A permission processing method and system based on artificial intelligence

Abstract

The present invention relates to the field of artificial intelligence technology, and to an artificial intelligence-based permission processing method and system. The present invention uses an encoder to extract permission access vectors of multiple template permission access application events from permission access behavior data through a permission discrimination network, and further performs significance processing on these vectors through a significance attention unit to generate a significance vector. Subsequently, the permission discrimination network generates two sets of permission discrimination labels based on the permission access vector and the significance vector: a first permission discrimination label and a second permission discrimination label, and then updates the parameters of the permission discrimination network according to a first error parameter and a second error parameter; these two error parameters respectively measure the deviation between the real permission training label of the template permission access behavior data and the two sets of permission discrimination labels. Based on artificial intelligence technology, the present invention can automatically identify and evaluate permission request events, providing strong support for ensuring the security of information systems.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based permission processing method and system. Background Art

[0002] With the rapid development of information technology, various applications and systems have put forward higher requirements for user rights management while providing rich services. Access control has become the core link to ensure data security and prevent unauthorized access and abuse of key resources. Traditional access control methods rely on predefined rules or policies, but as business logic becomes increasingly complex, these static rules are difficult to fully and accurately handle dynamically changing access requests.

[0003] The existing permission identification systems are mainly based on simple logical judgments or manually set rules, lacking flexibility and adaptability, and cannot effectively identify and respond to abnormal or malicious permission application behaviors. In addition, due to the lack of in-depth analysis of contextual information, these systems often cannot fully understand the actual intention of permission requests, which may result in false positives or false negatives, affecting system security and user experience. Summary of the invention

[0004] In view of this, the purpose of an embodiment of the present invention is to provide a permission processing method and system based on artificial intelligence, which uses an encoder to extract permission access vectors of multiple template permission access application events from permission access behavior data through a permission discrimination network, and further performs saliency processing on these vectors through a saliency attention unit to generate a saliency vector. Subsequently, the permission discrimination network generates two sets of permission discrimination labels based on the permission access vector and the saliency vector: a first permission discrimination label and a second permission discrimination label, and then updates the parameters of the permission discrimination network based on the first error parameter and the second error parameter. These two error parameters respectively measure the deviation between the real permission training label of the template permission access behavior data and the two sets of permission discrimination labels. By minimizing these errors, the discrimination ability of the network is enhanced. As a result, permission request events can be automatically identified and evaluated, providing strong support for ensuring the security of information systems.

[0005] According to one aspect of an embodiment of the present invention, a permission processing method and system based on artificial intelligence are provided, and the method includes:

[0006] Loading the template permission access behavior data into the permission discrimination network, and obtaining permission access vectors of multiple template permission access application events of the template permission access behavior data based on an encoder in the permission discrimination network;

[0007] Based on the saliency attention unit in the permission discrimination network, the permission access vectors of the plurality of template permission access application events are processed for saliency to generate a saliency vector of the template permission access behavior data;

[0008] Based on the permission discrimination network, the permission access vectors of the plurality of template permission access application events are processed to generate a first permission discrimination label of the template permission access behavior data;

[0009] Processing the saliency vector of the template permission access behavior data to generate a second permission discrimination label of the template permission access behavior data;

[0010] The parameters of the permission discrimination network are updated according to a first error parameter and a second error parameter, wherein the first error parameter is an error parameter between a permission training label of the template permission access behavior data and the first permission discrimination label, and the second error parameter is an error parameter between the permission training label and the second permission discrimination label.

[0011] In an alternative implementation, updating the parameters of the authority discrimination network according to the first error parameter and the second error parameter includes:

[0012] updating parameters of the encoder in the authority discrimination network according to the first error parameter and the second error parameter;

[0013] According to the second error parameter, parameters of the saliency attention unit in the authority discrimination network are updated.

