Knowledge base retrieval methods, devices, media, and equipment

Abstract

This specification provides a knowledge base retrieval method, apparatus, medium, and device. The method includes: receiving input parameters sent by a caller; determining the class corresponding to the input parameters in a class inheritance model; wherein the class inheritance model includes multiple classes, each corresponding one-to-one with a knowledge category in the knowledge base, and the inheritance relationship between classes in the class inheritance model is determined by the hierarchical relationship between knowledge categories in the knowledge base; searching for knowledge in the knowledge base from the corresponding knowledge category of the corresponding class according to the input parameters; and returning the searched knowledge to the caller. This invention allows for accurate and rapid retrieval of required knowledge.

Description

Technical Field

[0001] This specification relates to one or more embodiments in the field of knowledge base technology, and in particular to a knowledge base retrieval method, apparatus, medium, and device. Background Technology

[0002] With the rise of digital life, the content risk situation is becoming increasingly severe, and risk governance capabilities are facing multifaceted challenges.

[0003] Traditional content security primarily relies on feature-engineered algorithms, sample matching, and manual review to filter risks. Since the rise of deep learning in 2012, deep neural network models have rapidly improved the performance of content security algorithms, effectively increasing the automation rate of machine-based risk control and further promoting the intelligentization of content risk prevention. Current industry content security prevention revolves around two main lines: first, focusing on the sample dimension, using explicit features to match business content for risk filtering; second, using machine learning models such as deep learning, where machines autonomously learn from large amounts of risk data to obtain implicit features of given risks, then extract features from business content to match these implicit features, thus deciding whether to block or allow content. However, with the increasing contentification of businesses, including live streaming, short videos, and digital collectibles, Alipay has gradually transformed from a "passive source" of content risks to a "source" of them. User-posted content on its platform is becoming increasingly cryptic and shows clear adversarial intent, while content risks mutate and iterate rapidly, with new memes constantly emerging. There are two main approaches. The former relies on the explicit features of the sample library, which are limited by the discreteness and uncertain dimensionality of the risk space. The latter approach, which combines pre-training with large-scale modeling, requires significant training costs, such as machine resources and batches of sample data.

[0004] As a result, the industry began exploring "knowledge-driven risk control models," which require a knowledge base adapted to content security. Given the vast amount of knowledge in the knowledge base, how to access and utilize that knowledge is extremely crucial. Summary of the Invention

[0005] This specification describes one or more embodiments of a knowledge base retrieval method, apparatus, medium, and device.

[0006] According to the first aspect, the knowledge base invocation method provided in the embodiments of this specification includes:

[0007] Receive input parameters sent by the caller;

[0008] Determine the class corresponding to the input parameter in the class inheritance model; wherein, the class inheritance model includes multiple classes, each of which corresponds one-to-one with a knowledge category in the knowledge base, and the inheritance relationship between classes in the class inheritance model is determined by the hierarchical relationship between knowledge categories in the knowledge base;

[0009] Based on the input parameters, a knowledge search is performed from the corresponding knowledge category in the knowledge base for the corresponding class.

[0010] The retrieved knowledge is returned to the caller.

[0011] According to the second aspect, the knowledge base retrieval device provided in the embodiments of this specification includes:

[0012] The receiving module is used to receive input parameters sent by the caller;

[0013] The determination module is used to determine the class corresponding to the input parameter in the class inheritance model; wherein, the class inheritance model includes multiple classes, each of which corresponds one-to-one with a knowledge category in the knowledge base, and the inheritance relationship between classes in the class inheritance model is determined by the hierarchical relationship between knowledge categories in the knowledge base;

[0014] The search module is used to search for knowledge in the knowledge category corresponding to the corresponding class in the knowledge base according to the input parameters.

[0015] The return module is used to return the searched knowledge to the caller.

[0016] According to a third aspect, the computer-readable storage medium provided in the embodiments of this specification stores a computer program that, when executed in a computer, causes the computer to perform the method provided in the first aspect.

