information processing device according to an exemplary embodiment. Figure 6 As shown, the information processing device 600 may include:

[0141] A first acquisition module 610 is used to acquire the user's sharing information;

[0142] A first identification module 620 is configured to identify private data in the shared information, where the private data in the shared information is data associated with the user's identity;

[0143] A first determining module 630 is configured to determine a subject of the shared information based on the context information and source of the shared information;

[0144] A second determining module 640 is configured to determine a processing strategy for processing the private data in the shared information based on the correlation between the subject of the shared information and the private data in the shared information;

[0145] The third determining module 650 is configured to process the private data in the shared information based on the processing strategy to obtain target shared information.

[0146] In an embodiment of the present application, when the user's shared information is obtained, the private data in the shared information can be identified, and the subject of the shared information can be identified based on the context information and source of the shared information. In this way, through the scheme of the embodiment of the present application, it is possible to identify whether the shared information to be shared by the user contains private data, and when the shared information contains private data, it is possible to determine the processing strategy for processing the private data in the shared information based on the correlation between the subject of the shared information and the private data in the shared information, and then the private data in the shared information can be processed based on the processing strategy to obtain the target shared information. The target shared information obtained in this way has already processed the private data in the shared information, thereby ensuring the security of the user's private data.

[0147] In some embodiments of the present application, the second determining module 640 may include:

[0148] a first determining unit, configured to, if the correlation between the subject of the shared information and the private data in the shared information is less than a first threshold, determine that a processing strategy for processing the private data in the shared information is to delete the private data from the shared information;

[0149] The second determining unit is configured to determine, when the correlation between the subject of the shared information and the private data in the shared information is greater than or equal to a first threshold, a processing strategy for processing the private data in the shared information based on the semantic correlation between the shared information and the private data in the shared information.

[0150] In some embodiments of the present application, the second determining unit is specifically configured to:

[0151] If the semantic relevance between the shared information and the private data in the shared information is greater than a second threshold, determining that a processing strategy for processing the private data in the shared information is to retain the private data in the shared information;

[0152] When the semantic correlation between the shared information and the private data in the shared information is less than or equal to the second threshold, determining that the processing strategy for the private data in the shared information is to obfuscate the private data in the shared information, wherein the obfuscation of the private data in the shared information is to replace the private data in the shared information with semantically equivalent obfuscated data.

[0153] In some embodiments of the present application, the apparatus may further include:

[0154] A display module, configured to display prompt information before processing the private data in the shared information based on the processing strategy to obtain target shared information, wherein the prompt information includes at least one processing strategy candidate;

[0155] The third determining module 650 is specifically configured to:

[0156] In response to a first input of the user on the at least one processing strategy candidate, the private data in the shared information is processed according to the processing strategy corresponding to the processing strategy candidate selected by the first input to obtain target shared information.

[0157] In some embodiments of the present application, the first identification module 620 is specifically configured to identify private data in the shared information based on the first multimodal macro model;

[0158] A first determination module 630 is specifically configured to determine a topic of the shared information based on the first multimodal macro model and the context information and source of the shared information;

[0159] The second determining module 640 is specifically configured to determine a processing strategy for processing the private data in the shared information according to the correlation between the subject of the shared information and the private data in the shared information.

[0160] The information processing device in the embodiment of the present application can be an electronic device or a component in an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or a device other than a terminal. For example, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a mobile Internet device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a personal digital assistant (PDA), etc. It can also be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., and the embodiment of the present application does not specifically limit it.

[0161] The information processing device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0162] The information processing device provided in the embodiment of the present application can realize Figure 1 To avoid repetition, the various processes implemented in the method embodiment are not described here.

[0163] Alternatively, as Figure 7 As shown, an embodiment of the present application also provides an electronic device 700, including a processor 701 and a memory 702, wherein the memory 702 stores a program or instruction that can be run on the processor 701. When the program or instruction is executed by the processor 701, the various steps of the above-mentioned information processing method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0164] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0165] Figure 8 A schematic diagram of the hardware structure of an electronic device implementing an embodiment of the present application.