[0014] In an alternative implementation, updating parameters of the encoder in the authority discrimination network according to the first error parameter and the second error parameter includes:

[0015] When the multiple template permission access application events include at least two template permission access application events with different permission participation domains, the encoder is updated according to the first Loss layer and the first importance coefficient corresponding to the first error parameter, and the second Loss layer and the second importance coefficient corresponding to the second error parameter, the first importance coefficient reflects the relevance of the first Loss layer to the network parameters of the permission discrimination network when the network parameters are updated, the second importance coefficient reflects the relevance of the second Loss layer to the network parameters of the permission discrimination network when the network parameters are updated, and the second importance coefficient is greater than the first importance coefficient;

[0016] The updating of the parameters of the saliency attention unit in the authority discrimination network according to the second error parameter includes:

[0017] According to the second Loss layer and the second importance coefficient, parameters of the saliency attention unit are updated.

[0018] In an alternative implementation, updating parameters of the encoder in the authority discrimination network according to the first error parameter and the second error parameter includes:

[0019] When the multiple template permission access application events are template permission access application events of the same permission participation domain, the encoder is updated according to the first Loss layer and the first importance coefficient corresponding to the first error parameter, and the second Loss layer and the second importance coefficient corresponding to the second error parameter, the first importance coefficient reflects the relevance of the first Loss layer to the network parameters of the permission discrimination network when the network parameters are updated, the second importance coefficient reflects the relevance of the second Loss layer to the network parameters of the permission discrimination network when the network parameters are updated, and the second importance coefficient is less than the first importance coefficient;

[0020] The updating of the parameters of the saliency attention unit in the authority discrimination network according to the second error parameter includes:

[0021] According to the second Loss layer and the second importance coefficient, parameters of the saliency attention unit are updated.

[0022] In an alternative implementation, the saliency attention unit in the permission discrimination network performs saliency processing on the permission access vectors of the plurality of template permission access application events to generate the saliency vector of the template permission access behavior data, including:

[0023] Based on the saliency attention unit in the permission discrimination network, saliency processing is performed on the permission access vectors of every two associated template permission access application events in the multiple template permission access application events to generate saliency features of the multiple template permission access application events;

[0024] The significant features of the multiple template permission access application events are integrated to generate a significant vector of the template permission access behavior data.

[0025] In an alternative implementation, the processing of the permission access vectors of the plurality of template permission access application events to generate the first permission discrimination tag of the template permission access behavior data includes:

[0026] Performing full connection output on the permission access vectors of the plurality of template permission access application events to generate a first prediction parameter of the template permission access behavior data;

[0027] A first permission discrimination label of the template permission access behavior data is determined according to the first prediction parameter.

[0028] According to another aspect of an embodiment of the present invention, a permission processing method and system based on artificial intelligence are provided, and the system includes:

[0029] An acquisition module is configured to execute loading of the template permission access behavior data into the permission discrimination network, and based on an encoder in the permission discrimination network, acquire permission access vectors of a plurality of template permission access application events of the template permission access behavior data;

[0030] A processing module, configured to perform saliency processing on the permission access vectors of the plurality of template permission access application events based on the saliency attention unit in the permission discrimination network, and generate a saliency vector of the template permission access behavior data;

[0031] A discrimination module is configured to execute, based on the permission discrimination network, processing the permission access vectors of the plurality of template permission access application events to generate a first permission discrimination label of the template permission access behavior data; and processing the significance vector of the template permission access behavior data to generate a second permission discrimination label of the template permission access behavior data;

[0032] The training module is configured to execute parameter update of the permission discrimination network based on a first error parameter and a second error parameter, wherein the first error parameter is an error parameter between a permission training label of the template permission access behavior data and the first permission discrimination label, and the second error parameter is an error parameter between the permission training label and the second permission discrimination label.

[0033] According to another aspect of an embodiment of the present invention, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the above-described artificial intelligence-based permission processing methods when executing the computer program.

[0034] According to another aspect of an embodiment of the present invention, a storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned artificial intelligence-based permission processing methods are implemented.

[0035] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned artificial intelligence-based permission processing methods.