[0017] According to a fourth aspect, the computing device provided in the embodiments of this specification includes a memory and a processor, wherein the memory stores executable code, and the processor executes the executable code to implement the method provided in the first aspect.

[0018] The knowledge base retrieval method, apparatus, medium, and device provided in the embodiments of this specification first require the construction of a class inheritance model. This model includes multiple classes, each corresponding one-to-one with a knowledge category in the knowledge base. The inheritance relationship between classes is determined by the hierarchical relationship between the knowledge categories in the knowledge base. The system receives input parameters sent by the caller, determines the corresponding class based on the input parameters, searches for knowledge within the corresponding knowledge category of that class, and finally returns the searched knowledge to the caller. Therefore, by constructing a class inheritance library based on the knowledge base and then using this library to retrieve knowledge, even with a large amount of knowledge in the knowledge base, the required knowledge can be retrieved accurately and quickly. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating a knowledge base invocation method in one embodiment of this specification;

[0021] Figure 2 This is a structural block diagram of a knowledge base calling device in one embodiment of this specification. Detailed Implementation

[0022] The solution provided in this specification will now be described with reference to the accompanying drawings.

[0023] As mentioned in the background technology, the knowledge-driven risk control model that the industry is beginning to explore requires a knowledge base. This knowledge base contains multiple levels of knowledge categories, and each category contains a large amount of knowledge. Therefore, it is crucial to be able to access the knowledge in the knowledge base.

[0024] To this end, embodiments of this specification provide a knowledge base invocation method, which includes: receiving input parameters sent by a caller; determining the class corresponding to the input parameters in a class inheritance model; wherein the class inheritance model includes multiple classes, each of which corresponds one-to-one with a knowledge category in the knowledge base, and the inheritance relationship between classes in the class inheritance model is determined by the hierarchical relationship between knowledge categories in the knowledge base; searching for knowledge in the knowledge category corresponding to the corresponding class in the knowledge base according to the input parameters; and returning the searched knowledge to the caller.

[0025] The following describes the specific implementation of the above concept.

[0026] Figure 1 This is a flowchart illustrating a knowledge base retrieval method in one embodiment of the present invention. It is understood that this method can be executed by any device, equipment, platform, or device cluster with computing and processing capabilities. See also... Figure 1 The knowledge base retrieval method includes the following steps S102 to S108:

[0027] S102, Receive the input parameters sent by the caller;

[0028] S104. Determine the class corresponding to the input parameter in the class inheritance model; wherein, the class inheritance model includes multiple classes, each of which corresponds one-to-one with a knowledge category in the knowledge base, and the inheritance relationship between classes in the class inheritance model is determined by the hierarchical relationship between knowledge categories in the knowledge base;

[0029] S106. Based on the input parameters, perform a knowledge search in the knowledge category corresponding to the corresponding class in the knowledge base;

[0030] S108. Return the searched knowledge to the caller.

[0031] exist Figure 1 The method described first requires constructing a class inheritance model, which includes multiple classes that correspond one-to-one with various knowledge categories in the knowledge base. The inheritance relationship between classes is determined by the hierarchical relationship between knowledge categories in the knowledge base. The system receives input parameters from the caller, determines the corresponding class based on the parameters, searches for knowledge within the corresponding knowledge category of that class, and finally returns the found knowledge to the caller. Therefore, by constructing a class inheritance library based on the knowledge base and then using this library to access knowledge, even with a vast amount of knowledge in the knowledge base, the required knowledge can be accessed accurately and quickly.

[0032] The following description Figure 1 The execution method of each step.

[0033] S102, Receive the input parameters sent by the caller;

[0034] The caller refers to the user or device that needs to access the knowledge in the knowledge base.

[0035] The input parameters are usually the categories, attributes, and other parameters of the knowledge that the caller needs to access.

