Network management function recommendation method, apparatus, device, and computer storage medium

Abstract

The application discloses a network management function recommendation method, device and equipment and a computer storage medium, and relates to the technical field of wireless network management. In the method, the importance of each candidate network management function is evaluated in different user type dimensions according to function evaluation data sets corresponding to different user types, and a corresponding interactive function set is generated. The network management functions in the interactive function set are selected based on the importance of the functions for the user type, and thus the network management functions are more suitable for users of the corresponding type. Accordingly, when a user uses the functions, the user can quickly find the required functions, and the interactive efficiency of the network management functions is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more particularly to the field of wireless network management technology, providing a method, apparatus, device, and computer storage medium for recommending network management functions. Background Technology

[0002] With the development of wireless internet, the use of wireless networks has gradually spread to various industries such as government, catering, education, and healthcare. As the number of wireless network users surges, the seamless, unnoticed way of using wireless networks can no longer meet the needs of these businesses.

[0003] To provide a visual management platform for wireless network usage, cloud-based network management systems have emerged. Currently, the user types for these systems are gradually increasing, including not only general users but also professional maintenance personnel and users throughout the entire product lifecycle (pre-sales, sales, and after-sales). Similarly, as user needs grow, the functional categories of cloud-based network management systems are also expanding, encompassing areas such as network optimization, security management, intelligent analysis, and base station management, with each function further subdivided into numerous sub-functions. However, different users have different functional requirements. Accurately and quickly identifying the specific needs of different users is crucial for improving user experience.

[0004] Therefore, how to help users quickly find the functions they need in a complex system has become an urgent problem to be solved. Summary of the Invention

[0005] This application provides a method, apparatus, device, and computer storage medium for recommending network management functions, which helps users quickly find the functions they need in a complex system.

[0006] On the one hand, a method for recommending network management functions is provided, the method comprising:

[0007] Obtain the target function evaluation data set corresponding to the target user type. The target function evaluation data set includes the evaluation data required to evaluate multiple candidate network management functions in the dimension of the target user type.

[0008] Based on the target function evaluation data set, a target evaluation value set corresponding to the target user type is determined. Each evaluation value in the target evaluation value set is used to characterize the importance of a candidate network management function to the target user type.

[0009] Based on the target evaluation value set, at least one target network management function is determined from the plurality of candidate network management functions to generate the interaction function set for the target user type;

[0010] In response to a function display request initiated by a target user, a set of interactive functions for the target user type is sent to the target user, so that the cloud management network client displays functions based on the set of interactive functions, and the user type corresponding to the target user is the target user type.

[0011] On the one hand, a network management function recommendation device is provided, the device comprising:

[0012] The data acquisition unit is used to acquire a target function evaluation data set corresponding to the target user type. The target function evaluation data set includes the evaluation data required to evaluate multiple candidate network management functions in the dimension of the target user type.

[0013] The determining unit is configured to determine a set of target evaluation values ​​corresponding to the target user type based on the target function evaluation data set, wherein each evaluation value in the target evaluation value set is used to characterize the importance of a candidate network management function to the target user type;

[0014] The function set generation unit is used to determine at least one target network management function from the plurality of candidate network management functions based on the target evaluation value set, so as to generate the interaction function set of the target user type;

[0015] The function display unit is used to respond to a function display request initiated by a target user and send a set of interactive functions of the target user type to the target user, so that the cloud management network client can display functions based on the set of interactive functions, and the user type corresponding to the target user is the target user type.

[0016] Optionally, if the plurality of candidate network management functions include multiple levels of candidate network management functions, then the data acquisition unit is specifically used for:

[0017] For the candidate network management functions at the multiple levels, the following operations are performed respectively:

[0018] For each level of candidate network management function, a corresponding function transfer graph is generated based on the transfer relationship between each candidate network management function; wherein, in the function transfer graph, the edge between two nodes represents the transfer relationship between the two corresponding candidate network management functions.

[0019] Based on the functional transition graph, multiple relationship pairs are obtained, each relationship pair including two nodes that are connected by an edge in the functional transition graph;

[0020] The obtained multiple relationship pairs are determined as the functional graph evaluation data corresponding to the candidate network management functions at each level.

[0021] Optionally, when the target user type is a first user type, the functional evaluation data set includes evaluation data of multiple data types;

[0022] The determining unit is specifically used for:

[0023] For each type of evaluation data, determine the evaluation value corresponding to each of the multiple candidate network management functions;

[0024] The target evaluation value set is determined based on the weights of the various data types and the evaluation values ​​corresponding to the various candidate network management functions.