[0166] The electronic device 800 includes but is not limited to: a radio frequency unit 801, a network module 802, an audio output unit 803, an input unit 804, a sensor 805, a display unit 806, a first user input unit 807, an interface unit 808, a memory 809, and a processor 810.

[0167] Those skilled in the art will understand that the electronic device 800 may also include a power source (such as a battery) to power each component, and the power source may be logically connected to the processor 810 through a power management system, thereby implementing functions such as charging, discharging, and power consumption management through the power management system. Figure 8 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be repeated here.

[0168] Among them, the processor 810 is used to obtain the user's shared information; identify the privacy data in the shared information, where the privacy data in the shared information is data associated with the user's identity; determine the subject of the shared information based on the context information and source of the shared information; determine a processing strategy for processing the privacy data in the shared information based on the correlation between the subject of the shared information and the privacy data in the shared information; and process the privacy data in the shared information based on the processing strategy to obtain the target shared information.

[0169] In this way, when the user's shared information is obtained, the private data in the shared information can be identified, and the subject of the shared information can be identified based on the context information and source of the shared information. In this way, through the solution of the embodiment of the present application, it is possible to identify whether the shared information to be shared by the user contains private data, and in the case that the shared information contains private data, it is possible to determine the processing strategy for processing the private data in the shared information based on the correlation between the subject of the shared information and the private data in the shared information, and then the private data in the shared information can be processed based on the processing strategy to obtain the target shared information. The target shared information obtained in this way has already processed the private data in the shared information, ensuring the security of the user's private data.

[0170] Optionally, the processor 810 is further used to determine, when the correlation between the subject of the shared information and the privacy data in the shared information is less than a first threshold, that a processing strategy for processing the privacy data in the shared information is to delete the privacy data in the shared information; and when the correlation between the subject of the shared information and the privacy data in the shared information is greater than or equal to the first threshold, determine, based on the semantic correlation between the shared information and the privacy data in the shared information, a processing strategy for processing the privacy data in the shared information.

[0171] In this way, if the correlation between the subject of the shared information and the private data in the shared information is less than a first threshold, the private data can be deleted from the shared information, thereby protecting the user's private data without affecting the user's shared content. If the correlation between the subject of the shared information and the private data in the shared information is greater than or equal to the first threshold, a processing strategy for the private data in the shared information can be further determined based on the semantic correlation between the shared information and the private data in the shared information. In this way, different processing strategies for the private data in the shared information can be determined based on different semantic correlations between the shared information and the private data in the shared information, thereby increasing the flexibility of handling the private data in the shared information.

[0172] Optionally, the processor 810 is further configured to determine, when the semantic correlation between the shared information and the privacy data in the shared information is greater than a second threshold, that a processing strategy for processing the privacy data in the shared information is to retain the privacy data in the shared information; and when the semantic correlation between the shared information and the privacy data in the shared information is less than or equal to the second threshold, determine that the processing strategy for processing the privacy data in the shared information is to blur the privacy data in the shared information, wherein the blurring of the privacy data in the shared information is to replace the privacy data in the shared information with semantically equivalent blurred data.

[0173] In this way, when the semantic relevance between the shared information and the private data in the shared information is greater than the second threshold, the processing strategy for the private data in the shared information is determined to be to retain the private data. This ensures that others can well understand the user's shared information so that they can provide accurate feedback to the user, such as providing accurate medical consultation advice. When the semantic relevance between the shared information and the private data in the shared information is less than or equal to the second threshold, the processing strategy for the private data in the shared information is determined to be to replace the private data with semantically equivalent fuzzified data. This ensures the security of the user's private data while also facilitating others to provide accurate feedback to the user based on the replaced semantically equivalent fuzzified data, thereby improving the user's sharing experience of sharing content.