[0036] Before executing S102, it is necessary to construct the class inheritance model corresponding to the knowledge base. The knowledge base includes multiple levels of knowledge categories. In two adjacent knowledge categories, the upper-level knowledge category is the parent knowledge category, and the lower-level knowledge category is the child knowledge category, presenting an overall tree structure.

[0037] In one embodiment, the formation process of the class inheritance model may specifically include the following steps a1 to a3:

[0038] a1. Map each knowledge category in the knowledge base to a corresponding class;

[0039] a2. Configure the inheritance relationship between classes according to the hierarchical relationship between knowledge categories in the knowledge base;

[0040] a3. Based on the classes with configured inheritance relationships, determine the class inheritance model corresponding to the knowledge base.

[0041] In other words, each knowledge category in the knowledge base is mapped to a corresponding class, and then the inheritance relationship is configured for each class according to the hierarchical relationship between the knowledge categories. After the inheritance relationship is configured, the classes are associated with each other, and then the classes with the inheritance relationship configured form a class inheritance model.

[0042] As can be seen, the class inheritance model constructed in the above way has the same structure as the knowledge base, which facilitates subsequent knowledge retrieval.

[0043] Furthermore, the step a2, which describes configuring the inheritance relationship between classes according to the hierarchical relationship between knowledge categories in the knowledge base, can specifically include: for two classes corresponding to two levels of knowledge categories with a parent-child relationship, the subclass corresponding to the sub-knowledge category inherits the attributes and methods related to the attributes of the parent class corresponding to the parent knowledge category.

[0044] In other words, for two adjacent knowledge categories, the upper knowledge category is the parent knowledge category, which corresponds to the parent class in the two categories mentioned above. The lower knowledge category is the child knowledge category, which corresponds to the child class in the two categories mentioned above. The child class can inherit the attributes and methods related to the attributes from the parent class.

[0045] Inheritance is a concept in object-oriented software technology. If a class B "inherits" from another class A, then class B is called a "subclass of A," and class A is called the "parent class of B," or "A is the superclass of B." Inheritance allows subclasses to possess the various attributes and methods of their parent classes without needing to rewrite the same code.

[0046] In this context, a class is a constructive category in an object-oriented computer programming language. It serves as a blueprint for creating objects, describing the common attributes and methods of the created objects. A more rigorous definition is a cohesive package composed of certain metadata.

[0047] Here, an object is defined as having a unique identifier. An object includes attributes and methods related to those attributes. Attributes are information that needs to be remembered, and methods are the services that the object can provide. In this embodiment of the invention, an object within a class can be understood as knowledge within the knowledge category corresponding to that class.

[0048] For example, a parent class might be "Animal," and a subclass might be "Dog." The parent class "Animal" can have attributes such as name, weight, and height. The subclass "Dog," in addition to inheriting these attributes from its parent class, also has its own attributes, such as olfactory sensitivity. This subclass also has its own subclass "Corgi," which, besides possessing all the attributes of its parent class "Dog," also has its own attributes, such as leg length.

[0049] Regarding methods related to attributes, every object in a class has at least one method, and these methods come in many forms, such as methods for finding attributes, methods for constructing attributes, and methods for implementing attributes.

[0050] As can be seen, a tree-structured knowledge base can be used to construct a class inheritance model, which is also tree-structured. This model includes multiple classes, and each class in the model corresponds one-to-one with each knowledge category in the knowledge base. Therefore, these classes in the class inheritance model also have a hierarchical relationship. Inheritance relationships can be set for each class based on the hierarchical relationship between knowledge categories, specifically ensuring that subclasses possess the attributes and methods of their parent classes. This eliminates the need to rewrite the same code, simplifying the construction process of the class inheritance model. In other words, the inheritance relationship between classes in the aforementioned class inheritance model is determined by the hierarchical relationship between knowledge categories in the knowledge base.

[0051] In one embodiment, S102 may specifically include:

[0052] The system receives input parameters sent by the caller through a standardized communication interface; wherein, the standardized communication interface is a unified interface provided by the class inheritance model to the caller, so that the caller can access the knowledge in the knowledge category corresponding to any class through the standardized communication interface.

