Trust model evaluation method and apparatus

Abstract

The present application relates to the field of information security, and discloses a trust model evaluation method and apparatus. The method comprises: performing trust evaluation on a first entity on the basis of a trust model, so as to obtain trust evaluation results of the first entity, wherein there is at least one group of trust evaluation results, each group of trust evaluation results corresponds to one first indicator, and the first indicators are used for indicating an evaluation dimension of the trust model; and evaluating the trust model on the basis of the trust evaluation results, so as to obtain an evaluation result of the trust model, wherein the evaluation result of the trust model is used for indicating a trust evaluation capability of the trust model within the dimension of the first indicators. The present application can evaluate the trust evaluation capability of the trust model on the basis of the dimension of the first indicators for an entity in a specific application scenario, such as the first entity, so as to provide a decision-making basis for the selection of the trust model.

Description

Trust model evaluation method and device

[0001] This application claims priority to Chinese patent application number 202311739101.6, filed on December 15, 2023, entitled “Trust Model Evaluation Method and Device,” the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of information security, and in particular to a trust model evaluation method and device. Background Art

[0003] Trust assessment generally refers to evaluating the trustworthiness of entities within an application scenario. This can reveal whether an entity is trustworthy, whether it can interact with others, or whether its data is usable. For example, in some communications-related scenarios, an entity can refer to an interactive object or a communication node in a communication network, such as a network device or terminal device. Based on the trust assessment results of a communication node in the communication network, the security of the node can be determined, such as whether its data is trustworthy, thereby testing the security and reliability of the communication network.

[0004] The trust assessment method may include: using a trust assessment model to perform a trust assessment on an entity, and outputting a trust assessment result of the entity. The trust assessment model is also referred to as a trust model, and the trust assessment result may refer to the trustworthiness of the entity. Different trust models may output trust assessment results with different granularity. For example, some trust models may output trust assessment results that only include trustworthy or untrustworthy, with a larger (or coarser) granularity, while some trust models may output trust assessment results that are divided into multiple levels of trustworthiness, with a smaller (or finer) granularity.

[0005] For entities in specific application scenarios, trust assessment is currently generally performed on entities by manually selecting trust models based on human experience. However, the trust assessment results output by the manually selected trust models may have too large a granularity, resulting in low accuracy of the trust assessment results. Alternatively, the granularity may be too small, resulting in unnecessary increased computational costs.

[0006] Summary of the Invention

[0007] The present application provides a trust model evaluation method and device, which can evaluate the trust evaluation capability of a trust model according to the dimension of a first indicator for an entity in a specific application scenario, such as a first entity, and provide a decision-making basis for the selection of a trust model.

[0008] In a first aspect, the present application provides a trust model evaluation method, the method comprising: performing a trust evaluation on a first entity based on a trust model to obtain a trust evaluation result of the first entity, the trust evaluation result comprising at least one group, each group of trust evaluation results corresponding to a first indicator, the first indicator being used to indicate an evaluation dimension of the trust model; based on the trust evaluation result, evaluating the trust model to obtain an evaluation result of the trust model, the evaluation result of the trust model being used to indicate the trust evaluation capability of the trust model within the dimension of the first indicator.

[0009] Exemplarily, the method is applied to an electronic device. For example, the method is executed by the electronic device, or by a device (eg, a chip or a functional module) built into the electronic device.

[0010] This trust model evaluation method can evaluate the trust assessment capability of a trust model based on a first indicator for an entity in a specific application scenario, such as a first entity. By evaluating the trust assessment capability of a trust model, a more suitable trust model can be selected for the trust assessment of the entity in the application scenario, or a user can be assisted in determining whether a selected trust model is appropriate. Alternatively, a decision-making basis can be provided for trust model selection. For example, based on the evaluation results of the trust model, a user can determine whether the trust assessment granularity is appropriate or select a trust model with a more appropriate trust assessment granularity.

[0011] In one possible design, the trust evaluation of the first entity based on the trust model to obtain the trust evaluation result of the first entity includes: obtaining a first indicator, scenario information of the application scenario, and entity information of the first entity; generating an evaluation environment based on the first indicator, the scenario information of the application scenario, and the entity information of the first entity, wherein the evaluation environment indicates that the first entity operates in an environment of the application scenario; calling the trust model, performing a trust evaluation on the first entity based on the evaluation environment, and obtaining the trust evaluation result of the trust model on the first entity.

[0012] In this design, an evaluation environment is generated for a specific application scenario and the first entity within it. The trust model's trust assessment capabilities are then further evaluated based on the evaluation environment. This allows the evaluation environment to be flexibly adjusted based on the application scenario and the first entity, making this method more flexibly applicable to trust model evaluations in a wider range of application scenarios. In other words, this method's implementation framework can flexibly adjust to changes in the application scenario and the first entity, resulting in strong adaptability.

[0013] In one possible design, obtaining the first indicator, scenario information of the application scenario, and entity information of the first entity includes: obtaining the scenario information of the application scenario and entity information of the first entity; and obtaining the first indicator based on the scenario information of the application scenario and the entity information of the first entity.

[0014] Exemplarily, the method of obtaining the scene information of the application scenario and the entity information of the first entity may include: receiving the scene information of the application scenario and the entity information of the first entity input by the user, or obtaining the scene information of the application scenario and the entity information of the first entity from a specified data interface.

[0015] In some implementations, the first indicator used to generate the evaluation environment can be predefined, preconfigured, or configured. For example, matching evaluation indicators can be configured for the application scenario and the entity to obtain a mapping relationship between the evaluation indicator and the application scenario and the entity. Based on the scenario information of the application scenario and the entity information of the first entity, obtaining the first indicator can include: determining an evaluation indicator that matches the application scenario and the first entity based on this mapping relationship, such as a target evaluation indicator, and selecting at least one indicator from the target evaluation indicators as the first indicator.

[0016] In this implementation, the first indicator can be related to the application scenario and / or the first entity. It can be customized according to user design to select the first indicator for the current application environment and the first entity to evaluate the trust model. This can improve the accuracy of the trust model evaluation results, so that the trust model evaluation results reflect the performance of the trust model from a more accurate and effective dimension.

[0017] In some other implementations, the first indicator used to generate the evaluation environment may also be dynamically determined based on the scenario information and the entity information of the first entity. For example, obtaining the first indicator based on the scenario information of the application scenario and the entity information of the first entity may include: dynamically determining, through deep learning or machine learning, an evaluation indicator that matches the application scenario and the first entity based on the scenario information and the entity information of the first entity using a pre-trained neural network model, such as a target evaluation indicator, and selecting at least one indicator from the target evaluation indicators as the first indicator.

[0018] This design can customize and dynamically select the first indicator for the current application environment and the first entity to evaluate the trust model. It can improve the accuracy of the trust model evaluation results, enhance the adaptability of the trust model evaluation to different application scenarios, increase the flexibility of the evaluation, and make the trust model evaluation results reflect the performance of the trust model from a more accurate and effective dimension.

[0019] In another possible design, the first indicator used to generate the evaluation environment may also be one or more first indicators selected by a user from among the obtained first indicators based on scenario information of the application scenario and entity information of the first entity. For example, the user may perform an operation to select the first indicator, and the method may further include: in response to the user's selection operation on the first indicator, using the first indicator indicated by the selection operation as the first indicator used to generate the evaluation environment.

[0020] In this design, the first indicator obtained based on the scenario information of the application scenario and the entity information of the first entity can be called an alternative first indicator, and the first indicator selected by the user from the alternative first indicators can be called a target first indicator.

[0021] This design not only allows for customized selection of the first indicator for the current application environment and the first entity, but also allows users to adjust the first indicator based on their specific needs. For example, users can select a more meaningful or relevant first indicator based on their needs, further enhancing the value of the trust model's evaluation results to the user. Furthermore, by screening and selecting more relevant first indicators, the noise introduced by irrelevant or minor indicators can be reduced, further improving the accuracy of the evaluation results.

[0022] Alternatively, users can also select some specific indicators for evaluation based on the need to save evaluation time and resources to improve evaluation efficiency.

[0023] In one possible design, obtaining the first indicator based on the scenario information of the application scenario and the entity information of the first entity includes: fusing the scenario information of the application scenario and the entity information of the first entity to obtain a fusion feature; and obtaining the first indicator based on the fusion feature.

[0024] For example, the scene features of the scene information of the application scene and the entity features of the entity information of the first entity may be extracted, and the scene features and the entity features may be fused to obtain fused features.

[0025] In this design, the first indicator is obtained based on the fusion feature, which can further improve the effectiveness or accuracy of the first indicator and select a more suitable first indicator for the application scenario and the first entity to evaluate the trust model.

[0026] In one possible design, the evaluation environment is generated based on the first indicator, scenario information of the application scenario, and entity information of the first entity in the application scenario, including: for each of the first indicators, in turn, generating an evaluation environment corresponding to the first indicator based on the first indicator, scenario information of the application scenario, and entity information of the first entity in the application scenario.

[0027] Correspondingly, the calling of the trust model, performing a trust evaluation on the first entity based on the evaluation environment, and outputting the trust evaluation result of the first entity includes: performing a trust evaluation on the first entity based on the evaluation environment corresponding to the first indicator, and outputting the trust evaluation result of the first entity.

[0028] That is, in this design, each first indicator corresponds to an evaluation environment, and different first indicators correspond to different evaluation environments. This design can implement the process of generating an evaluation environment based on the first indicators and performing an evaluation based on the evaluation environment in a serial manner for multiple first indicators. For example, the trust assessment capability of a trust model can be evaluated for one first indicator first; after completing the trust model evaluation for one first indicator, the trust model evaluation for the next first indicator can be continued, until the trust model evaluation for all first indicators is completed.

[0029] In this design, for multiple first indicators, the process of generating an evaluation environment based on the first indicators and performing the evaluation based on the evaluation environment is implemented in a serial manner. Focusing on a single indicator (evaluating only one specific first indicator at a time) makes the evaluation process more concise and clear, and easier to understand and explain. Furthermore, for multiple first indicators, the serial implementation of the evaluation environment based on the first indicators and the evaluation based on the evaluation environment can also enhance the depth and accuracy of the evaluation. For example, it can focus resources and attention on a single indicator, avoiding the noise and interference that multiple indicators may bring, and more clearly understanding and analyzing the importance and role of each indicator.

[0030] In one possible design, the generated evaluation environment may include an initial evaluation environment and at least one other evaluation environment; the initial evaluation environment is generated based on the first indicator, scene information, and entity information of the first entity; the other evaluation environments can be obtained by adjusting the parameters in the initial evaluation environment.

[0031] For example, in this design, the method further includes: adjusting parameters of the evaluation environment to obtain at least one updated evaluation environment; invoking the trust model, performing a trust evaluation on the first entity based on the updated evaluation environment, and outputting a trust evaluation result for the first entity. The evaluation environment is the initial evaluation environment, and the updated evaluation environment is another evaluation environment.

[0032] In this design, the evaluation environment can be expanded to provide a richer environment for trust model evaluation and improve the accuracy of trust model evaluation. For example, the trust model can be evaluated based on multiple evaluation environments, such as the initial evaluation environment and other evaluation environments. The performance of the trust model can be comprehensively evaluated based on the evaluation results obtained in different evaluation environments.

[0033] In one possible design, the application scenarios include at least one of the following: network security scenarios, intelligent system scenarios, online platform scenarios, complex decision-making environment scenarios, Internet of Things scenarios, cloud computing scenarios, edge computing scenarios, network slicing and virtualized network scenarios, software-defined network scenarios, blockchain scenarios, and communication network scenarios; the first entity includes at least one of the following: hardware devices or modules, applications or software modules, and data of hardware and / or software interaction.

[0034] In one possible design, the evaluation result of the trust model is also used to indicate the update strategy of the trust model.

[0035] In this design, the evaluation results of the trust model can indicate the update strategy of the trust model, point out the improvement direction (dimension) of the trust model to developers or users, or provide users with more detailed model optimization suggestions, so that users can further optimize or adjust the trust model according to the evaluation results of the trust model to improve the performance of the trust model.