[0036] In order to make the above-mentioned purposes, features and advantages of the embodiments of the present invention more obvious and easy to understand, the embodiments will be described in detail below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 A schematic diagram showing components of a server provided by an embodiment of the present invention is shown;

[0039] Figure 2 A schematic diagram of a flow chart of a permission processing method based on artificial intelligence provided by an embodiment of the present invention is shown;

[0040] Figure 3 A functional module block diagram of an artificial intelligence-based permission processing system provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0041] In order to enable students in the technical field to better understand the scheme of the present invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. According to the embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] The terms "first", "second", "third", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0043] Figure 1An exemplary component diagram of a server 100 is shown. The server 100 may include one or more processors 104, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. The server 100 may also include any storage medium 106 for storing any kind of information such as code, settings, data, etc. Non-limitingly, for example, the storage medium 106 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any storage medium may use any technology to store information. Further, any storage medium may provide volatile or non-volatile retention of information. Further, any storage medium may represent a fixed or removable component of the server 100. In one case, when the processor 104 executes an associated instruction stored in any storage medium or a combination of storage media, the server 100 may perform any operation of the associated instruction. The server 100 also includes one or more drive units 108 for interacting with any storage medium, such as a hard disk drive unit, an optical disk drive unit, etc.

[0044] The server 100 also includes input / output 110 (I / O) for receiving various inputs (via input unit 112) and for providing various outputs (via output unit 114). One specific output mechanism may include a presentation device 116 and an associated graphical user interface (GUI) 118. The server 100 may also include one or more network interfaces 120 for exchanging data with other devices via one or more communication units 122. One or more communication buses 124 couple the components described above together.

[0045] The communication unit 122 may be implemented in any manner, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication unit 122 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers 100, etc. governed by any protocol or combination of protocols.

[0046] Figure 2 The flowchart of a permission processing method and system based on artificial intelligence provided by an embodiment of the present invention is shown. The permission processing method and system based on artificial intelligence can be Figure 1 The server 100 shown in the figure executes the detailed steps of the permission processing method based on artificial intelligence.

[0047] Step S110, loading the template permission access behavior data into the permission discrimination network, and obtaining permission access vectors of multiple template permission access application events of the template permission access behavior data based on the encoder in the permission discrimination network;

[0048] Step S120, based on the saliency attention unit in the permission discrimination network, performing saliency processing on the permission access vectors of the plurality of template permission access application events to generate a saliency vector of the template permission access behavior data;

[0049] Step S130: Based on the permission discrimination network, the permission access vectors of the plurality of template permission access application events are processed to generate a first permission discrimination label of the template permission access behavior data; the significance vector of the template permission access behavior data is processed to generate a second permission discrimination label of the template permission access behavior data;

[0050] Step S140, updating the parameters of the permission discrimination network according to the first error parameter and the second error parameter, wherein the first error parameter is the error parameter between the permission training label of the template permission access behavior data and the first permission discrimination label, and the second error parameter is the error parameter between the permission training label and the second permission discrimination label.

[0051] Based on the above steps, this embodiment uses an encoder to extract permission access vectors of multiple template permission access application events from permission access behavior data through a permission discrimination network, and further performs saliency processing on these vectors through a saliency attention unit to generate a saliency vector. Subsequently, the permission discrimination network generates two sets of permission discrimination labels based on the permission access vector and the saliency vector: a first permission discrimination label and a second permission discrimination label, and then updates the parameters of the permission discrimination network based on the first error parameter and the second error parameter. These two error parameters respectively measure the deviation between the real permission training label of the template permission access behavior data and the two sets of permission discrimination labels. By minimizing these errors, the discrimination ability of the network is enhanced. As a result, permission request events can be automatically identified and evaluated, providing strong support for ensuring the security of information systems.

[0052] In an alternative implementation, updating the parameters of the authority discrimination network according to the first error parameter and the second error parameter includes:

[0053] updating parameters of the encoder in the authority discrimination network according to the first error parameter and the second error parameter;

[0054] According to the second error parameter, parameters of the saliency attention unit in the authority discrimination network are updated.