[0053] In other words, a standardized communication interface is set up for the class inheritance model, instead of setting up a separate interface for each level of class. All input parameters sent by the caller are received through this standardized communication interface, and the retrieved knowledge is also returned to the caller through the same interface. In this way, the caller can send input parameters and receive returned knowledge through this unified interface—the standardized communication interface—simplifying the caller's logic and making the class inheritance model suitable for multiple callers to access knowledge.

[0054] Understandably, due to the rapid iteration of content risk knowledge, the abundance of knowledge in vertical fields, and its highly adversarial nature, coupled with the lack of unified standards and the accumulation of expert experience, it is impossible to achieve end-to-end application and standardized output. Furthermore, the application requirements for knowledge risk control vary greatly depending on the specific risks involved, and the attributes of different knowledge used for content prevention and control also differ significantly. Therefore, a universal, standardized communication interface is crucial for knowledge risk control applications, enabling the generalization of the knowledge base and facilitating the retrieval of knowledge within it.

[0055] S104. Determine the class corresponding to the input parameter in the class inheritance model; wherein, the class inheritance model includes multiple classes, each of which corresponds one-to-one with a knowledge category in the knowledge base, and the inheritance relationship between classes in the class inheritance model is determined by the hierarchical relationship between knowledge categories in the knowledge base;

[0056] In other words, after receiving the input parameters sent by the caller, the class corresponding to the knowledge to be invoked in the class inheritance model is determined based on the input parameters.

[0057] For example, in the class inheritance model formed by the three levels of classes mentioned above (Animal-Dog-Corgi), if the received input parameter is leg length, the determined class is Corgi. If the received input parameter is olfactory sensitivity, the determined class is Dog, not Corgi. If the received input parameter is height, the determined class can only be Animal, not both Dog and Corgi, even though Dog and Corgi classes also inherit the height attribute. If the user wants knowledge about dogs, the search will be conducted from the knowledge category corresponding to the Dog class, not from the knowledge category corresponding to the lower-level Corgi class, ensuring accurate and fast knowledge retrieval.

[0058] Once a class is determined based on the input parameters sent by the caller, the class inheritance model only exposes the attributes and methods of that class; other classes are not visible to the application. That is, once a class is determined, knowledge searches will be limited to that class and will not penetrate other classes.

[0059] In one embodiment, after executing S104 and before executing S106, the method provided by the present invention may further include: adjusting the input parameters through overloading technology to adapt to the input parameter requirements of the corresponding class.

[0060] Overloading allows the creation of multiple functions with the same name but different implementations. When a function is called, its context-specific implementation is executed, allowing a function call to perform different tasks depending on the context.

[0061] Especially when a standardized communication interface is established, different knowledge categories have different requirements for input parameters during searches. For example, a certain knowledge category might not require a specific input parameter for its search, but the caller might send this parameter. Therefore, overloading can be used to remove the unnecessary parameter, and the remaining parameters can then be used for the search. It's clear that overloading allows input parameters received from the standardized communication interface to be adapted to various knowledge categories. Furthermore, since the class inheritance model only sets one standardized communication interface (i.e., a communication function), overloading allows a single communication function to meet the diverse knowledge application needs when calling different knowledge categories.

[0062] S106. Based on the input parameters, perform a knowledge search in the knowledge category corresponding to the corresponding class in the knowledge base;

[0063] In other words, after determining the corresponding class, a knowledge search is performed in the knowledge category of the corresponding class in the knowledge base based on the input parameters to obtain the search results.

[0064] S108. Return the searched knowledge to the caller.

[0065] For example, after the search is completed, the searched knowledge can be returned to the caller through a standardized communication interface.