[0036] In one possible design, the method further includes: updating the trust model according to an evaluation result of the trust model.

[0037] In this design, the trust model is updated according to the evaluation results, which can improve the trust evaluation capability of the trust model.

[0038] In one possible design, the evaluation result of the trust model is a semantic trust evaluation report.

[0039] Exemplarily, the trust assessment result corresponding to the first indicator may be input into a large language model (LLM), the trust assessment result corresponding to the first indicator may be parsed by the LLM, and a semantic trust assessment report may be output as an assessment result of the trust model.

[0040] In this design, using a semantic trust evaluation report as the evaluation result of the trust model can enable users to better understand the trust evaluation capability of the trust model within the dimension of the first indicator, and more intuitively understand from which dimensions the trust model can be improved, and / or how the trust model can be improved.

[0041] In one possible design, the first indicator includes one or more of the following indicators: security of data, comprehensiveness of trust assessment results, availability of trust model, functionality of trust model, robustness of trust model, neutrality of trust assessment results, and interpretability of trust assessment results.

[0042] This application does not limit the specific type of the first indicator.

[0043] In a second aspect, the present application provides a trust model evaluation device that implements the method described in the first aspect. The function can be implemented through hardware or by hardware executing corresponding software. The hardware or software includes one or more units or modules corresponding to the functions of the method described in the first aspect, such as a trust evaluation unit, a model evaluation unit, etc.

[0044] Among them, the trust evaluation unit is used to perform a trust evaluation on the first entity based on the trust model to obtain a trust evaluation result of the first entity, and the trust evaluation result includes at least one group, each group of trust evaluation results corresponds to a first indicator, and the first indicator is used to indicate the evaluation dimension of the trust model.

[0045] The model evaluation unit is used to evaluate the trust model according to the trust evaluation result to obtain an evaluation result of the trust model, and the evaluation result of the trust model is used to indicate the trust evaluation capability of the trust model within the dimension of the first indicator.

[0046] In one possible design, the trust evaluation unit is specifically used to: obtain a first indicator, scenario information of an application scenario, and entity information of a first entity; generate an evaluation environment based on the first indicator, scenario information of the application scenario, and entity information of the first entity, where the evaluation environment indicates that the first entity runs in an environment of the application scenario; call a trust model, perform a trust evaluation on the first entity based on the evaluation environment, and obtain a trust evaluation result of the trust model on the first entity.

[0047] In one possible design, the trust assessment unit is specifically used to: obtain scenario information of the application scenario and entity information of the first entity; and obtain a first indicator based on the scenario information of the application scenario and the entity information of the first entity.

[0048] In one possible design, the first indicator used to generate the evaluation environment can be predefined, preconfigured, or configured. For example, matching evaluation indicators can be configured for the application scenario and the entity, resulting in a mapping relationship between the evaluation indicators, the application scenario, and the entity. The trust evaluation unit is specifically configured to: determine, based on this mapping relationship, an evaluation indicator that matches the application scenario and the first entity, such as a target evaluation indicator, and select at least one indicator from the target evaluation indicators as the first indicator.

[0049] In another possible design, the first indicator used to generate the evaluation environment can also be dynamically determined based on the scenario information and the entity information of the first entity. For example, the trust evaluation unit is further configured to dynamically determine, based on the scenario information and the entity information of the first entity, an evaluation indicator that matches the application scenario and the first entity, such as a target evaluation indicator, using a pre-trained neural network model through deep learning or machine learning. At least one indicator from the target evaluation indicators is selected as the first indicator.

[0050] In another possible design, the first indicator used to generate the evaluation environment may also be one or more first indicators selected by the user from among the first indicators obtained after obtaining the first indicator based on scenario information of the application scenario and entity information of the first entity. For example, the trust assessment unit is further configured to, in response to a user selecting a first indicator, use the first indicator indicated by the selection as the first indicator used to generate the evaluation environment.

[0051] In a possible design, the trust assessment unit is specifically configured to: fuse the scenario information of the application scenario and the entity information of the first entity to obtain a fusion feature; and obtain the first indicator based on the fusion feature.

[0052] In one possible design, the trust evaluation unit is specifically used to generate an evaluation environment corresponding to the first indicator for each of the first indicators in turn, based on the first indicator, scenario information of the application scenario, and entity information of the first entity in the application scenario; perform a trust evaluation on the first entity based on the evaluation environment corresponding to the first indicator, and output a trust evaluation result of the first entity.

[0053] That is, in this design, each first indicator corresponds to an evaluation environment, and different first indicators correspond to different evaluation environments.

[0054] In one possible design, the generated evaluation environment may include an initial evaluation environment and at least one other evaluation environment; the initial evaluation environment is generated based on the first indicator, scenario information, and entity information of the first entity; the other evaluation environment may be obtained by adjusting parameters in the initial evaluation environment. For example, the trust evaluation unit is further configured to adjust parameters in the evaluation environment to obtain at least one updated evaluation environment; invoke the trust model, perform a trust evaluation on the first entity based on the updated evaluation environment, and output a trust evaluation result for the first entity. The evaluation environment is the initial evaluation environment, and the updated evaluation environment is the other evaluation environment.

[0055] In one possible design, the application scenarios include at least one of the following: network security scenarios, intelligent system scenarios, online platform scenarios, complex decision-making environment scenarios, Internet of Things scenarios, cloud computing scenarios, edge computing scenarios, network slicing and virtualized network scenarios, software-defined network scenarios, blockchain scenarios, and communication network scenarios; the first entity includes at least one of the following: hardware devices or modules, applications or software modules, and data of hardware and / or software interaction.

[0056] In one possible design, the evaluation result of the trust model is also used to indicate the update strategy of the trust model.

[0057] In one possible design, the apparatus further includes: an updating unit, configured to update the trust model according to an evaluation result of the trust model.

[0058] In one possible design, the evaluation result of the trust model is a semantic trust evaluation report.

[0059] In one possible design, the first indicator includes one or more of the following indicators: security of data, comprehensiveness of trust assessment results, availability of trust model, functionality of trust model, robustness of trust model, neutrality of trust assessment results, and interpretability of trust assessment results.

[0060] In a third aspect, the present application further provides a trust model evaluation device, comprising: a processor configured to execute computer instructions stored in a memory, wherein when the computer instructions are executed, the device performs the method described in the first aspect or any possible design of the first aspect. Alternatively, the processor is configured to perform the method described in the first aspect or any possible design of the first aspect.

[0061] In a fourth aspect, the present application also provides a trust model evaluation device, comprising: a processor and an interface circuit, the processor being configured to communicate with other devices through the interface circuit and execute the method described in the first aspect or any possible design of the first aspect.

[0062] The trust model evaluation device described in the second to fourth aspects above may be an electronic device, or a device (eg, a chip) built into an electronic device.

[0063] In a fifth aspect, the present application further provides a computer-readable storage medium comprising: computer software instructions (or instructions); when the computer software instructions are executed, the method described in the first aspect or any possible design of the first aspect is implemented. For example, when the computer software instructions are executed in an electronic device or a device (e.g., a chip) built into the electronic device, the electronic device executes the method described in the first aspect or any possible design of the first aspect.

[0064] It can be understood that the beneficial effects that can be achieved by the second to fifth aspects provided above can refer to the beneficial effects in the first aspect and any possible design thereof, and will not be repeated here.

[0065] In a sixth aspect, the present application also provides a trust model evaluation device, comprising: a transceiver unit and a processing unit. The transceiver unit can be used to send and receive information, or to communicate with other network elements (such as terminal devices or network devices, or other electronic devices or devices). The processing unit can be used to process data. The device can implement the method described in the first aspect and any possible design thereof through the transceiver unit and the processing unit.

[0066] In a seventh aspect, the present application also provides a computer program product, which, when executed, can implement the method described in the first aspect and any possible design thereof.

[0067] In an eighth aspect, the present application also provides a chip system, which includes one or more interface circuits and one or more processors; the interface circuits and the processors are interconnected through lines; the processor receives and executes computer instructions from the memory of the electronic device through the interface circuit to implement the method described in the first aspect and any possible design thereof.

[0068] In a ninth aspect, the present application also provides an artificial intelligence model, which has the function of implementing the method described in the first aspect and any possible design thereof.

[0069] Optionally, the artificial intelligence model includes one or more models. When the artificial intelligence model includes multiple models, the multiple models implement different functions in the method described in the first aspect and any possible design thereof.

[0070] In a tenth aspect, the present application also provides a communication system, which includes a first entity and a second entity, and the second entity interacts with the first entity to implement the method described in the first aspect and any possible design thereof.

[0071] It can be understood that the beneficial effects that can be achieved by the sixth to tenth aspects provided above can refer to the beneficial effects described in the first to fifth aspects, etc., and will not be repeated here.

[0072] It should be understood that the description of technical features, technical solutions, beneficial effects or similar language in this application does not imply that all features and advantages can be realized in any single embodiment. On the contrary, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution or beneficial effect is included in at least one embodiment. Therefore, the description of a technical feature, technical solution or beneficial effect in this specification does not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions and beneficial effects described in the present embodiment can also be combined in any appropriate manner. Those skilled in the art will understand that the embodiment can be implemented without one or more specific technical features, technical solutions or beneficial effects of a specific embodiment. In other embodiments, additional technical features and beneficial effects can also be identified in specific embodiments that do not embody all embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] FIG1 shows a schematic diagram of the composition of an electronic device provided in an embodiment of the present application;

[0074] FIG2 shows a schematic diagram of a flow chart of a trust model evaluation method provided in an embodiment of the present application;

[0075] FIG3 shows a schematic diagram of the principles of a trust model evaluation system provided by an embodiment of the present application;

[0076] FIG4 shows another implementation flow diagram of the trust model evaluation method provided in an embodiment of the present application;

[0077] FIG5 shows a schematic diagram showing the principle of another trust model evaluation system provided by an embodiment of the present application;

[0078] FIG6 shows another implementation flow diagram of the trust model evaluation method provided in an embodiment of the present application;

[0079] FIG7 shows another implementation flow diagram of the trust model evaluation method provided in an embodiment of the present application;

[0080] FIG8 shows another implementation flow diagram of the trust model evaluation method provided in an embodiment of the present application;

[0081] FIG9 shows another implementation flow diagram of the trust model evaluation method provided in an embodiment of the present application;

[0082] FIG10 shows a schematic diagram of the composition of a trust model evaluation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0083] Trust assessment generally refers to the evaluation of the trustworthiness of entities in application scenarios. By performing trust assessment on entities, we can understand whether the entity is trustworthy, whether the entity can interact, or whether the entity's data is available.

[0084] For example, in some communication-related application scenarios, an entity can refer to an interactive object or communication node in a communication network, such as a network device or terminal device. Based on the trust evaluation results of a communication node in the communication network, the security of the communication node can be determined, for example, whether the data on the communication node is trustworthy, thereby testing the security and reliability of the communication network.

[0085] A trust assessment method may include: performing a trust assessment on an entity using a trust assessment model, and outputting a trust assessment result for the entity. The trust assessment model may also be referred to as a trust model, and the trust assessment result may refer to the trustworthiness of the entity. The trustworthiness may also be referred to as a degree of trust, credibility, or dependability, and the description of the trustworthiness is not limited herein.

[0086] Different trust models may output trust assessment results at different granularities. For example, in some trust models, the trustworthiness of an entity is defined as two levels: trusted or untrustworthy. The trust assessment results output by the trust model for an entity are either of these two levels, such as trusted or untrustworthy. These trust models have a larger (or coarser) granularity in trust assessment.

[0087] Some trust models may output trust assessment results based on multiple levels of trust, or define the trustworthiness of an entity as multiple tiers, such as high, medium, and low. The trust assessment results for an entity output by the trust model are one of these tiers. The granularity of the trust assessment in such trust models is related to the number of tiers: the more tiers, the finer the granularity.

[0088] Currently, trust assessments are typically performed on entities in specific application scenarios by manually selecting trust models based on experience. However, the trust assessment results output by these manually selected trust models may be too granular, resulting in inaccurate trust assessments, or too granular, resulting in unnecessary computational costs.