[0025] Optionally, the determining unit is specifically used for:

[0026] For each of the multiple candidate network management functions, the following operations are performed respectively:

[0027] For a candidate network management function, a first evaluation value is determined based on the historical interaction data of multiple users with the candidate network management function, as well as the historical interaction data of all candidate network management functions at the same level as the candidate network management function.

[0028] A second evaluation value is determined based on the evaluation values ​​of the multiple users for the candidate network management function;

[0029] A third evaluation value is determined based on the industry-specific evaluation value of the candidate network management function.

[0030] The fourth evaluation value is determined based on the functional graph evaluation data corresponding to the candidate network management functions at each level.

[0031] Optionally, the determining unit is specifically used for:

[0032] The fourth evaluation value of the plurality of candidate network management functions is initialized;

[0033] Based on the out-degree and in-degree of each node in the functional graph evaluation data, the fourth evaluation value after initialization of the multiple candidate network management functions is iteratively updated until the iteration termination condition is met; wherein, each iteration update includes:

[0034] For a candidate network management function, the fourth evaluation value of the candidate network management function is updated based on the in-degree of the target node in the function transition graph and the out-degree of the edges pointing to other nodes of the candidate network management function.

[0035] Optionally, the determining unit is specifically used for:

[0036] Based on the first evaluation value, the second evaluation value, the third evaluation value, the fourth evaluation value, and the weights of each data type dimension corresponding to each candidate network management function, the target evaluation value set corresponding to the first user type is determined.

[0037] Optionally, when the target user type is the second user type, the target function evaluation dataset includes evaluation values ​​of multiple users belonging to the second user type for at least one candidate network management function.

[0038] The determining unit is specifically used for:

[0039] The target function evaluation dataset is preprocessed to obtain a preprocessed target function evaluation dataset, which includes the evaluation values ​​of the multiple users for the multiple candidate network management functions.

[0040] For each candidate network management function, an evaluation value corresponding to that candidate network management function is determined based on the evaluation values ​​corresponding to the multiple users, so as to obtain the target evaluation value set corresponding to the second user type.

[0041] Optionally, the device further includes a function customization unit for:

[0042] Receive a function customization request sent by the target user, the function customization request being used to instruct that network management functions be displayed in a specified order;

[0043] Based on the network management function order specified in the function customization request, the set of interactive functions for the target user is updated, so that the cloud management network client displays functions based on the updated set of interactive functions.

[0044] On one hand, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the above methods.

[0045] On the one hand, a computer storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of any of the above methods.

[0046] On one hand, a computer program product is provided, comprising a computer program stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium, and executes the computer program, causing the computer device to perform the steps of any of the methods described above.

[0047] In this embodiment, a target function evaluation data set corresponding to the target user type is obtained. This data set includes evaluation data required to evaluate multiple candidate network management functions along the target user type dimension. Based on this data set, a target evaluation value set corresponding to the target user type is determined. Each evaluation value in the value set represents the importance of a candidate network management function to the target user type. Then, based on the evaluation value set corresponding to each target user type, at least one target network management function is determined from the multiple candidate network management functions to generate an interactive function set for the target user type. When a target user of the target user type initiates a function display request, the interactive function set for that user type can be sent to the target user, allowing the cloud network management client to display functions based on the interactive function set. This allows for the generation of corresponding interactive function sets based on different user types. The network management functions in this set are selected based on their importance to that user type, making them more suitable for that user type. Consequently, users can find the functions they need more quickly, improving the interactive efficiency of network management functions. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0049] Figure 1 This is a schematic diagram illustrating an application scenario provided in the embodiments of this application;

[0050] Figure 2 This is a schematic diagram of the cloud management network system architecture provided in the embodiments of this application;

[0051] Figure 3 A flowchart illustrating the network management function recommendation method provided in this application embodiment;

[0052] Figure 4 This is a schematic diagram illustrating the process of obtaining functional diagram evaluation data provided in the embodiments of this application;

[0053] Figure 5 Example diagram of obtaining functional diagram evaluation data provided in the embodiments of this application;

[0054] Figure 6 A schematic diagram illustrating the PR value calculation process provided in this application embodiment;

[0055] Figure 7A schematic diagram of a functional interface provided for an embodiment of this application;

[0056] Figure 8 This application provides a schematic diagram of a user-defined interface in an embodiment.