[0055] In an alternative implementation, updating parameters of the encoder in the authority discrimination network according to the first error parameter and the second error parameter includes:

[0056] When the multiple template permission access application events include at least two template permission access application events with different permission participation domains, the encoder is updated according to the first Loss layer and the first importance coefficient corresponding to the first error parameter, and the second Loss layer and the second importance coefficient corresponding to the second error parameter, the first importance coefficient reflects the relevance of the first Loss layer to the network parameters of the permission discrimination network when the network parameters are updated, the second importance coefficient reflects the relevance of the second Loss layer to the network parameters of the permission discrimination network when the network parameters are updated, and the second importance coefficient is greater than the first importance coefficient;

[0057] The updating of the parameters of the saliency attention unit in the authority discrimination network according to the second error parameter includes:

[0058] According to the second Loss layer and the second importance coefficient, parameters of the saliency attention unit are updated.

[0059] In an alternative implementation, updating parameters of the encoder in the authority discrimination network according to the first error parameter and the second error parameter includes:

[0060] When the multiple template permission access application events are template permission access application events of the same permission participation domain, the encoder is updated according to the first Loss layer and the first importance coefficient corresponding to the first error parameter, and the second Loss layer and the second importance coefficient corresponding to the second error parameter, the first importance coefficient reflects the relevance of the first Loss layer to the network parameters of the permission discrimination network when the network parameters are updated, the second importance coefficient reflects the relevance of the second Loss layer to the network parameters of the permission discrimination network when the network parameters are updated, and the second importance coefficient is less than the first importance coefficient;

[0061] The updating of the parameters of the saliency attention unit in the authority discrimination network according to the second error parameter includes:

[0062] According to the second Loss layer and the second importance coefficient, parameters of the saliency attention unit are updated.

[0063] In an alternative implementation, the saliency attention unit in the permission discrimination network performs saliency processing on the permission access vectors of the plurality of template permission access application events to generate the saliency vector of the template permission access behavior data, including:

[0064] Based on the saliency attention unit in the permission discrimination network, saliency processing is performed on the permission access vectors of every two associated template permission access application events in the multiple template permission access application events to generate saliency features of the multiple template permission access application events;

[0065] The significant features of the multiple template permission access application events are integrated to generate a significant vector of the template permission access behavior data.

[0066] In an alternative implementation, the processing of the permission access vectors of the plurality of template permission access application events to generate the first permission discrimination tag of the template permission access behavior data includes:

[0067] Performing full connection output on the permission access vectors of the plurality of template permission access application events to generate a first prediction parameter of the template permission access behavior data;

[0068] A first permission discrimination label of the template permission access behavior data is determined according to the first prediction parameter.

[0069] Figure 3 The functional module diagram of a permission processing system 200 based on artificial intelligence provided by an embodiment of the present invention is shown. The functions implemented by the permission processing system 200 based on artificial intelligence can correspond to the steps performed by the above method. The permission processing system 200 based on artificial intelligence can be understood as the above server 100, or the processor of the server 100, or can be understood as a component independent of the above server 100 or the processor that implements the functions of the present invention under the control of the server 100, such as Figure 3 As shown, the functions of each functional module of the permission processing system 200 based on artificial intelligence are described in detail below.

[0070] The acquisition module 210 is configured to execute loading the template permission access behavior data into the permission discrimination network, and based on the encoder in the permission discrimination network, acquire the permission access vectors of multiple template permission access application events of the template permission access behavior data;

[0071] The processing module 220 is configured to execute a saliency attention unit in the permission discrimination network to perform saliency processing on the permission access vectors of the plurality of template permission access application events to generate a saliency vector of the template permission access behavior data;

[0072] The discrimination module 230 is configured to execute, based on the permission discrimination network, processing the permission access vectors of the plurality of template permission access application events to generate a first permission discrimination label of the template permission access behavior data; processing the significance vector of the template permission access behavior data to generate a second permission discrimination label of the template permission access behavior data;

[0073] The training module 240 is configured to perform parameter update on the permission discrimination network based on a first error parameter and a second error parameter, wherein the first error parameter is an error parameter between a permission training label of the template permission access behavior data and the first permission discrimination label, and the second error parameter is an error parameter between the permission training label and the second permission discrimination label.