[0174] Optionally, the display unit 806 is configured to display prompt information before processing the private data in the shared information based on the processing strategy to obtain target shared information, the prompt information including at least one processing strategy candidate;

[0175] The processor 810 is further configured to, in response to a user's first input of the at least one processing strategy candidate, process the private data in the shared information according to the processing strategy corresponding to the processing strategy candidate selected by the first input to obtain target shared information.

[0176] In this way, by displaying prompt information including at least one processing strategy candidate, and then responding to the user's first input of at least one processing strategy candidate, the privacy data can be processed according to the processing strategy corresponding to the processing strategy candidate selected by the first input to obtain the target sharing information. In this way, the privacy data can be processed according to the processing strategy selected by the user based on the user's needs, thereby meeting the user's personalized needs for privacy data processing.

[0177] Optionally, the processor 810 is further used to identify the private data in the shared information based on the first multimodal large model, and determine the subject of the shared information based on the context information and source of the shared information, and determine a processing strategy for processing the private data in the shared information based on the correlation between the subject of the shared information and the private data in the shared information.

[0178] In this way, the privacy data in the shared information is identified through the first multimodal large model, and the subject of the shared information is determined based on the context information and source of the shared information, and the processing strategy for processing the privacy data in the shared information is determined based on the correlation between the subject of the shared information and the privacy data in the shared information. In this way, there is no need for the user to manually identify the subject of the shared information and the privacy data in the shared information, and calculate the correlation between the subject of the shared information and the privacy data in the shared information to determine the processing strategy for processing the privacy data in the shared information. This improves the efficiency and accuracy of judging whether the shared information contains privacy data, and determining the processing strategy for processing the privacy data in the shared information when the shared information contains privacy data.

[0179] It should be understood that in an embodiment of the present application, the input unit 804 may include a graphics processing unit (GPU) 8041 and a microphone 8042, and the graphics processor 8041 processes the image data of a static picture or video obtained by an image capture device (such as a color camera) in a video capture mode or an image capture mode. The display unit 806 may include a display panel 8061, and the display panel 8061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The first user input unit 807 includes a touch panel 8071 and at least one of other input devices 8072. The touch panel 8071 is also called a touch screen. The touch panel 8071 may include two parts: a touch detection device and a touch controller. Other input devices 8072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and an operating stick, which will not be repeated here.

[0180] The memory 809 can be used to store software programs and various data. The memory 809 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 809 may include a volatile memory or a non-volatile memory, or the memory 809 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 809 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0181] Processor 810 may include one or more processing units. Optionally, processor 810 integrates an application processor and a modem processor. The application processor primarily handles operations related to the operating system, the first user interface, and application programs, while the modem processor primarily processes wireless communication signals, such as a baseband processor. It is understood that the modem processor may not be integrated into processor 810.

[0182] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned information processing method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0183] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0184] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned information processing method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0185] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0186] An embodiment of the present application provides a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement the various processes of the above-mentioned information processing method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0187] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0188] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0189] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

Claims

1. An information processing method, characterized in that: The method comprises: Get user's sharing information; Identifying private data in the shared information, where the private data in the shared information is data associated with the user's identity; Determining a subject of the shared information based on context information and a source of the shared information; determining, based on the correlation between the subject of the shared information and the private data in the shared information, a processing strategy for processing the private data in the shared information; The private data in the shared information is processed based on the processing strategy to obtain target shared information.

2. The method according to claim 1, characterized in that The determining, based on the correlation between the subject of the shared information and the private data in the shared information, a processing strategy for processing the private data in the shared information includes: If the correlation between the subject of the shared information and the private data in the shared information is less than a first threshold, determining that a processing strategy for processing the private data in the shared information is to delete the private data from the shared information; When the correlation between the subject of the shared information and the private data in the shared information is greater than or equal to a first threshold, a processing strategy for processing the private data in the shared information is determined according to the semantic correlation between the shared information and the private data in the shared information.