[0089] To this end, an embodiment of the present application provides a trust model evaluation method, which can evaluate the trust evaluation capability of the trust model according to the dimension of the first indicator for entities in a specific application scenario, such as the first entity, and provide a decision-making basis for the selection of the trust model.

[0090] For example, it can assist in selecting a trust model with a more appropriate trust assessment granularity for specific application scenarios and entities, conduct trust assessment on entities in application scenarios, improve the accuracy of trust assessment results, and reduce unnecessary computational cost waste.

[0091] Exemplarily, taking the trust evaluation of the first entity in the application scenario as an example, the method may include: performing a trust evaluation on the first entity based on the trust model to obtain a trust evaluation result of the first entity, the trust evaluation result including at least one group, each group of trust evaluation results corresponding to a first indicator, the first indicator being used to indicate the evaluation dimension of the trust model; based on the trust evaluation result, evaluating the trust model to obtain an evaluation result of the trust model, the evaluation result of the trust model being used to indicate the trust evaluation capability of the trust model within the dimension of the first indicator.

[0092] Exemplarily, the trust model evaluation method provided in the embodiments of the present application may be executed by an electronic device, or by a device built into an electronic device (eg, a chip or one or more functional modules in the electronic device).

[0093] In some embodiments, the electronic device may be an entity in an application scenario or an electronic device related to the entity. For example, in an application scenario, a first entity interacts with a second entity. When evaluating the trust assessment capability of a trust model for the application scenario and the first entity, the electronic device may be the second entity itself (the second entity is an electronic device), or the electronic device may be a device that carries the second entity or an electronic device included in the second entity, or other electronic devices that have data interaction or connection with the second entity.

[0094] In some other embodiments, the electronic device may be a device outside of the application scenario. For example, the electronic device may be a computer or a server, or may be other devices with data processing capabilities, such as a mobile phone, a computer, a wireless terminal, etc.

[0095] It should also be understood that the electronic device described above can be a single electronic device or can be composed of multiple electronic devices. For example, taking a server as an example, the server can be a single server or a server cluster composed of multiple servers. In some embodiments, the server cluster can also be a distributed cluster.

[0096] This application does not limit the implementation method or product form of the above-mentioned electronic device, nor does it limit the execution entity of the trust model evaluation method.

[0097] For example, Figure 1 shows a schematic diagram of the components of an electronic device provided in an embodiment of the present application. In one possible implementation, the trust model evaluation method provided in an embodiment of the present application can be applied to the electronic device shown in Figure 1. As shown in Figure 1, the electronic device may include: at least one processor 11, a memory 12, a communication interface 13, and a bus 14.

[0098] The processor 11 is the control center of the electronic device and can be a single processor or a collective term for multiple processing elements. For example, the processor 11 can be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application, such as one or more microprocessors (digital signal processors, DSPs) or one or more field programmable gate arrays (FPGAs).

[0099] The processor 11 can execute various functions of the electronic device by running or executing software programs stored in the memory 12 and calling data stored in the memory 12. For example, the steps included in the trust model evaluation method provided in the embodiment of the present application can be executed.

[0100] In a specific implementation, as an embodiment, the processor 11 may include one or more CPUs, such as CPU0 and CPU1 shown in FIG. 1 .

[0101] In a specific implementation, as an embodiment, an electronic device may include multiple processors, such as processor 11 and processor 15 shown in FIG1 . Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0102] The memory 12 can store a software program for the method steps performed by the electronic device and be controlled by the processor 11 for execution. The memory 12 can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0103] The memory 12 may exist independently and be connected to the processor 11 via the bus 14. Alternatively, the memory 12 may be integrated with the processor 11, which is not limited here.

[0104] Communication interface 13, using any transceiver or other device, is used to communicate with other devices or communication networks. Communication interface 13 can be an Ethernet interface, a radio access network (RAN) interface, a wireless local area network (WLAN) interface, etc. Communication interface 13 can include a receiving unit to implement a receiving function and a sending unit to implement a sending function.

[0105] Bus 14 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. This bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, FIG1 shows only one thick line, but this does not imply that there is only one bus or only one type of bus.

[0106] Although the bus 14 is used in FIG. 1 , it is understandable that the bus can be replaced by other forms of connection relationships and is not limited to the bus itself.

[0107] It should be understood that what is shown in FIG1 is merely an exemplary illustration. In the embodiment of the present application, the electronic device may also include more or fewer components than those shown in FIG1 , which is not limited here.

[0108] The following is an exemplary description of the trust model evaluation method provided in the embodiments of the present application.

[0109] It should be noted that the processing described below as being performed by a single execution subject can also be divided into processing performed by multiple execution subjects, and these execution subjects can be logically and / or physically separated. For example, the functions involved in the trust model evaluation method can be divided into processing performed by at least one functional module. In addition, in the description of the embodiments of the present application, words such as "first" and "second" are only used to distinguish the description and are not used to specifically limit a certain feature, that is, the first or second can include more content, rather than being limited to a specific concept. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previous and subsequent associated objects are in an "or" relationship. At least one refers to one or more; multiple refers to two or more. The embodiments of the present application may only execute fewer steps than all the steps, or execute more steps, without limitation. "At least one of the following" or similar expressions is used to indicate any combination of the listed items; for example, at least one of A, B and / or C may mean the following situations: A exists alone, B exists alone, C exists alone, A and B exist at the same time, B and C exist at the same time, A and C exist at the same time, and A, B and C exist at the same time, where A, B, C may be single or multiple.

[0110] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the art of this application. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0111] As shown above, in the trust model evaluation method provided in the present application, a trust evaluation can be performed on the first entity based on the trust model to obtain a trust evaluation result of the first entity, and the trust evaluation result includes at least one group, each group of trust evaluation results corresponds to a first indicator, and the first indicator is used to indicate the evaluation dimension of the trust model; according to the trust evaluation result, the trust model is evaluated to obtain an evaluation result of the trust model, and the evaluation result of the trust model is used to indicate the trust evaluation capability of the trust model within the dimension of the first indicator.

[0112] In some implementations, the trust evaluation result of the trust model on the first entity may be obtained by a user evaluating the first entity using the trust model, or may be a trust evaluation result obtained from other existing data sources.

[0113] In other implementations, an evaluation environment may be constructed first for specific application scenarios and entities, and a trust evaluation result of the trust model on the first entity may be obtained based on the evaluation environment.

[0114] For example, FIG2 shows a flow chart of a trust model evaluation method provided in an embodiment of the present application. As shown in FIG2 , the trust model evaluation method may include S201-S203. Exemplarily, S201-S203 may be executed by an electronic device, or by a device built into an electronic device (e.g., a chip or one or more functional modules in an electronic device). The electronic device may refer to the electronic device described in the aforementioned embodiment.

[0115] S201. Generate an evaluation environment based on a first indicator, scenario information of an application scenario, and entity information of a first entity in the application scenario.

[0116] The evaluation environment may indicate an environment in which the first entity runs in an application scenario.

[0117] For example, in embodiments of the present application, application scenarios may include network security scenarios, intelligent system scenarios, online platform scenarios, and complex decision-making environment scenarios. For any of the aforementioned application scenarios, the first entity may be any real or virtual object in the application scenario, such as a hardware device or module, an application or software module, or data generated by hardware and / or software interactions.

[0118] For example, in network security scenarios, with the increase in network attacks and data leakage incidents, ensuring the trust of network interactions and data transmission is becoming increasingly important. By evaluating the reliability of network nodes or data, it can help identify potential security threats and ensure the integrity and privacy of data. When the trust model evaluation method provided in the embodiment of the present application is applied to a network security scenario, the first entity can be any object in the network (such as a communication network or other network), such as a network device, a hardware or software module running in a network device, data generated or interacted by a network device, etc.

[0119] For another example, the intelligent system may include an autonomous driving system, an intelligent medical decision-making system, etc., which are not limited here. In an autonomous driving system, the vehicle needs to evaluate the trust of other entities in the surrounding environment (such as pedestrians, other vehicles or road signs, etc.). The trust model can provide a trust rating for the vehicle based on the data and context of other entities to improve the safety of autonomous driving. When the trust model evaluation method provided in the embodiment of the present application is applied to the scenario of an autonomous driving system, the first entity may be a pedestrian, a hardware or software module in a vehicle, other vehicles or road signs, or data interacted or generated by these entities, etc. In an intelligent medical decision-making system, trust evaluation of various medical devices, drugs and treatment methods is required to improve safety. When the trust model evaluation method provided in the embodiment of the present application is applied to the scenario of an intelligent medical decision-making system, the first entity may be a medical device, a drug or treatment method, etc.

[0120] For another example, online platforms may include e-commerce platforms, social networking platforms, etc., which are not limited here. In the e-commerce platform scenario, buyers need to evaluate the credibility of stores or products when shopping. The trust model can provide users with more accurate and detailed trust evaluations to enhance their shopping experience. When the trust model evaluation method provided in the embodiment of the present application is applied to the e-commerce platform scenario, the first entity may be a store or a product. In the social networking platform scenario, when a user interacts with other unknown users, the user wants to know the credibility of other users. The trust model can provide them with detailed trust evaluations based on the historical behavior and feedback of other users, helping users to better judge which other users to interact with. When the trust model evaluation method provided in the embodiment of the present application is applied to the social networking platform scenario, the first entity may be a user account.

[0121] For example, complex decision-making environments can include finance, insurance, and other fields. In finance and insurance, decisions often involve capital flows and risks, and decision-makers need to accurately assess the reliability of various investments or strategies. The trust model can flexibly adapt to different market conditions, dynamically evaluate various data and information, and provide decision-makers with clear and specific trust ratings. When the trust model evaluation method provided in the embodiments of the present application is applied to complex decision-making environment scenarios, the first entity can be the data and information that needs to be evaluated.

[0122] It should be understood that the application scenarios described above are all exemplary descriptions, and the trust model evaluation method can also be applied to more application scenarios with trust evaluation requirements. For example, the trust model evaluation method can be applied to the Internet of Things scenario, where the first entity can be a device or sensor, etc. Alternatively, the trust model evaluation method can be applied to a cloud computing scenario, where the first entity can be a computing device or a storage device, etc. Alternatively, the trust model evaluation method can be applied to an edge computing scenario, where the first entity can be an edge node or a central node. Alternatively, the trust model evaluation method can be applied to network slicing and virtualized network scenarios, software-defined network scenarios, blockchain scenarios, etc. This application will not list them one by one, but this application does not limit the application scenarios to which the trust model evaluation method can be applied.

[0123] In S201, the scenario information of the application scenario can be used to describe the content of the application scenario. For example, the scenario information may include which entities the application scenario includes, the connection or interaction relationship between the entities, etc. The first entity may be any one or more entities in the application scenario. The entity information of the first entity can be used to describe the first entity. For example, the entity information of the first entity may include static attribute information of the first entity, and / or dynamic behavior information. The static attribute information of the first entity may include attribute information of the first entity itself. The dynamic behavior information of the first entity may include relevant information of the operation or operation of the first entity, interaction information with other entities, etc.

[0124] For example, in an application scenario such as a communication network, such as a cellular network or an Internet Protocol (IP) network, the first entity may be a network element in the communication network, such as an access network device (e.g., a base station), a terminal device, a core network device, etc. The scenario information may include the network elements included in the communication network, the connection relationships and interaction relationships between the network elements, etc. The entity information of the first entity may include information such as the packet loss rate of the first network element and whether the packet is forwarded according to the path.

[0125] It is understandable that, before S201 , the method may further include a step of acquiring scene information of the application scene and entity information of the first entity in the application scene.

[0126] In some possible implementations, for a specific application scenario and a first entity, scenario information of the application scenario and entity information of the first entity can be obtained from a specified data source and / or interface. For example, for an autonomous driving system, scenario information of the autonomous driving system and entity information of a first entity (such as a vehicle) in the autonomous driving system can be obtained from an application programming interface (API) provided by the autonomous driving system. For another example, for a cellular network, scenario information of the cellular network and entity information of a first entity (such as a first network element) in the cellular network can be obtained from the southbound / northbound interface, serial bus interface (SBI), etc. of the cellular network.