[0057] Figure 9 A schematic diagram of a network management function recommendation device provided in the embodiments of this application;

[0058] Figure 10 A schematic diagram of the composition structure of the electronic device provided in the embodiments of this application;

[0059] Figure 11 This is a schematic diagram of the composition structure of another electronic device using an embodiment of this application. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0061] It is understood that the following specific embodiments of this application involve user evaluation data, interaction data and other related data. When the various embodiments of this application are applied to specific products or technologies, relevant licenses or consents need to be obtained, and the collection, use and processing of related data need to comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0062] To facilitate understanding of the technical solutions provided in the embodiments of this application, some key terms used in the embodiments of this application will be explained below:

[0063] Network management functions include comprehensive management of network hardware and software to monitor, test, configure, analyze, evaluate and control network resources, achieving a better network experience. Network management functions include, but are not limited to, network optimization, security management, intelligent analysis and base station management. Of course, each function can be further subdivided into sub-functions.

[0064] User Types: In the cloud-managed network system, different user types tend to handle different content, and therefore use different network processing functions. User types include, but are not limited to, ordinary users, professional maintenance personnel, and full lifecycle users (including pre-sales, sales, and after-sales). Ordinary users are those who provide the network, while professional maintenance personnel are those who use the network. Through the cloud-managed network system, they can manage their own network services. Full lifecycle users (including pre-sales, sales, and after-sales) are defined based on the user's lifecycle stage.

[0065] Page Rank (PR) algorithm: Originally used to calculate the importance of web pages on the internet, the PR algorithm can actually be defined on any directed graph. The basic idea of ​​the PR algorithm is to define a random walk model, i.e., a first-order Markov chain, on the directed graph to describe the behavior of a random walker randomly visiting nodes along the graph. Under certain conditions, in the extreme case, the probability of visiting each node converges to a stationary distribution. The stationary probability value of each node is then its PR value, representing the node's importance.

[0066] Currently, the types of users and network management functions of cloud-based network systems are gradually increasing. Different users have different functional requirements, and being able to accurately and quickly identify the needs of different users is an important measure to improve the user experience.

[0067] In related technologies, the following methods are typically used when using network management functions:

[0068] (1) User-defined interaction based on a visual framework. In this method, users can drag and drop controls to customize the sorting of cloud management network functions. This method requires users to manually control the sorting, addition or hiding of functions. Customizing functions while carrying out busy business will cause a certain degree of decline in user experience. In addition, users need to be very familiar with each function, which has a high learning cost.

[0069] (2) Automated interaction based on user search: In this method, users can input function search conditions, and the cloud management network system matches functions that meet the conditions through predefined programs. This method makes users' impression of related functions relatively vague, and they cannot be sure whether related functions exist when using them in the future. They need to spend more time searching, such as checking manuals, which reduces the ease of use of the system to a certain extent.

[0070] Therefore, how to help users quickly find the functions they need in a complex system has become an urgent problem to be solved.

[0071] In practical applications, it has been found that different user types in cloud management network systems tend to have different processing preferences, and therefore use different network processing functions. If different functions can be provided to different users based on their user type, the matching degree between the displayed functions and the current user can be improved, and users can find the functions they need more quickly.

[0072] Based on this, embodiments of this application provide a method, apparatus, device, and computer storage medium for recommending network management functions. In this method, a target function evaluation data set corresponding to a target user type is obtained. This data set includes evaluation data required to evaluate multiple candidate network management functions along the target user type dimension. Based on the target function evaluation data set, a target evaluation value set corresponding to the target user type is determined. Each evaluation value in the evaluation value set characterizes the importance of a candidate network management function to the target user type. Then, based on the evaluation value set corresponding to each target user type, at least one target network management function is determined from the multiple candidate network management functions to generate an interactive function set for the target user type. When a target user of the target user type initiates a function display request, the interactive function set for the target user type can be sent to the target user, allowing the cloud network management client to display functions based on the interactive function set. This allows for the generation of corresponding interactive function sets according to different user types. The network management functions in this interactive function set are selected based on their importance to this type of user, making them more suitable for this type of user. Consequently, users can more quickly find the functions they need when using the functions, improving the interactive efficiency of network management functions.