[0074] Those skilled in the art can clearly understand that, for the 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.

[0075] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, the embodiments should be considered exemplary and non-restrictive in all respects, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the present invention.

Claims

1. A permission processing method based on artificial intelligence, characterized in that: The method comprises: Loading the template permission access behavior data into the permission discrimination network, and obtaining permission access vectors of multiple template permission access application events of the template permission access behavior data based on an encoder in the permission discrimination network; Based on the saliency attention unit in the permission discrimination network, the permission access vectors of the plurality of template permission access application events are processed for saliency to generate a saliency vector of the template permission access behavior data; Based on the permission discrimination network, the permission access vectors of the plurality of template permission access application events are processed to generate a first permission discrimination label of the template permission access behavior data; the significance vector of the template permission access behavior data is processed to generate a second permission discrimination label of the template permission access behavior data; updating parameters of the permission discrimination network according to a first error parameter and a second error parameter, wherein the first error parameter is an error parameter between a permission training label of the template permission access behavior data and the first permission discrimination label, and the second error parameter is an error parameter between the permission training label and the second permission discrimination label; The updating of the parameters of the authority discrimination network according to the first error parameter and the second error parameter comprises: updating parameters of the encoder in the authority discrimination network according to the first error parameter and the second error parameter; According to the second error parameter, updating the parameters of the saliency attention unit in the authority discrimination network; The updating of parameters of the encoder in the authority discrimination network according to the first error parameter and the second error parameter comprises: When the multiple template permission access application events include at least two template permission access application events with different permission participation domains, the encoder is updated according to the first Loss layer and the first importance coefficient corresponding to the first error parameter, and the second Loss layer and the second importance coefficient corresponding to the second error parameter, the first importance coefficient reflects the relevance of the first Loss layer to the network parameters of the permission discrimination network when the network parameters are updated, the second importance coefficient reflects the relevance of the second Loss layer to the network parameters of the permission discrimination network when the network parameters are updated, and the second importance coefficient is greater than the first importance coefficient; The updating of the parameters of the saliency attention unit in the authority discrimination network according to the second error parameter includes: According to the second Loss layer and the second importance coefficient, updating parameters of the salient attention unit; The updating of parameters of the encoder in the authority discrimination network according to the first error parameter and the second error parameter comprises: When the multiple template permission access application events are template permission access application events of the same permission participation domain, the encoder is updated according to the first Loss layer and the first importance coefficient corresponding to the first error parameter, and the second Loss layer and the second importance coefficient corresponding to the second error parameter, the first importance coefficient reflects the relevance of the first Loss layer to the network parameters of the permission discrimination network when the network parameters are updated, the second importance coefficient reflects the relevance of the second Loss layer to the network parameters of the permission discrimination network when the network parameters are updated, and the second importance coefficient is less than the first importance coefficient; The updating of the parameters of the saliency attention unit in the authority discrimination network according to the second error parameter includes: According to the second Loss layer and the second importance coefficient, updating parameters of the salient attention unit; The saliency attention unit in the permission discrimination network performs saliency processing on the permission access vectors of the plurality of template permission access application events to generate the saliency vector of the template permission access behavior data, including: Based on the saliency attention unit in the permission discrimination network, saliency processing is performed on the permission access vectors of every two associated template permission access application events in the multiple template permission access application events to generate saliency features of the multiple template permission access application events; Integrating the significant features of the plurality of template permission access application events to generate a significant vector of the template permission access behavior data; The processing of the permission access vectors of the plurality of template permission access application events to generate a first permission discrimination tag of the template permission access behavior data includes: Performing full connection output on the permission access vectors of the plurality of template permission access application events to generate a first prediction parameter of the template permission access behavior data; A first permission discrimination label of the template permission access behavior data is determined according to the first prediction parameter.