[0127] In some other possible implementations, the scene information of the application scene and the entity information of the first entity can also be input by the user. For example, a human-computer interaction interface can be provided, and the user can input the scene information of the application scene and the entity information of the first entity through the human-computer interaction interface.

[0128] After acquiring the scenario information of the application scenario and the entity information of the first entity in the application scenario, S201 may be executed. In S201, the first indicator may be understood as a dimension for evaluating the trust model. The first indicator may include at least one, that is, the trust model may be evaluated according to one or more dimensions.

[0129] For example, in one possible design, the first indicator may include one or more of the following indicators: data security, comprehensiveness of the trust assessment results, usability of the trust model, functionality of the trust model, robustness of the trust model, neutrality of the trust assessment results, and explainability of the trust assessment results. These indicators are referred to as security, comprehensiveness, usability, functionality, robustness, neutrality, and explainability, respectively.

[0130] Security can be used to assess whether the trust model ensures data security when processing data and making predictions, preventing data leakage or malicious exploitation. Comprehensiveness can be used to assess whether the trust model covers relevant factors and variables to provide the most comprehensive prediction and analysis possible. Usability can be used to assess whether the trust model can be effectively called upon and used when needed, and whether it maintains stable and reliable performance in different environments. Functionality can be used to assess whether the trust model can effectively implement its designed functions, including data processing, feature extraction, prediction, and analysis. Robustness can be used to assess whether the trust model maintains stable performance in the face of abnormal or noisy data, avoiding serious deviations or errors due to data changes. Neutrality can be used to assess whether the trust model maintains an objective and neutral stance when making predictions and analyses, unaffected by subjective factors. Explainability can be used to assess whether the trust model clearly explains its prediction results and analysis process, allowing users to understand the model's decision-making basis and reasoning process.

[0131] In S201, an evaluation environment can be generated based on the first indicator, the scenario information of the application scenario, and the entity information of the first entity in the application scenario. The application scenario can be restored in the evaluation environment. In the embodiment of the present application, the evaluation environment can be understood as a test environment, in which the performance of the trust model within the dimension of each first indicator can be tested, or the performance of the trust model in the dimension corresponding to each first indicator, such as the trust evaluation capability of the trust model within the dimension of the first indicator.

[0132] Exemplarily, the evaluation environment may include an environment module and agent modules. The environment module may provide environmental information such as scenario information of the application scenario and entity information of the first entity. The agent module may invoke a trust model to be evaluated, evaluate the trustworthiness of the first entity based on the environment information, and output a trust evaluation result for the first entity. For example, S202 may be executed.

[0133] S202: Call the trust model, perform a trust evaluation on the first entity based on the evaluation environment, and output a trust evaluation result of the first entity. The first indicator includes at least one indicator, and the trust evaluation result of the first entity includes a trust evaluation result corresponding to each first indicator.

[0134] Alternatively, S202 may also be described as: calling the trust model, performing a trust evaluation on the first entity based on the evaluation environment, and obtaining a trust evaluation result of the trust model on the first entity.

[0135] As described in the above embodiments, different trust models may output trust evaluation results at different granularities. In S202, each or any granularity level of the trust model may be called to output the trust evaluation result of the first entity to evaluate the trust evaluation capability of the trust model at that granularity level.

[0136] For example, the trust model described in S202 may be any one of the following granularity levels: a binary level, a coarse-grained level, and a fine-grained level.

[0137] Among them, the binary level trust model can be used to evaluate whether an entity can be trusted. Its trust evaluation results have two states: trustworthy or untrustworthy. For example, the entity can be marked as 1 (trust) or 0 (untrust). The decision is clear, relatively simple, without ambiguity and easy to explain. It does not require detailed measurement or calculation of trust. The computing resources and time required in the evaluation process are relatively small. It can be used in scenarios that require quick decision-making, such as binary authentication systems and rapid screening.

[0138] The coarse-grained level trust model is more granular than the binary level trust model, or in other words, the trust assessment results of the coarse-grained level trust model have more levels than the trust assessment results of the binary level trust model. The coarse-grained level trust model defines several preset classification levels for trust, such as "high trust," "medium trust," and "low trust," providing greater flexibility than the binary level trust model. The coarse-grained level trust model can be applied to certain scenarios where it is necessary to understand the approximate trust level of an entity without knowing its specific trust value. For example, in some recommendation systems, users may only care about whether a recommendation should be "highly trusted," "medium trust," or "lowly trusted" without knowing the specific trust level or trust score.

[0139] The fine-grained level trust model is more granular than the coarse-grained level trust model and can capture more detailed trust information. For example, it can use continuous numerical values ​​or more categorical levels to represent trust. The fine-grained level trust model is suitable for scenarios that require highly accurate and detailed trust assessments, such as complex decision support systems, security assessments, and detailed user feedback systems.

[0140] For example, in S202, environmental information such as scenario information of the application scenario and entity information of the first entity can be input into the trust model. The trust model then performs a trust assessment on the first entity based on the scenario information of the application scenario and the entity information of the first entity, and outputs a trust assessment result for the first entity. The trust assessment result for the first entity is related to the first indicator and can include a trust assessment result corresponding to each first indicator. The trust assessment results corresponding to a first indicator can be referred to as a group, i.e., each group of trust assessment results corresponds to a first indicator, and the first indicators corresponding to different groups of trust assessment results can be different.

[0141] For example, if the first indicator includes robustness, for robustness, some abnormal data or noise data can be added to the input data, and multiple trust evaluations can be performed on the first entity to obtain multiple trust evaluation results (i.e., trust evaluation results of the first entity corresponding to the robustness). The aforementioned multiple trust evaluation results can reflect the robustness of the trust model and can indicate that the trust model maintains stable performance in the face of abnormal or noisy data.

[0142] For another example, if the first metric includes explainability, the trust model's explainability can be determined by analyzing the trust assessment results of the first entity to see if they meet the assessment requirements. Any trust assessment result can be used as the trust assessment result for the first entity corresponding to the explainability.

[0143] It should be understood that for different first indicators, the corresponding trust assessment results of the first entity may be the same or different. For example, the trust assessment results of the first entity corresponding to functionality and interpretability may be the same. Alternatively, the trust assessment result of the first entity corresponding to interpretability may be a trust assessment result output once, while the trust assessment result of the first entity corresponding to robustness may be a trust assessment result output multiple times, etc.

[0144] The process described in S201-S202 above can be understood as a process of performing a trust assessment on the first entity based on the trust model to obtain a trust assessment result for the first entity. For example, performing a trust assessment on the first entity based on the trust model to obtain a trust assessment result for the first entity includes: obtaining a first indicator, scenario information of the application scenario, and entity information of the first entity; generating an assessment environment based on the first indicator, the scenario information of the application scenario, and the entity information of the first entity, where the assessment environment indicates the environment in which the first entity operates in the application scenario; and invoking the trust model to perform a trust assessment on the first entity based on the assessment environment to obtain a trust assessment result of the trust model on the first entity.

[0145] The trust evaluation result includes trust evaluation results corresponding to at least one first indicator of the trust model, and the first indicator is used to indicate an evaluation dimension of the trust model.

[0146] After obtaining the trust evaluation result corresponding to the first indicator, S203 may be executed to evaluate the trust evaluation capability of the trust model.

[0147] S203. Output / determine an evaluation result of the trust model according to the trust evaluation result corresponding to the first indicator. The evaluation result of the trust model is used to indicate the trust evaluation capability of the trust model within the dimension of the first indicator.

[0148] Alternatively, S203 may also be described as: evaluating the trust model according to the trust evaluation result to obtain an evaluation result of the trust model.

[0149] For example, for each first indicator, the performance of the trust model within the dimension of the first indicator can be analyzed based on the trust assessment result corresponding to the first indicator, or the performance of the trust model on the first indicator. This performance can be referred to as the trust assessment capability of the trust model. The analysis result can be referred to as the evaluation result of the trust model, which can indicate the trust assessment capability of the trust model within the dimension of the first indicator.

[0150] For example, taking the first indicator as interpretability, that is, the trust assessment result of the first entity includes the trust assessment result corresponding to interpretability as an example, in S203, the performance of the trust model in the dimension of interpretability can be analyzed and evaluated based on the trust assessment result corresponding to interpretability, and the evaluation result of the trust model on interpretability can be obtained. The evaluation result can be used to indicate the trust assessment ability of the trust model within the dimension of interpretability, such as: whether the trust model can clearly explain its prediction results and analysis process, whether the granularity of the trust assessment result output by the trust model is appropriate, etc.

[0151] Optionally, deep learning or machine learning can be used to output the evaluation results of the trust model regarding interpretability based on the trust assessment results corresponding to the interpretability. For example, the characteristics of the trust assessment results (such as granularity, user feedback, information entropy, etc.) can be used as input, and the annotation information of the trust assessment results, such as the score (the score is used to indicate the appropriateness of the trust assessment granularity) or the label (such as appropriate or inappropriate) can be used as output to pre-train a neural network model. The neural network model has the function of outputting whether the trust assessment granularity is appropriate or the degree of suitability (such as a score) based on the characteristics of the input trust assessment results. The trust assessment results corresponding to the aforementioned interpretability are input into the neural network model, and the neural network model can output the evaluation results of the trust model regarding interpretability, such as whether the trust assessment granularity is appropriate.

[0152] Similarly, for other first indicators, the above-described step of outputting the evaluation result of the trust model based on the trust evaluation result corresponding to the first indicator can also be implemented using a neural network model using deep learning or machine learning. Examples are not given here one by one. It should be understood that for different first indicators, the above-described step of outputting the evaluation result of the trust model based on the trust evaluation result corresponding to the first indicator can be implemented using the same or different neural network models.

[0153] As described above, the trust model evaluation method provided in the embodiment of the present application can evaluate the trust evaluation capability of the trust model according to the dimension of the first indicator for an entity in a specific application scenario, such as a first entity. By evaluating the trust evaluation capability of the trust model, a more suitable trust model can be selected for the trust evaluation of the entity in the application scenario, or the user can be assisted in judging whether the selected trust model is appropriate, or in other words, a decision basis can be provided for the selection of the trust model. For example, the user can judge whether the trust evaluation granularity is appropriate based on the evaluation results of the trust model, or select a trust model with a more appropriate trust evaluation granularity.

[0154] For example, the binary-level trust model, coarse-grained-level trust model, and fine-grained-level trust model mentioned above offer a coarser granularity for trust assessment, a simpler assessment method, and consumes fewer computing resources. However, the binary-level trust model lacks consideration of intermediate states or continuous levels of trust. Its stark black-and-white nature makes it easy to overlook subtle distinctions, potentially leading to misjudgments. The binary-level trust model may overlook subtle distinctions, evaluating objects of different trust levels as either "good" or "bad," and making it impossible to further compare "good" models. The binary-level trust model also offers a relatively rough handling of edge cases.

[0155] The fine-grained level trust model can provide in-depth and detailed trust assessment, but it is relatively complex and may consume relatively large computing resources.

[0156] Compared to the binary and fine-grained level trust models, the coarse-grained level trust model provides a tool for applications that require a certain degree of classification or grading. It is more flexible than the binary level trust model but less complex than the fine-grained level trust model. The coarse-grained level trust model strikes a balance between simplicity and detailed measurement, providing users with a tool that is neither overly simplistic nor overly complex. However, the coarse-grained level trust model may overlook subtle distinctions, potentially categorizing objects of different trust levels into the same grading category, and may also inaccurately handle edge cases.

[0157] When conducting trust evaluation for entities in specific application scenarios, some application scenarios may be more suitable for quick judgment using a binary level trust model, some application scenarios may be more suitable for detailed evaluation using a fine-grained level trust model, and some application scenarios may be more suitable for relatively coarse-grained evaluation using a coarse-grained level trust model, without wasting too much computing resources. For users, when manually selecting a trust model to conduct trust evaluation on an entity, there may be problems such as the trust evaluation result output by the selected trust model being too granular, resulting in low accuracy of the trust evaluation result, or the granularity being too small, resulting in unnecessary increase in computing costs. The trust model evaluation method provided by the embodiment of the present application evaluates the trust evaluation capability of the trust model, which can assist or help users select a more suitable trust model for the trust evaluation of the entity in the application scenario. For example, the user can judge whether the trust evaluation granularity is appropriate based on the evaluation result of the trust model, or select a trust model with a more appropriate trust evaluation granularity.