[0073] Furthermore, considering the discrete nature of functional needs of ordinary users, the accuracy of measuring from a single dimension is low. Therefore, evaluation data from multiple data types and dimensions can be combined to assess the importance of each network management function, improve the accuracy of the evaluation results, and thus provide more accurate functional demonstrations to ordinary users.

[0074] The following is a brief introduction to the application scenarios to which the technical solutions of the embodiments of this application are applicable. It should be noted that the application scenarios described below are only for illustrating the embodiments of this application and are not intended to limit the scope. In specific implementation, the technical solutions provided by the embodiments of this application can be flexibly applied according to actual needs.

[0075] The solutions provided in this application can be applied to most network management scenarios, such as... Figure 1 The diagram shown is an application scenario provided by an embodiment of this application. In this scenario, a terminal device 101 and a cloud management server 102 may be included.

[0076] Terminal device 101 can be any device capable of installing and running the cloud management network client, such as a mobile phone, tablet computer (PAD), laptop computer, desktop computer, smart TV, smart in-vehicle device, and smart wearable device. Terminal device 101 can have the cloud management network client provided by cloud management server 102 installed. The application involved in this embodiment can be a software client, or a web page, mini-program, etc. The cloud management server 102 is the backend server corresponding to the software, web page, mini-program, etc., and there is no limitation on the specific type of client.

[0077] The cloud management server 102 is used to provide backend services for cloud management network clients. For example, it can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, i.e., content delivery network (CDN), as well as big data and artificial intelligence platforms, but it is not limited to these.

[0078] It should be noted that the network management function recommendation method in this embodiment can be executed by the cloud management server 102 alone, or by the cloud management server 102 and the terminal device 101 together. For example, the cloud management server 102 obtains function evaluation data sets corresponding to multiple user types, determines the evaluation value set corresponding to each user type based on the function evaluation data sets corresponding to each user type, and then determines at least one target network management function from multiple candidate network management functions based on the evaluation value sets corresponding to each user type, so as to generate an interactive function set for the corresponding user type, and returns the corresponding interactive function set based on the requested user type when the terminal device 101 requests to display it. Alternatively, the cloud management server 102 generates interactive function sets for various user types based on the above process, sends these interactive function sets to the terminal device 101, and then the terminal device selects the corresponding interactive function set for display based on the currently logged-in user type. This application does not make specific limitations here, and the following mainly uses the cloud management server 102 as an example for illustration.

[0079] Taking the execution of the above steps by the cloud management server 102 as an example, the cloud management server 102 may include one or more processors 1021, a memory 1022, and an I / O interface 1023 for interacting with the terminal. Furthermore, the cloud management server 102 may also be configured with a database 1024, which can be used to store the aforementioned functional evaluation data set, interactive function set, etc. The memory 1022 of the cloud management server 102 may also store program instructions for the network management function recommendation method provided in this application embodiment. When these program instructions are executed by the processor 1021, they can be used to implement the steps of the network management function recommendation method provided in this application embodiment, thereby realizing the network management function recommendation process.

[0080] In this embodiment, the terminal device 101 and the cloud management server 102 can communicate directly or indirectly through one or more networks 103. The network 103 can be a wired network or a wireless network. For example, the wireless network can be a mobile cellular network or a Wireless-Fidelity (WIFI) network. Of course, it can also be other possible networks, and this embodiment of the invention does not limit them.

[0081] It should be noted that, Figure 1 The examples shown are merely illustrative; in reality, the number of terminal devices and cloud management servers is unlimited and is not specifically limited in this embodiment.

[0082] See Figure 2 The diagram shown is an architectural representation of the cloud management network system provided in this application embodiment. This architecture includes a data storage and processing module, an importance ranking module, an automated conversion algorithm module, a customized framework module, and a front-end display module. These modules can be deployed on the terminal device 101 and the cloud management server 102. For example, the data storage and processing module, the importance ranking module, and the automated conversion algorithm module can be deployed on the cloud management server 102, while the customized framework module and the front-end display module can be deployed on the terminal device 101. Of course, other deployment methods can also be used, and this application embodiment does not impose any limitations on this.

[0083] (1) Data processing and storage module

[0084] It is used to store raw functional evaluation data, such as raw operation and maintenance personnel evaluation data, full lifecycle user evaluation data, user click rate data, industry evaluation data and general user evaluation data, etc., and the raw functional evaluation data is processed through data preprocessing methods to form initial functional evaluation data, such as cleaning and filtering.