[0066] As can be seen, this embodiment of the invention references the concept of classes in object-oriented programming design in computer science, abstracting knowledge categories in traditional knowledge bases into classes, configuring inheritance relationships between classes, thus obtaining a class inheritance model. By defining inheritance relationships, subclasses can possess the attributes and methods related to those attributes of their parent classes, and can also have their own independent attributes and methods related to those attributes. This facilitates refined application without interfering with their parent or sibling classes.

[0067] In real-world scenarios, in addition to setting classes in the class inheritance model, you can also set instances in the class inheritance model. For example, you can use the knowledge of the lowest-level knowledge category in the knowledge base as an instance of the last-level class in the class inheritance model. In this way, when you need to search in the lowest-level knowledge category, you can search directly in the instance of the last class.

[0068] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0069] Secondly, one embodiment of this specification provides a knowledge base retrieval device.

[0070] See Figure 2 The device 200 includes:

[0071] The receiving module 202 is used to receive input parameters sent by the caller;

[0072] The determining module 204 is used to determine the class corresponding to the input parameter in the class inheritance model; wherein, the class inheritance model includes multiple classes, each of which corresponds one-to-one with a knowledge category in the knowledge base, and the inheritance relationship between classes in the class inheritance model is determined by the hierarchical relationship between knowledge categories in the knowledge base;

[0073] Search module 206 is used to perform knowledge search in the knowledge category corresponding to the corresponding class in the knowledge base according to the input parameters;

[0074] Return module 208 is used to return the searched knowledge to the caller.

[0075] In one embodiment, the receiving module is specifically used to: receive input parameters sent by the caller through a standardized communication interface; wherein, the standardized communication interface is a unified interface provided by the class inheritance model to the caller, so that the caller can call knowledge in any knowledge category corresponding to any class through the standardized communication interface.

[0076] In one embodiment, the search module is further configured to adjust the input parameters using overloading technology before performing a knowledge search in the knowledge category corresponding to the corresponding class in the knowledge base based on the input parameters, so as to adapt to the input parameter requirements of the corresponding class.

[0077] In one embodiment, the apparatus further includes:

[0078] A construction module is used for the class inheritance model described by Guo Jian; the construction module includes:

[0079] A mapping unit is used to map each knowledge category in the knowledge base to a corresponding class.

[0080] The configuration unit is used to configure the inheritance relationship between classes according to the hierarchical relationship between knowledge categories in the knowledge base.

[0081] The determining unit is used to determine the class inheritance model corresponding to the knowledge base based on the classes with configured inheritance relationships.

[0082] In one embodiment, the configuration unit is specifically used to: for two classes corresponding to two levels of knowledge categories with a parent-child relationship, the subclass corresponding to the sub-knowledge category inherits the attributes and methods related to the attributes of the parent class corresponding to the parent knowledge category.

[0083] It is understood that explanations, specific implementation methods, beneficial effects, examples, etc. of the contents of the device provided in the embodiments of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0084] Thirdly, one embodiment of this specification provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the methods of any embodiment in the specification.

[0085] Specifically, a system or apparatus equipped with a storage medium may be provided, on which software program code implementing the functions of any of the embodiments described above is stored, and the computer (or CPU or MPU) of the system or apparatus may read and execute the program code stored in the storage medium.

[0086] In this case, the program code read from the storage medium can itself implement the function of any of the above embodiments, and therefore the program code and the storage medium storing the program code constitute part of the present invention.

[0087] Furthermore, it should be clear that not only can the program code read by the computer be executed, but also the operating system or other components operating on the computer can be instructed based on the program code to perform some or all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0088] Furthermore, it is understood that the program code read from the storage medium is written to the memory set in the expansion board inserted into the computer or to the memory set in the expansion module connected to the computer. Then, based on the instructions of the program code, the CPU or other components installed on the expansion board or expansion module execute some and all of the actual operations, thereby realizing the function of any of the above embodiments.

[0089] It is understood that explanations, specific implementation methods, beneficial effects, examples, etc. of the contents in the computer-readable medium provided in the embodiments of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0090] Fourthly, one embodiment of this specification provides a computing device including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, it implements the method of any embodiment of the specification.