[0158] Furthermore, this trust model evaluation method generates an evaluation environment for a specific application scenario and a first entity within that scenario, and then further evaluates the trust model's trust evaluation capabilities based on that evaluation environment. This allows the evaluation environment to be flexibly adjusted based on the application scenario and the first entity, making the method more flexibly applicable to trust model evaluations in a wider range of application scenarios. In other words, the implementation framework of this method can flexibly adjust to changes in the application scenario and the first entity, resulting in strong adaptability.

[0159] It should also be understood that in the embodiments of the present application, the richer the categories of the first indicators, the more comprehensive the results of evaluating the trust assessment capabilities of the trust model. Outputting the evaluation results of the trust model based on the trust assessment results corresponding to different first indicators can enable the evaluation results of the trust model to reflect the trust assessment capabilities of the trust model in different first indicator dimensions, and to show or describe the performance of the trust model for users in different first indicator dimensions, or to show more comprehensive performance of the trust model. For example, the embodiments of the present application can provide developers and users of the trust model with feedback on different first indicator dimensions, so that they can more clearly understand the performance of the trust model in different dimensions.

[0160] The trust model examples described in the above embodiments are divided from the perspective of trust evaluation granularity. Optionally, the trust model can also be classified from the perspective of function, and the trust model corresponding to each function can be further divided according to the evaluation granularity. For different application scenarios, the trust model may also be the same or different. For example, in a communication network, for point-to-point file sharing and communication environments, considering the characteristics of direct interaction between users and emphasizing the behavior evaluation of peers, a point-to-point (P2P) trust model can be adopted. For evaluating traditional computer network environments, the focus is on the trustworthiness of devices and data, and a network trust model can be adopted. For mobile Ad hoc wireless networks, to deal with dynamic, decentralized network environments, an Ad hoc trust model can be adopted. For wireless sensor networks, emphasizing the issues of resource constraints and energy efficiency, a wireless sensor network (WSN) trust model can be adopted.

[0161] In one possible design, before executing S201 above, the scene information of the application scene and / or the entity information of the first entity in the application scene may be preprocessed. For example, noise and irregularities in the scene information and entity information may be removed, such as by removing abnormal data or filling in missing data. The specific method of preprocessing is not limited herein.

[0162] In this design, by preprocessing the scenario information of the application scenario and / or the entity information of the first entity in the application scenario, the accuracy of the scenario information and the entity information can be improved, thereby generating a better or more stable evaluation environment to improve the accuracy of the trust model evaluation.

[0163] In one possible design, the step of generating an evaluation environment based on the first indicator, the scenario information of the application scenario, and the entity information of the first entity in the application scenario as described in S201 above may include: extracting scenario features of the scenario information of the application scenario and entity features of the entity information of the first entity; generating an evaluation environment based on the first indicator, the scenario features, and the entity features of the first entity.

[0164] For example, a feature extraction model trained using machine learning or deep learning can be used to extract scene features of the scene information of the application scenario and entity features of the entity information of the first entity. The training method for the feature extraction model is relatively mature and will not be described in detail here.

[0165] In this design, by extracting the scenario features of the scenario information of the application scenario and the entity features of the entity information of the first entity, an evaluation environment is generated according to the first indicator, the scenario information and the entity features of the first entity, which can further improve the effectiveness or accuracy of the evaluation environment, more accurately restore the application scenario, and thus improve the accuracy of the trust model evaluation.

[0166] Optionally, generating the evaluation environment based on the first indicator, the scene features, and the entity features of the first entity may include: fusing the scene features and the entity features of the first entity to obtain a fused feature; and generating the evaluation environment based on the first indicator and the fused feature. Fusing the scene features and the entity features of the first entity and then generating the evaluation environment based on the obtained fused feature can improve the authenticity and accuracy of the evaluation environment.

[0167] Exemplarily, the trust model evaluation method provided in the embodiment of the present application can be implemented by a trust model evaluation system. For example, FIG3 shows a schematic diagram of the principle of a trust model evaluation system provided in the embodiment of the present application. As shown in FIG3, the trust model evaluation system may include: an entity analysis module 311, a scenario analysis module 312, a fusion module 320, an evaluation module 330, an indicator storage module 340, a trust model 350, and a parsing module 360. The aforementioned modules may be software modules, which may be integrated into one device or deployed on different devices, without limitation herein.

[0168] The entity analysis module 311 can obtain entity information of a first entity, extract entity features of the first entity based on the entity information of the first entity, and transmit the entity features of the first entity to the fusion module 320. The scenario analysis module 312 can obtain scenario information of an application scenario, extract scenario features of the application scenario based on the scenario information of the application scenario, and transmit the scenario features of the application scenario to the fusion module 320.

[0169] The fusion module 320 can fuse the scenario features of the application scenario with the entity features of the first entity and generate an evaluation context based on the first indicator and the fusion result. For example, the fusion result can be referred to as a fusion feature. The fusion module 320 can transmit information about the generated evaluation context to the evaluation module 330. The first indicator can be stored in the indicator storage module 340 and provided by the indicator storage module 340 to the fusion module 320.

[0170] The evaluation module 330 may call the trust model 350 , perform a trust evaluation on the first entity based on the evaluation environment, and output a trust evaluation result of the first entity, where the trust evaluation result of the first entity includes a trust evaluation result corresponding to each first indicator.

[0171] The evaluation module 330 may transmit the trust evaluation result corresponding to the first indicator to the analysis module 360. The analysis module 360 ​​may output an evaluation result of the trust model (or referred to as a model evaluation result) based on the trust evaluation result corresponding to the first indicator.

[0172] The principles of the trust model evaluation system described above can also be referred to in Figure 4 below. Figure 4 shows another implementation flow diagram of the trust model evaluation method provided in an embodiment of the present application. As shown in Figure 4, based on the trust model evaluation system shown in Figure 3, the trust model evaluation method may include S401-S411.

[0173] S401: An interface module receives an application scenario and a first entity input by a user.

[0174] Exemplarily, the trust model evaluation system may further include an interface module (not shown in FIG3 ). The interface module may provide a user with an input interface, allowing the user to input a specific application scenario and a first entity for which a trust model evaluation is required, such as a scenario name and an entity name. The interface module may obtain scenario information of the application scenario and entity information of the first entity based on the application scenario and the first entity input by the user. The acquisition method may be as described in the aforementioned embodiments and will not be further elaborated.

[0175] S402: The interface module sends scenario information of the application scenario and entity information of the first entity to an analyzing module.

[0176] The analysis module may include the entity analysis module and the scenario analysis module shown in Figure 3. The interface module may send entity information of the first entity to the entity analysis module and send scenario information of the application scenario to the scenario analysis module.

[0177] Accordingly, the analysis module receives scenario information of the application scenario and entity information of the first entity.

[0178] Optionally, the interface module may send an assessment request message to the analysis module, where the assessment request message includes scenario information of the application scenario and entity information of the first entity.

[0179] S403: The analysis module extracts entity features of the first entity and scenario features of the application scenario.

[0180] S404: The analysis module sends the entity features of the first entity and the scenario features of the application scenario to a fusion module.

[0181] Accordingly, the fusion module receives the entity features of the first entity and the scenario features of the application scenario.

[0182] S405. The fusion module obtains the first metric from the metric storage module.

[0183] In other words, the indicator storage module sends the first indicator to the fusion module, and the fusion module receives the first indicator.

[0184] S406. The fusion module generates an evaluation environment based on the first indicator, the entity characteristics of the first entity and the scenario characteristics of the application scenario.

[0185] S407: The fusion module sends the assessment environment information to the assessment module.

[0186] Accordingly, the evaluation module receives information of the evaluation environment.

[0187] S408: The evaluation module calls a trust model and performs a trust evaluation on the first entity based on the evaluation environment.

[0188] S409: The trust model returns a trust evaluation result corresponding to the first indicator to the evaluation module.

[0189] That is, the trust model outputs a trust evaluation result of the first entity, and the trust evaluation result of the first entity includes a trust evaluation result corresponding to each first indicator.

[0190] S410: The evaluation module sends a trust evaluation result corresponding to the first indicator to a parsing module.

[0191] Correspondingly, the parsing module receives the trust assessment result corresponding to the first indicator.

[0192] S411. The parsing module outputs an evaluation result of the trust model according to the trust evaluation result corresponding to the first indicator.

[0193] Exemplarily, the parsing module may store and parse the trust evaluation result to obtain an evaluation result of the trust model.

[0194] Optionally, the first indicator used in generating the evaluation environment in the trust model evaluation method is related to the application scenario and / or the first entity. For example, the method further includes: outputting / determining the first indicator based on the scenario information and the entity information of the first entity.

[0195] Exemplarily, the steps of obtaining the first indicator, scenario information of the application scenario, and entity information of the first entity described in the aforementioned embodiment may include: obtaining the scenario information of the application scenario and entity information of the first entity; and obtaining the first indicator based on the scenario information of the application scenario and the entity information of the first entity.

[0196] In one possible design, the first indicator corresponding to the specific application scenario and the first entity may be predefined, preconfigured, or configured. For example, matching evaluation indicators may be configured for the application scenario and the entity to obtain a mapping relationship between the evaluation indicator and the application scenario and the entity. Based on the scenario information of the application scenario and the entity information of the first entity, obtaining the first indicator may include: determining an evaluation indicator that matches the application scenario and the first entity according to this mapping relationship, such as a target evaluation indicator, and selecting at least one indicator from the target evaluation indicators as the first indicator. In other words, the mapping relationship may be predefined, preconfigured, or configured.

[0197] For example, in one implementation, the mapping relationship may be pre-configured in the hardware and / or software of the electronic device, such as being recorded / written in advance into the indicator storage module, and may be modified through software or hardware.

[0198] For another example, in another implementation, the mapping relationship may be configured to the electronic device, such as by recording / writing into the hardware and / or software of the electronic device.

[0199] For example, in another implementation, the mapping relationship does not require other device configurations and can be information predefined (can be recorded / written in advance) in the hardware and / or software of the above-mentioned electronic device, or can be understood as not being able to be changed by other devices.

[0200] This application does not limit the implementation method of the mapping relationship.

[0201] For example, a developer or other user may pre-define or configure the mapping relationship or association relationship between the application scenario and the first entity and the first indicator. For different application scenarios and / or first entities, the corresponding first indicators may be the same or different.

[0202] This design can realize customized selection of the first indicator for the current application environment and the first entity according to user design, and evaluate the trust model. It can improve the accuracy of the trust model evaluation results, so that the trust model evaluation results reflect the performance of the trust model from a more accurate and effective dimension.

[0203] In another possible design, the first indicator used to generate the evaluation environment can also be dynamically determined based on the scene information and the entity information of the first entity. For example, obtaining the first indicator based on the scene information of the application scenario and the entity information of the first entity can include: through deep learning or machine learning, a pre-trained neural network model dynamically determines an evaluation indicator that matches the application scenario and the first entity based on the scene information and the entity information of the first entity, such as a target evaluation indicator, and selects at least one indicator from the target evaluation indicators as the first indicator. For example, the scene information and the entity information of the first entity (or scene features and entity features, or fusion features) can be input into a pre-trained neural network model, and the pre-trained neural network model can output a first indicator that matches the application scenario and the first entity based on the input.

[0204] Exemplarily, obtaining the first indicator based on the scenario information of the application scenario and the entity information of the first entity includes: fusing the scenario information of the application scenario with the entity information of the first entity to obtain a fused feature; and obtaining the first indicator based on the fused feature. The fused feature may be specifically described in the aforementioned embodiments. For example, scenario features of the scenario information of the application scenario and entity features of the entity information of the first entity may be extracted, and the scenario features and entity features may be fused to obtain the fused feature.

[0205] By obtaining the first indicator based on the fusion feature, the validity or accuracy of the first indicator can be further evaluated, and a more suitable first indicator can be selected for the application scenario and the first entity to evaluate the trust model.