2. An artificial intelligence-based rights processing system, characterized in that: include: An acquisition module is configured to execute loading of the template permission access behavior data into the permission discrimination network, and based on an encoder in the permission discrimination network, acquire permission access vectors of a plurality of template permission access application events of the template permission access behavior data; A processing module, configured to perform saliency processing on the permission access vectors of the plurality of template permission access application events based on the saliency attention unit in the permission discrimination network, and generate a saliency vector of the template permission access behavior data; A determination module configured to execute, based on the permission determination network, processing the permission access vectors of the plurality of template permission access application events, and generating a first permission determination label of the template permission access behavior data; Processing the saliency vector of the template permission access behavior data to generate a second permission discrimination label of the template permission access behavior data; a training module configured to perform parameter update on the permission discrimination network according to a first error parameter and a second error parameter, wherein the first error parameter is an error parameter between a permission training label of the template permission access behavior data and the first permission discrimination label, and the second error parameter is an error parameter between the permission training label and the second permission discrimination label; The updating of the parameters of the authority discrimination network according to the first error parameter and the second error parameter comprises: updating parameters of the encoder in the authority discrimination network according to the first error parameter and the second error parameter; According to the second error parameter, updating the parameters of the saliency attention unit in the authority discrimination network; The updating of parameters of the encoder in the authority discrimination network according to the first error parameter and the second error parameter comprises: When the multiple template permission access application events include at least two template permission access application events with different permission participation domains, the encoder is updated according to the first Loss layer and the first importance coefficient corresponding to the first error parameter, and the second Loss layer and the second importance coefficient corresponding to the second error parameter, the first importance coefficient reflects the relevance of the first Loss layer to the network parameters of the permission discrimination network when the network parameters are updated, the second importance coefficient reflects the relevance of the second Loss layer to the network parameters of the permission discrimination network when the network parameters are updated, and the second importance coefficient is greater than the first importance coefficient; The updating of the parameters of the saliency attention unit in the authority discrimination network according to the second error parameter includes: According to the second Loss layer and the second importance coefficient, updating parameters of the salient attention unit; The updating of parameters of the encoder in the authority discrimination network according to the first error parameter and the second error parameter comprises: When the multiple template permission access application events are template permission access application events of the same permission participation domain, the encoder is updated according to the first Loss layer and the first importance coefficient corresponding to the first error parameter, and the second Loss layer and the second importance coefficient corresponding to the second error parameter, the first importance coefficient reflects the relevance of the first Loss layer to the network parameters of the permission discrimination network when the network parameters are updated, the second importance coefficient reflects the relevance of the second Loss layer to the network parameters of the permission discrimination network when the network parameters are updated, and the second importance coefficient is less than the first importance coefficient; The updating of the parameters of the saliency attention unit in the authority discrimination network according to the second error parameter includes: According to the second Loss layer and the second importance coefficient, updating parameters of the salient attention unit; The saliency attention unit in the permission discrimination network performs saliency processing on the permission access vectors of the plurality of template permission access application events to generate the saliency vector of the template permission access behavior data, including: Based on the saliency attention unit in the permission discrimination network, saliency processing is performed on the permission access vectors of every two associated template permission access application events in the multiple template permission access application events to generate saliency features of the multiple template permission access application events; Integrating the significant features of the plurality of template permission access application events to generate a significant vector of the template permission access behavior data; The processing of the permission access vectors of the plurality of template permission access application events to generate a first permission discrimination tag of the template permission access behavior data includes: Performing full connection output on the permission access vectors of the plurality of template permission access application events to generate a first prediction parameter of the template permission access behavior data; A first permission discrimination label of the template permission access behavior data is determined according to the first prediction parameter.

3. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the artificial intelligence-based permission processing method described in claim 1 are implemented.

4. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the artificial intelligence-based permission processing method according to claim 1 are implemented.

5. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the artificial intelligence-based permission processing method described in claim 1 are implemented.

Images