[0091] It is understood that explanations, specific implementation methods, beneficial effects, examples, etc. of the computing device provided in the embodiments of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0092] It is understood that the structures illustrated in the embodiments of this specification do not constitute a specific limitation on the apparatus of the embodiments of this specification. In other embodiments of the specification, the above-described apparatus may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0093] The information interaction and execution process between the modules in the above-mentioned device and system are based on the same concept as the method embodiments in this specification, and the specific details can be found in the descriptions in the method embodiments in this specification, so they will not be repeated here.

[0094] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the apparatus embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0095] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this invention can be implemented using hardware, software, widgets, or any combination thereof. When implemented in software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium.

[0096] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solution of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for invoking a knowledge base, comprising: Receive input parameters sent by the caller; wherein, the input parameters are the category and attributes of the knowledge that the caller needs to access; Determine the class corresponding to the input parameter in the class inheritance model; wherein, the class inheritance model includes multiple classes, each of which corresponds one-to-one with a knowledge category in the knowledge base, and the inheritance relationship between classes in the class inheritance model is determined by the hierarchical relationship between knowledge categories in the knowledge base; Based on the input parameters, a knowledge search is performed from the corresponding knowledge category in the knowledge base for the corresponding class. The retrieved knowledge will be returned to the caller. The receipt of input parameters sent by the caller includes: receiving input parameters sent by the caller through a standardized communication interface; wherein, the standardized communication interface is a unified interface provided by the class inheritance model to the caller, so that the caller can call knowledge in any knowledge category corresponding to any class through the standardized communication interface.

2. The method according to claim 1, wherein, Before performing a knowledge search in the knowledge base based on the corresponding knowledge category of the corresponding class according to the input parameters, the method further includes: The input parameters are adjusted using overloading techniques to adapt to the input parameter requirements of the corresponding class.

3. The method according to claim 1, wherein, The formation process of the class inheritance model includes: Map each knowledge category in the knowledge base to a corresponding class; Configure the inheritance relationships between classes according to the hierarchical relationship between knowledge categories in the knowledge base; Based on the classes with configured inheritance relationships, determine the class inheritance model corresponding to the knowledge base.

4. The method according to claim 3, wherein, The step of configuring the inheritance relationship between classes according to the hierarchical relationship between knowledge categories in the knowledge base includes: For two classes corresponding to two levels of knowledge categories with a parent-child relationship, the subclass of the sub-knowledge category inherits the attributes and methods related to the attributes of the parent class of the parent knowledge category.

5. A knowledge base retrieval device, comprising: The receiving module is used to receive input parameters sent by the caller; wherein, the input parameters are the category and attributes of the knowledge that the caller needs to access; The determination module is used to determine the class corresponding to the input parameter in the class inheritance model; wherein, the class inheritance model includes multiple classes, each of which corresponds one-to-one with a knowledge category in the knowledge base, and the inheritance relationship between classes in the class inheritance model is determined by the hierarchical relationship between knowledge categories in the knowledge base; The search module is used to search for knowledge in the knowledge category corresponding to the corresponding class in the knowledge base according to the input parameters. The return module is used to return the searched knowledge to the caller; Specifically, the receiving module is used to: receive input parameters sent by the caller through a standardized communication interface; wherein the standardized communication interface is a unified interface provided by the class inheritance model to the caller, so that the caller can call knowledge in any knowledge category corresponding to any class through the standardized communication interface.

6. The apparatus according to claim 5, wherein, The search module is further configured to adjust the input parameters using overloading technology before performing a knowledge search in the knowledge category corresponding to the corresponding class in the knowledge base based on the input parameters, so as to adapt to the input parameter requirements of the corresponding class.

7. A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the method according to any one of claims 1 to 4.

8. A computing device comprising a memory and a processor, wherein the memory stores executable code, and the processor, when executing the executable code, implements the method according to any one of claims 1 to 4.

Images