3. The method according to claim 2, characterized in that The processing strategy for processing the private data in the shared information according to the semantic relevance between the shared information and the private data in the shared information includes: If the semantic relevance between the shared information and the private data in the shared information is greater than a second threshold, determining that a processing strategy for processing the private data in the shared information is to retain the private data in the shared information; When the semantic correlation between the shared information and the private data in the shared information is less than or equal to the second threshold, determining that the processing strategy for the private data in the shared information is to obfuscate the private data in the shared information, wherein the obfuscation of the private data in the shared information is to replace the private data in the shared information with semantically equivalent obfuscated data.

4. The method according to claim 2, characterized in that Before processing the private data in the shared information based on the processing strategy to obtain target shared information, the method further includes: Displaying prompt information, wherein the prompt information includes at least one processing strategy candidate; The processing of the private data in the shared information based on the processing strategy to obtain target shared information includes: In response to a first input of the user on the at least one processing strategy candidate, the private data in the shared information is processed according to the processing strategy corresponding to the processing strategy candidate selected by the first input to obtain target shared information.

5. The method according to claim 1, wherein The identifying the private data in the shared information, determining the subject of the shared information based on the context information and source of the shared information, and determining a processing strategy for the private data in the shared information based on the correlation between the subject of the shared information and the private data in the shared information, includes: Based on the first multimodal large model, the private data in the shared information is identified, and based on the context information and source of the shared information, the subject of the shared information is determined; and based on the correlation between the subject of the shared information and the private data in the shared information, a processing strategy for processing the private data in the shared information is determined.

6. An information processing device, characterized in that The device comprises: The first acquisition module is used to obtain the user's sharing information; A first identification module is used to identify private data in the shared information, where the private data in the shared information is data associated with the user identity; A first determining module, configured to determine a subject of the shared information based on context information and a source of the shared information; a second determining module, configured to determine a processing strategy for processing the private data in the shared information based on the correlation between the subject of the shared information and the private data in the shared information; The third determining module is configured to process the private data in the shared information based on the processing strategy to obtain target shared information.

7. The device according to claim 6, characterized in that The second determining module includes: a first determining unit, configured to, if the correlation between the subject of the shared information and the private data in the shared information is less than a first threshold, determine that a processing strategy for processing the private data in the shared information is to delete the private data from the shared information; The second determining unit is configured to determine, when the correlation between the subject of the shared information and the private data in the shared information is greater than or equal to a first threshold, a processing strategy for processing the private data in the shared information based on the semantic correlation between the shared information and the private data in the shared information.

8. The device according to claim 7, characterized in that The second determining unit is specifically configured to: If the semantic relevance between the shared information and the private data in the shared information is greater than a second threshold, determining that a processing strategy for processing the private data in the shared information is to retain the private data in the shared information; When the semantic correlation between the shared information and the private data in the shared information is less than or equal to the second threshold, determining that the processing strategy for the private data in the shared information is to obfuscate the private data in the shared information, wherein the obfuscation of the private data in the shared information is to replace the private data in the shared information with semantically equivalent obfuscated data.

9. The device according to claim 7, characterized in that The device further comprises: A display module, configured to display prompt information before processing the private data in the shared information based on the processing strategy to obtain target shared information, wherein the prompt information includes at least one processing strategy candidate; The third determining module is specifically configured to: In response to a first input of the user on the at least one processing strategy candidate, the private data in the shared information is processed according to the processing strategy corresponding to the processing strategy candidate selected by the first input to obtain target shared information.

10. The device according to claim 6, characterized in that The first identification module is specifically configured to identify private data in the shared information based on the first multimodal large model; The first determining module is specifically configured to determine a topic of the shared information based on the first multimodal macro model and the context information and source of the shared information; The second determining module is specifically configured to determine a processing strategy for processing the private data in the shared information according to the correlation between the subject of the shared information and the private data in the shared information.

Images