[0206] It can be understood that the neural network model can be obtained by training the neural network by taking scene features and entity features as input and the first indicator labeled with scene features and entity features as output. The training process will not be described in detail here.

[0207] For example, Figure 5 shows a schematic diagram of another trust model evaluation system provided by an embodiment of the present application. As shown in Figure 5, based on the above-mentioned Figure 3, the trust model evaluation system may further include: an indicator generation module 370. The indicator generation module 370 may be a software module.

[0208] The fusion module 320 may also transmit the fusion result (e.g., fusion feature) of the scene features and the entity features to the indicator generation module 370. The indicator generation module 370 may use a pre-trained neural network model to output a first indicator that matches the application scenario and the first entity based on the fusion feature. The indicator generation module 370 may transmit the generated first indicator to the indicator storage module 340 for storage. The indicator storage module 340 may provide the first indicator that matches the application scenario and the first entity to the fusion module 320 for the fusion module 320 to generate the evaluation environment.

[0209] The principle of the trust model evaluation system described in FIG5 can also be referred to in FIG6 below. FIG6 shows another implementation flow diagram of the trust model evaluation method provided in an embodiment of the present application. As shown in FIG6, based on the trust model evaluation system shown in FIG5, the trust model evaluation method may include S601-S615.

[0210] S601: An interface module receives an application scenario and a first entity input by a user.

[0211] S602: The interface module sends scenario information of the application scenario and entity information of the first entity to the analysis module.

[0212] Accordingly, the analysis module receives scenario information of the application scenario and entity information of the first entity.

[0213] S603: The analysis module extracts entity features of the first entity and scenario features of the application scenario.

[0214] S604: The analysis module sends the entity features of the first entity and the scenario features of the application scenario to the fusion module.

[0215] Accordingly, the fusion module receives the entity features of the first entity and the scenario features of the application scenario.

[0216] S601-S604 can refer to the above-mentioned S401-S404 and will not be described in detail.

[0217] S605: The fusion module fuses the entity feature of the first entity and the scene feature of the application scene to obtain a fusion feature.

[0218] S605 can refer to the above S406 for fusing entity features and scene features, which will not be described in detail.

[0219] S606: The fusion module sends the fusion features to the metric generation module.

[0220] Accordingly, the indicator generation module receives the fused features.

[0221] S607: The indicator generation module outputs a first indicator that matches the application scenario and the first entity based on the fusion feature.

[0222] S606-S607 can refer to the above-mentioned method of dynamically determining the first indicator by the pre-trained neural network model, and will not be repeated here.

[0223] S608. The indicator generation module sends a first indicator that matches the application scenario and the first entity to the indicator storage module.

[0224] Accordingly, the indicator storage module receives a first indicator that matches the application scenario and the first entity.

[0225] S609. The fusion module obtains the first indicator from the indicator storage module.

[0226] It can be understood that the first indicator is an indicator that matches the application scenario and the first entity.

[0227] S610: The fusion module generates an evaluation environment according to the first indicator, the entity characteristics of the first entity, and the scenario characteristics of the application scenario.

[0228] S611. The fusion module sends information about the evaluation environment to the evaluation module.

[0229] Accordingly, the evaluation module receives information of the evaluation environment.

[0230] S612: The evaluation module calls the trust model and performs a trust evaluation on the first entity based on the evaluation environment.

[0231] S613: The trust model returns a trust evaluation result corresponding to the first indicator to the evaluation module.

[0232] S614: The evaluation module sends the trust evaluation result corresponding to the first indicator to the analysis module.

[0233] Correspondingly, the parsing module receives the trust assessment result corresponding to the first indicator.

[0234] S615. The parsing module outputs an evaluation result of the trust model according to the trust evaluation result corresponding to the first indicator.

[0235] S609-S615 can refer to the above-mentioned S405-S411 and will not be repeated here.

[0236] This design can utilize deep learning or machine learning to customize and dynamically select the first indicator for the current application environment and the first entity to evaluate the trust model. This can improve the accuracy of the trust model evaluation results, enhance the adaptability of the trust model evaluation to different application scenarios, increase the flexibility of the evaluation, and enable the trust model evaluation results to reflect the performance of the trust model from a more accurate and effective dimension.

[0237] In some other possible designs, the first indicator used in generating the evaluation environment in the trust model evaluation method may also be one or more first indicators selected by the user from the obtained first indicators based on the scenario information of the application scenario and the entity information of the first entity after the first indicator is obtained. For example, the user may perform a selection operation on the first indicator, and the method further includes: in response to the user's selection operation on the first indicator, using the first indicator indicated by the selection operation as the first indicator used to generate the evaluation environment. In this design, the first indicator obtained based on the scenario information of the application scenario and the entity information of the first entity can be referred to as an alternative first indicator, and the first indicator selected by the user from the alternative first indicators can be referred to as a target first indicator.

[0238] For example, the step of generating an evaluation environment based on the first indicator, scenario information of the application scenario, and entity information of the first entity in the application scenario described in the above embodiments may include: in response to the user's selection operation of the first indicator (alternative first indicator), generating an evaluation environment based on the first indicator (target first indicator) indicated by the selection operation, the scenario information, and the entity information of the first entity.

[0239] For example, taking the implementation of the user selecting the first indicator in the trust model evaluation method process shown in FIG6 as an example, FIG7 shows another implementation flow diagram of the trust model evaluation method provided in an embodiment of the present application. As shown in FIG7, the trust model evaluation method may include S701-S717.

[0240] S701: An interface module receives an application scenario and a first entity input by a user.

[0241] S702: The interface module sends scenario information of the application scenario and entity information of the first entity to the analysis module.

[0242] Accordingly, the analysis module receives scenario information of the application scenario and entity information of the first entity.

[0243] S703: The analysis module extracts entity features of the first entity and scenario features of the application scenario.

[0244] S704: The analysis module sends the entity features of the first entity and the scenario features of the application scenario to the fusion module.

[0245] Accordingly, the fusion module receives the entity features of the first entity and the scenario features of the application scenario.

[0246] S705 : The fusion module fuses the entity feature of the first entity and the scene feature of the application scene to obtain a fusion feature.

[0247] S706: The fusion module sends the fusion features to the indicator generation module.

[0248] Accordingly, the indicator generation module receives the fused features.

[0249] S707: The indicator generation module outputs a first indicator that matches the application scenario and the first entity based on the fusion feature.

[0250] S708. The indicator generation module sends a first indicator that matches the application scenario and the first entity to the indicator storage module.

[0251] Accordingly, the indicator storage module receives a first indicator that matches the application scenario and the first entity.

[0252] S701-S708 can refer to the above S601-S608 and will not be repeated here.

[0253] S709: The indicator storage module sends a first indicator that matches the application scenario and the first entity to the interface module.

[0254] Accordingly, the interface module receives a first indicator that matches the application scenario and the first entity.

[0255] The interface module receives the first indicator (i.e., the alternative first indicator) that matches the application scenario and the first entity, and can display the first indicator that matches the application scenario and the first entity to the user for selection. The user can select one or more target first indicators from the alternative first indicators. For example, the interface module can display the alternative first indicators to the user through a human-computer interaction interface, and the user can perform a selection operation on the human-computer interaction interface to select the target first indicator. There is no restriction on the implementation method of the user performing the selection operation.

[0256] After the user selects the target first indicator, the interface module may execute S710.

[0257] S710. The interface module sends the first indicator of the selection operation instruction, that is, the target first indicator, to the indicator storage module.

[0258] Accordingly, the indicator storage module receives the first indicator indicating the selection operation.

[0259] Exemplarily, after receiving the first indicator of the selection operation indication, the indicator storage module may update the stored first indicator that matches the application scenario and the first entity, and update it to the first indicator of the selection operation indication.

[0260] S711. The fusion module obtains the first indicator indicating the selection operation from the indicator storage module.

[0261] S712. The fusion module generates an evaluation environment according to the first indicator indicated by the selection operation, the entity characteristics of the first entity, and the scenario characteristics of the application scenario.

[0262] S713: The fusion module sends the evaluation environment information to the evaluation module.

[0263] Accordingly, the evaluation module receives information of the evaluation environment.

[0264] S714: The evaluation module calls the trust model and performs a trust evaluation on the first entity based on the evaluation environment.

[0265] S715: The trust model returns a trust evaluation result corresponding to the first indicator indicated by the selection operation to the evaluation module.

[0266] S716: The evaluation module sends the trust evaluation result corresponding to the first indicator of the selection operation indication to the analysis module.

[0267] Correspondingly, the parsing module receives the trust evaluation result corresponding to the first indicator indicated by the selection operation.

[0268] S717: The parsing module outputs an evaluation result of the trust model according to the trust evaluation result corresponding to the first indicator indicated by the selection operation.

[0269] S711-S717 can refer to the above-mentioned S609-S615 and will not be repeated here.

[0270] This design allows for customized selection of the first indicator for the current application environment and the first entity, while also allowing users to adjust the first indicator based on their specific needs. For example, users can select a more meaningful or relevant first indicator based on their needs, further enhancing the value of the trust model's evaluation results to the user. Furthermore, by screening and selecting more relevant first indicators, the noise introduced by irrelevant or secondary indicators can be reduced, further improving the accuracy of the evaluation results.

[0271] Alternatively, users can also select some specific indicators for evaluation based on the need to save evaluation time and resources to improve evaluation efficiency.

[0272] It should be understood that the types of the first indicators described in the above embodiments are all exemplary. In specific implementations, the first indicators may also be divided into more or fewer categories. This application does not limit the types of the first indicators.

[0273] For the case where the first indicator includes multiple indicators, the process of generating an evaluation environment according to the first indicator and performing evaluation based on the evaluation environment in the above embodiments (such as the embodiments shown in Figures 4, 6, 7, etc.) can be understood as multiple first indicators implementing the process in parallel. In a possible design, the above-mentioned process of generating an evaluation environment according to the first indicator and performing evaluation based on the evaluation environment can also be implemented in a serial manner for multiple first indicators. For example, S201-S203 may include: generating an evaluation environment corresponding to the first indicator according to the first indicator, the scenario information of the application scenario, and the entity information of the first entity in the application scenario for each first indicator in turn; calling the trust model, performing trust evaluation on the first entity based on the evaluation environment corresponding to the first indicator, and outputting the trust evaluation result of the first entity; outputting the evaluation result of the trust model according to the trust evaluation result corresponding to the first indicator.

[0274] In other words, in this design, the trust model's trust assessment capability can be evaluated for a specific first indicator. After completing the trust model evaluation for a specific first indicator, the trust model evaluation for the next first indicator can be continued, until the trust model evaluation for all first indicators is completed. In other words, each first indicator corresponds to an evaluation environment, and different first indicators correspond to different evaluation environments.

[0275] For example, taking the process of generating an evaluation environment based on the first indicator and performing an evaluation based on the evaluation environment in the embodiment shown in FIG6 as an example (which may also be the embodiment shown in FIG4 or FIG7 ), FIG8 shows another implementation flow diagram of the trust model evaluation method provided in an embodiment of the present application. As shown in FIG8 , the trust model evaluation method may include S801-S816.

[0276] S801: An interface module receives an application scenario and a first entity input by a user.

[0277] S802: The interface module sends scenario information of the application scenario and entity information of the first entity to the analysis module.

[0278] Accordingly, the analysis module receives scenario information of the application scenario and entity information of the first entity.

[0279] S803: The analysis module extracts entity features of the first entity and scenario features of the application scenario.

[0280] S804: The analysis module sends the entity features of the first entity and the scenario features of the application scenario to the fusion module.

[0281] Accordingly, the fusion module receives the entity features of the first entity and the scenario features of the application scenario.

[0282] S805: The fusion module fuses the entity feature of the first entity and the scene feature of the application scene to obtain a fusion feature.

[0283] S806. The fusion module sends the fusion features to the indicator generation module.

[0284] Accordingly, the indicator generation module receives the fused features.

[0285] S807: The indicator generation module outputs a first indicator that matches the application scenario and the first entity based on the fusion feature.

[0286] S808. The indicator generation module sends a first indicator that matches the application scenario and the first entity to the indicator storage module.

[0287] Accordingly, the indicator storage module receives a first indicator that matches the application scenario and the first entity.

[0288] S801-S808 can refer to the above-mentioned S601-S608 and will not be repeated here.

[0289] S809. The fusion module obtains a first indicator from the indicator storage module.

[0290] It can be understood that the first indicator is any indicator that matches the application scenario and the first entity.

[0291] S810. The fusion module generates an evaluation environment corresponding to the first indicator based on the first indicator, the entity characteristics of the first entity, and the scenario characteristics of the application scenario.

[0292] S811. The fusion module sends information about the evaluation environment corresponding to the first indicator to the evaluation module.

[0293] Correspondingly, the evaluation module receives information of the evaluation environment corresponding to the first indicator.

[0294] S812: The evaluation module calls the trust model and performs a trust evaluation on the first entity based on the evaluation environment corresponding to the first indicator.

[0295] S813: The trust model returns a trust evaluation result corresponding to the first indicator to the evaluation module.

[0296] S814. The evaluation module sends the trust evaluation result corresponding to the first indicator to the analysis module.

[0297] Correspondingly, the parsing module receives the trust assessment result corresponding to the first indicator.

[0298] S815. The parsing module outputs an evaluation result of the trust model corresponding to the first indicator based on the trust evaluation result corresponding to the first indicator.

[0299] S809-S815 can refer to the above-mentioned S609-S615, the difference being that each step in S809-S815 is implemented for a first indicator, which will not be repeated here.

[0300] S816. Repeat S809-S815 for the next first indicator until all first indicator evaluations are completed.

[0301] For example, the next indicator may be obtained, and the evaluation result of the trust model corresponding to the next first indicator may be output according to the process of S810-S815; this cycle may be repeated until the evaluation results of the trust models corresponding to all first indicators are obtained.

[0302] In this design, for multiple first indicators, the process of generating an evaluation environment based on the first indicators and performing the evaluation based on the evaluation environment is implemented in a serial manner. Focusing on a single indicator (evaluating only one specific first indicator at a time) makes the evaluation process more concise and clear, and easier to understand and explain. Furthermore, for multiple first indicators, the serial implementation of the evaluation environment based on the first indicators and the evaluation based on the evaluation environment can also enhance the depth and accuracy of the evaluation. For example, it can focus resources and attention on a single indicator, avoiding the noise and interference that multiple indicators may bring, and more clearly understanding and analyzing the importance and role of each indicator.

[0303] In one possible design, the evaluation environment generated in the above embodiments may include an initial evaluation environment and at least one other evaluation environment; the initial evaluation environment is generated based on the first indicator, the scenario information, and the entity information of the first entity, as described in the above embodiments. The other evaluation environments may be obtained by adjusting parameters in the initial evaluation environment. For example, the scenario features and entity features in the initial evaluation environment may be changed or adjusted to obtain the other evaluation environments.

[0304] Exemplarily, in this design, the method further includes: adjusting parameters of the evaluation environment to obtain at least one updated evaluation environment; invoking the trust model, performing a trust evaluation on the first entity based on the updated evaluation environment, and outputting a trust evaluation result for the first entity. The evaluation environment is the initial evaluation environment, and the updated evaluation environment is another evaluation environment.

[0305] In this design, the evaluation environment can be expanded to provide a richer environment for trust model evaluation and improve the accuracy of trust model evaluation. For example, the trust model can be evaluated based on multiple evaluation environments, such as the initial evaluation environment and other evaluation environments. The performance of the trust model can be comprehensively evaluated based on the evaluation results obtained in different evaluation environments.

[0306] In a possible design, the evaluation result of the trust model described in the above embodiment can also be used to indicate an update strategy of the trust model.

[0307] For example, as described in the aforementioned embodiment, the evaluation result of the trust model may indicate the trust evaluation capability of the trust model within the dimension of the first indicator. For different first indicators, the trust evaluation capability of the trust model may be better in some first indicator dimensions and worse in other first indicator dimensions. The evaluation result of the trust model may indicate that the trust model needs to be optimized or updated for the first indicator with relatively poor trust evaluation capability, so as to improve the performance of the trust model in such first indicator dimensions. That is, the update strategy of the trust model may include: which dimensions of the trust model need to be optimized or updated. For example, the update strategy may indicate that the security of the trust model is insufficient.

[0308] Optionally, the trust model update policy may also indicate specific methods for updating the trust model, or recommendations for improvement or optimization. For example, to optimize the robustness of the trust model, the update policy may indicate the use of more training data to train the trust model. For another example, to optimize the security of the trust model, the update policy may indicate specific methods for improving the design of the trust assessment curve.

[0309] Exemplarily, the evaluation result of the trust model may include specific indication information, and the indication information may be used to indicate an update strategy of the trust model.

[0310] In this design, the evaluation results of the trust model can indicate the update strategy of the trust model, point out the improvement direction (dimension) of the trust model to developers or users, or provide users with more detailed model optimization suggestions, so that users can further optimize or adjust the trust model according to the evaluation results of the trust model to improve the performance of the trust model.

[0311] In other words, this design can provide feedback and guidance for the optimization of the trust model.

[0312] Furthermore, by updating the trust model based on its evaluation results, the trust model's generalization performance across different application scenarios can be improved. For example, by updating the same trust model in different application scenarios using this design, the trust model can demonstrate improved performance across all scenarios, providing greater adaptability.

[0313] Optionally, the trust model evaluation method provided in the embodiment of the present application may further include: updating the trust model according to the evaluation result of the trust model.

[0314] Exemplarily, the update method of the trust model may refer to the instructions of the update policy described in the above embodiment, which will not be described in detail here.

[0315] Taking the embodiment shown in FIG4 as an example, FIG9 shows another implementation flow diagram of the trust model evaluation method provided in the embodiment of the present application. As shown in FIG9, the trust model evaluation method may include S901-S911.

[0316] S901: An interface module receives an application scenario and a first entity input by a user.

[0317] S902: The interface module sends scenario information of the application scenario and entity information of the first entity to the analysis module.

[0318] Accordingly, the analysis module receives scenario information of the application scenario and entity information of the first entity.

[0319] S903: The analysis module extracts entity features of the first entity and scenario features of the application scenario.

[0320] S904: The analysis module sends the entity features of the first entity and the scenario features of the application scenario to the fusion module.

[0321] Accordingly, the fusion module receives the entity features of the first entity and the scenario features of the application scenario.

[0322] S905. The fusion module obtains the first indicator from the indicator storage module.

[0323] S906. The fusion module generates an evaluation environment according to the first indicator, the entity characteristics of the first entity and the scenario characteristics of the application scenario.

[0324] S907: The fusion module sends the evaluation environment information to the evaluation module.

[0325] Accordingly, the evaluation module receives information of the evaluation environment.

[0326] S908: The evaluation module calls the trust model and performs a trust evaluation on the first entity based on the evaluation environment.

[0327] S909: The trust model returns a trust evaluation result corresponding to the first indicator to the evaluation module.

[0328] S910: The evaluation module sends a trust evaluation result corresponding to the first indicator to the analysis module.

[0329] Correspondingly, the parsing module receives the trust assessment result corresponding to the first indicator.

[0330] S911. The parsing module outputs an evaluation result of the trust model according to the trust evaluation result corresponding to the first indicator.

[0331] S901-S911 can refer to the above-mentioned S401-S411 and will not be repeated here.

[0332] S912: The parsing module sends the evaluation result of the trust model to the trust model.

[0333] Accordingly, the trust model receives the evaluation result.

[0334] S913. The trust model is updated according to the evaluation results.

[0335] It can be understood that the trust model shown in the figure can be a software module that stores or manages the trust model, such as a model maintenance module, which can receive the evaluation results and update the trust model according to the evaluation results.

[0336] In this design, the trust model is updated according to the evaluation results, which can improve the trust evaluation capability of the trust model.

[0337] In a possible design, the evaluation result of the trust model described in the above embodiment may be a semantic trust evaluation report.

[0338] Exemplarily, the trust assessment result corresponding to the first indicator may be input into a large language model (LLM), the trust assessment result corresponding to the first indicator may be parsed by the LLM, and a semantic trust assessment report may be output as an assessment result of the trust model.

[0339] For example, the above-mentioned parsing module can be deployed on a semantic information processor. The parsing module or the semantic information processor can use LLM to process information at the semantic level and parse the trust assessment result corresponding to the first indicator to generate a semantic trust assessment report.

[0340] Optionally, the semantic trust assessment report can provide improvement suggestions for the trust model, such as providing semantic adjustment solutions and optimization methods, to facilitate users to improve the trust model.

[0341] In this design, using a semantic trust evaluation report as the evaluation result of the trust model can enable users to better understand the trust evaluation capability of the trust model within the dimension of the first indicator, and more intuitively understand from which dimensions the trust model can be improved, and / or how the trust model can be improved.

[0342] In some other embodiments, in the trust model evaluation method described above, the steps of extracting scene features and entity features, and the steps of outputting the evaluation results of the trust model based on the trust evaluation results of the first entity, and other functions implemented separately, can be integrated into one module, for example, an artificial intelligence (AI) module.

[0343] This application does not limit the division of the functional modules for implementing the trust model evaluation method.

[0344] It should be understood that the above mainly introduces the solution provided by the embodiment of the present application from the perspective of the logic between the various steps of the trust model evaluation method. It is understandable that in order to realize the functions of the above method, the embodiment of the present application also provides a device for realizing the functions of the above trust model evaluation method, such as a trust model evaluation device. The functions of the device can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more units or modules corresponding to the functions of the above method, that is, the device can include hardware structures and / or software modules corresponding to the various functions of the above method. The device can be an electronic device, or it can be a chip built into an electronic device or a functional module in an electronic device. The electronic device can refer to the electronic device described in the aforementioned embodiment.

[0345] For example, Figure 10 shows a schematic diagram of the components of a trust model evaluation device provided in an embodiment of the present application. As shown in Figure 10 , the trust model evaluation device may include: a trust evaluation unit 1001 and a model evaluation unit 1002 .

[0346] Among them, the trust evaluation unit 1001 is used to perform a trust evaluation on the first entity based on the trust model to obtain a trust evaluation result of the first entity, where the trust evaluation result includes at least one group, each group of trust evaluation results corresponds to a first indicator, and the first indicator is used to indicate an evaluation dimension of the trust model.

[0347] The model evaluation unit 1002 evaluates the trust model according to the trust evaluation result to obtain an evaluation result of the trust model. The evaluation result of the trust model is used to indicate the trust evaluation capability of the trust model within the dimension of the first indicator.

[0348] Exemplarily, the trust evaluation unit 1001 may include the analysis module, fusion module, evaluation module, indicator generation / storage module, etc. described in the aforementioned embodiments. The model evaluation unit 1002 may include the parsing module described in the aforementioned embodiments.

[0349] In one possible design, the trust evaluation unit 1001 is specifically used to: obtain a first indicator, scenario information of an application scenario, and entity information of a first entity; generate an evaluation environment based on the first indicator, scenario information of the application scenario, and entity information of the first entity, where the evaluation environment indicates an environment in which the first entity runs in the application scenario; call a trust model, perform a trust evaluation on the first entity based on the evaluation environment, and obtain a trust evaluation result of the trust model on the first entity.

[0350] In a possible design, the trust evaluation unit 1001 is specifically used to: obtain scenario information of the application scenario and entity information of the first entity; and obtain a first indicator based on the scenario information of the application scenario and the entity information of the first entity.

[0351] In one possible design, the first indicator used to generate the evaluation environment can be predefined, preconfigured, or configured. For example, matching evaluation indicators can be configured for the application scenario and the entity, resulting in a mapping relationship between the evaluation indicators, the application scenario, and the entity. Trust evaluation unit 1001 is specifically configured to: determine, based on this mapping relationship, an evaluation indicator that matches the application scenario and the first entity, such as a target evaluation indicator, and select at least one indicator from the target evaluation indicators as the first indicator.

[0352] In another possible design, the first indicator used to generate the evaluation environment can also be dynamically determined based on the scenario information and the entity information of the first entity. For example, the trust evaluation unit 1001 is further configured to dynamically determine, based on the scenario information and the entity information of the first entity, an evaluation indicator that matches the application scenario and the first entity, such as a target evaluation indicator, using a pre-trained neural network model through deep learning or machine learning. At least one indicator is selected from the target evaluation indicators as the first indicator.

[0353] In another possible design, the first indicator used to generate the evaluation environment may also be one or more first indicators selected by the user from among the first indicators obtained after obtaining the first indicators based on scenario information of the application scenario and entity information of the first entity. For example, the trust evaluation unit 1001 is further configured to, in response to a user selecting a first indicator, use the first indicator indicated by the selection as the first indicator used to generate the evaluation environment.

[0354] In a possible design, the trust evaluation unit 1001 is specifically configured to: fuse the scenario information of the application scenario with the entity information of the first entity to obtain a fusion feature; and obtain a first indicator based on the fusion feature.

[0355] In one possible design, the trust evaluation unit 1001 is specifically used to generate an evaluation environment corresponding to the first indicator for each of the first indicators in turn, based on the first indicator, scenario information of the application scenario, and entity information of the first entity in the application scenario; perform trust evaluation on the first entity based on the evaluation environment corresponding to the first indicator, and output a trust evaluation result of the first entity.

[0356] That is, in this design, each first indicator corresponds to an evaluation environment, and different first indicators correspond to different evaluation environments.

[0357] In one possible design, the generated evaluation environment may include an initial evaluation environment and at least one additional evaluation environment; the initial evaluation environment is generated based on the first indicator, scenario information, and entity information of the first entity; the additional evaluation environment may be obtained by adjusting parameters in the initial evaluation environment. For example, the trust evaluation unit 1001 is further configured to adjust parameters in the evaluation environment to obtain at least one updated evaluation environment; invoke the trust model, perform a trust evaluation on the first entity based on the updated evaluation environment, and output a trust evaluation result for the first entity. The initial evaluation environment is the evaluation environment, and the updated evaluation environment is the additional evaluation environment.

[0358] In one possible design, the application scenarios include at least one of the following: network security scenarios, intelligent system scenarios, online platform scenarios, complex decision-making environment scenarios, Internet of Things scenarios, cloud computing scenarios, edge computing scenarios, network slicing and virtualized network scenarios, software-defined network scenarios, blockchain scenarios, and communication network scenarios; the first entity includes at least one of the following: hardware devices or modules, applications or software modules, and data of hardware and / or software interaction.

[0359] In one possible design, the evaluation result of the trust model is also used to indicate the update strategy of the trust model.

[0360] In one possible design, the apparatus further includes an updating unit (not shown in FIG10 ) configured to update the trust model according to an evaluation result of the trust model.

[0361] In one possible design, the evaluation result of the trust model is a semantic trust evaluation report.

[0362] In one possible design, the first indicator includes one or more of the following indicators: security of data, comprehensiveness of trust assessment results, availability of trust model, functionality of trust model, robustness of trust model, neutrality of trust assessment results, and interpretability of trust assessment results.

[0363] It should be understood that the division of units in the above device is merely a division of logical functions. In actual implementation, they may be fully or partially integrated into a single physical entity, or physically separated. Furthermore, the units in the device may be implemented entirely in the form of software invoked through processing elements, entirely in the form of hardware, or partially in the form of software invoked through processing elements, while others may be implemented in the form of hardware.

[0364] For example, each unit can be a separately established processing element, or it can be integrated into a certain chip of the device for implementation. In addition, it can also be stored in a memory in the form of a program, and called by a certain processing element of the device to execute the function of the unit. In addition, all or part of these units can be integrated together, or they can be implemented independently. The processing element described here can also be called a processor, which can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above units can be implemented by the integrated logic circuit of the hardware in the processor element or in the form of software called by the processing element.

[0365] In one example, the unit in any of the above devices can be one or more integrated circuits configured to implement the above method, such as: one or more application specific integrated circuits (ASICs), or one or more digital signal processing (DSP) circuits, or one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0366] For another example, when the units in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a CPU or other processor that can call programs. For another example, these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0367] When a device includes a unit for receiving, the unit for receiving in the device is an interface circuit or input circuit of the device, which is used to receive signals from other devices. For example, when the device is implemented as a chip, the receiving unit is an interface circuit or input circuit of the chip used to receive signals from other chips or devices. When a device includes a unit for sending, the unit for sending is an interface circuit or output circuit of the device, which is used to send signals to other devices. For example, when the device is implemented as a chip, the sending unit is an interface circuit or output circuit of the chip used to send signals to other chips or devices.

[0368] For example, embodiments of the present application may also provide a trust model evaluation device that can be applied to the above-mentioned electronic device. The trust model evaluation device may include: a processor and an interface circuit. The processor may include one or more processors. The processor is configured to communicate with other devices via the interface circuit and execute the steps performed by the electronic device in the above method.

[0369] In one implementation, the units for implementing the corresponding steps in the above method in an electronic device can be implemented in the form of a processing element scheduling program. For example, an apparatus for an electronic device may include a processing element and a storage element, with the processing element invoking a program stored in the storage element to execute the method performed by the electronic device in the above method embodiment. The storage element can be a storage element on the same chip as the processing element, i.e., an on-chip storage element.

[0370] In another implementation, the program for executing the above method may be stored in a memory element on a different chip from the processing element, i.e., an off-chip memory element. In this case, the processing element calls or loads the program from the off-chip memory element onto the on-chip memory element to call and execute the method in the above method embodiment.

[0371] For example, embodiments of the present application may further provide a trust model evaluation device, which may include a processor configured to execute computer instructions stored in a memory. When the computer instructions are executed, the device performs the method performed by the electronic device described above. The memory may be located within the trust model evaluation device or may be located outside the trust model evaluation device. The processor may include one or more processors.

[0372] In another implementation, the units in each step of the above method may be configured as one or more processing elements, which may be correspondingly provided on an electronic device. The processing elements herein may be integrated circuits, such as one or more ASICs, one or more DSPs, one or more FPGAs, or a combination of these integrated circuits. These integrated circuits may be integrated together to form a chip.

[0373] The units implementing each step of the above method can be integrated together and implemented in the form of a SOC chip, which is used to implement the corresponding method. The chip can integrate at least one processing element and a storage element, and the corresponding method can be implemented by the processing element calling the program stored in the storage element; alternatively, the chip can integrate at least one integrated circuit to implement the corresponding method; or, a combination of the above implementation methods can be used, with the functions of some units implemented by the processing element calling the program, and the functions of some units implemented by the integrated circuit.

[0374] The processing element here is the same as described above, and can be a general-purpose processor, such as a CPU, or one or more integrated circuits configured to implement the above method, such as: one or more ASICs, or one or more microprocessors DSPs, or one or more FPGAs, etc., or a combination of at least two of these integrated circuit forms.

[0375] A storage element may be a memory or a collective term for multiple storage elements.

[0376] For example, embodiments of the present application further provide a chip system that can be applied to the above-mentioned electronic device. The chip system includes one or more interface circuits and one or more processors; the interface circuits and processors are interconnected via circuits; the processors receive and execute computer instructions from the memory of the electronic device via the interface circuits to implement the methods in the above-mentioned method embodiments.

[0377] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0378] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0379] The units described as separate components may or may not be physically separate, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0380] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0381] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, such as a program. The software product is stored in a program product, such as a computer-readable storage medium, and includes a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0382] For example, an embodiment of the present application may also provide a computer-readable storage medium, including: computer software instructions; when the computer software instructions are executed in an electronic device, or in a chip built into the electronic device, the electronic device may execute the method described in the aforementioned embodiment.

[0383] Optionally, an embodiment of the present application further provides a trust model evaluation device, comprising: a transceiver unit and a processing unit. The transceiver unit can be used to send and receive information, or to communicate with other network elements (such as terminal devices or network devices, or other electronic devices or devices). The processing unit can be used to process data. The device can implement the method described in the above embodiment through the transceiver unit and the processing unit.

[0384] Optionally, an embodiment of the present application further provides a computer program product, which, when executed, can implement the method described in the above embodiment.

[0385] Based on the above embodiments, the embodiments of the present application also provide an artificial intelligence model, which has the function of implementing the method described in the above embodiments.

[0386] Optionally, the artificial intelligence model includes one or more models. When the artificial intelligence model includes multiple models, the multiple models implement different functions in the method described in the above embodiment.

[0387] An embodiment of the present application further provides a communication system, including: a first entity and a second entity, wherein the second entity interacts with the first entity to implement the method described in the above embodiment.

[0388] The above is only a specific embodiment of the present application, but the scope of protection of this application is not limited to this. Any changes or substitutions within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A trust model evaluation method, characterized in that: The method comprises: Performing a trust evaluation on the first entity based on the trust model to obtain a trust evaluation result of the first entity, wherein the trust evaluation result includes at least one group, each group of the trust evaluation results corresponds to a first indicator, and the first indicator is used to indicate an evaluation dimension of the trust model; The trust model is evaluated according to the trust evaluation result to obtain an evaluation result of the trust model, and the evaluation result of the trust model is used to indicate the trust evaluation capability of the trust model within the dimension of the first indicator.

2. The method according to claim 1, characterized in that The performing trust evaluation on the first entity based on the trust model to obtain a trust evaluation result of the first entity includes: Acquire the first indicator, scenario information of the application scenario, and entity information of the first entity; Generate an evaluation environment according to the first indicator, the scenario information of the application scenario, and the entity information of the first entity, wherein the evaluation environment indicates an environment in which the first entity runs in the application scenario; The trust model is called, and a trust evaluation is performed on the first entity based on the evaluation environment to obtain a trust evaluation result of the trust model on the first entity.

3. The method according to claim 2, characterized in that The acquiring the first indicator, the scenario information of the application scenario, and the entity information of the first entity includes: Acquire scenario information of the application scenario and entity information of the first entity; The first indicator is obtained based on the scenario information of the application scenario and the entity information of the first entity.

4. The method according to claim 3, characterized in that The acquiring the first indicator based on the scenario information of the application scenario and the entity information of the first entity includes: Fusing the scene information of the application scene with the entity information of the first entity to obtain a fusion feature; Based on the fusion feature, the first indicator is obtained.

5. The method according to any one of claims 2 to 4, characterized in that: The application scenarios include at least one of the following: network security scenarios, intelligent system scenarios, online platform scenarios, complex decision-making environment scenarios, Internet of Things scenarios, cloud computing scenarios, edge computing scenarios, network slicing and virtualized network scenarios, software-defined network scenarios, blockchain scenarios, and communication network scenarios; The first entity includes at least one of the following: a hardware device or module, an application or software module, and data of hardware and / or software interaction.

6. The method according to any one of claims 2 to 5, characterized in that: The entity information of the first entity includes static attribute information and / or dynamic behavior information of the first entity.

7. The method according to any one of claims 1 to 6, characterized in that: The evaluation result of the trust model is also used to indicate an update strategy of the trust model.

8. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: The trust model is updated according to the evaluation result of the trust model.

9. The method according to any one of claims 1 to 8, characterized in that: The evaluation result of the trust model is a semantic trust evaluation report.

10. The method according to any one of claims 1 to 9, characterized in that: The first indicator includes one or more of the following indicators: data security, comprehensiveness of trust assessment results, availability of trust model, functionality of trust model, robustness of trust model, neutrality of trust assessment results, and interpretability of trust assessment results.

11. A trust model evaluation device, characterized in that: The apparatus comprises means for performing the method according to any one of claims 1-10.

12. A trust model evaluation device, characterized in that: The device comprises: a processor configured to execute the method according to any one of claims 1-10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium comprises instructions, and when the instructions are executed, the method according to any one of claims 1 to 10 is implemented.

14. A computer program product, characterized in that When the computer program product is executed, the method according to any one of claims 1 to 10 is implemented.

15. A chip system, characterized in that: The chip system includes one or more interface circuits and one or more processors; the interface circuit and the processor are interconnected by lines; the processor receives and executes computer instructions from the memory of the electronic device through the interface circuit to implement the method described in any one of claims 1-10.

Images