[0085] (2) Importance Ranking Module

[0086] The data used for initial functional evaluation was compiled into importance data for each function.

[0087] (3) Automated conversion algorithm module

[0088] Automated interaction is a fully automated method that requires no user intervention. Through system recommendations, the front end displays recommended functions, which users can interact with to achieve the corresponding results. This interaction relies on the importance ranking calculated by the function importance module. The functional importance module and the automated interaction require conversion through an automated algorithm to form the data model to be interacted with, which is essentially a set of interaction data for each user type.

[0089] (4) Customized framework module

[0090] A customized framework combines two interaction methods: custom interaction and automated interaction. Custom interaction means that users can customize the functions and their order of display according to their preferences. Custom interaction is implemented using a visual framework and requires user intervention. A customized framework is essentially a customized interactive interface built upon automated interaction.

[0091] (5) Front-end display module

[0092] The front-end displays the corresponding interactive interface by switching user types.

[0093] The specific implementation of each of the above modules will be described in detail in the subsequent method embodiments, and will not be elaborated on here.

[0094] The following describes the network management function recommendation method provided by the exemplary embodiments of this application in conjunction with the application scenarios described above and with reference to the accompanying drawings. It should be noted that the above application scenarios are only shown to facilitate understanding of the spirit and principles of this application, and the embodiments of this application are not limited in any way in this respect.

[0095] See Figure 3 The diagram shown is a flowchart illustrating the network management function recommendation method provided in this application embodiment. The example uses a server as the execution entity. The specific implementation flow of this method is as follows:

[0096] Step 301: Obtain the target function evaluation data set corresponding to the target user type. The target function evaluation data set includes the evaluation data required to evaluate multiple candidate network management functions in the dimension of target user type.

[0097] In this embodiment of the application, the function of step 301 can be implemented by the above-mentioned data processing and storage module.

[0098] Among them, the candidate network management function can be an optional function item in the cloud management network system. It can be all the functions in the cloud management network system or some of the functions in the cloud management network system.

[0099] In one possible implementation, the scope of candidate network management functions can be pre-defined, and then the interaction content of related functional modules of the system can be customized according to the specified scope. For example, if the interaction content customization is specified for functions related to network optimization, then the functions related to network optimization will be selected as candidate network management functions.

[0100] It should be noted that in real-world scenarios, there may be multiple user types, and the process for obtaining the set of interactive functions for each user type is similar. Therefore, this paper takes one type, namely the target user type, as an example. In this embodiment, considering the different user types, the evaluation data required for evaluating the importance of candidate network functions can be different.

[0101] In one possible implementation, see Figure 2 As shown, the target user type can be any one of the following user types:

[0102] (1) Professional operation and maintenance personnel refers to users who are responsible for network operation and maintenance.

[0103] (2) Full lifecycle users are defined based on the user's lifecycle stage. For example, if a user has not yet purchased network services, they are in the pre-sales stage and are therefore considered a pre-sales user. If a user is purchasing network services, they are in the sales stage and are therefore considered a sales stage user. All of these users can be classified as full lifecycle users.

[0104] (3) Ordinary users refer to users other than the above user types, such as users who have purchased network services and then use them. These users can manage their network services through the network management functions provided by the client.

[0105] Corresponding to the above user types, the target function evaluation dataset for each user type can be as follows, which will be introduced one by one below.

[0106] (1) The target function evaluation data set of professional operation and maintenance personnel can include the evaluation values ​​of multiple professional operation and maintenance personnel for each candidate network management function. For example, an interface can be provided for professional operation and maintenance personnel to score, so that professional operation and maintenance personnel can score the candidate network management functions in the interface. For example, after using a candidate network management function, a prompt can be made to score, and the cloud management server records the score results.

[0107] (2) The target function evaluation dataset for all lifecycle users can include the evaluation values ​​of multiple lifecycle users for each candidate network management function. Similar to the professional operation and maintenance personnel mentioned above, an interface can be provided for all lifecycle users to rate the candidate network management functions. The users can rate the candidate network management functions on this interface. For example, after using a candidate network management function, they can be prompted to rate it, and the cloud management server will record the rating result.

[0108] (3) The target function evaluation dataset for ordinary users may include at least one of the following evaluation data:

[0109] 1) Historical interaction data of ordinary users, including the candidate network management functions that each user has interacted with in the past, such as the candidate network management functions that the user has clicked and used.

[0110] 2) Evaluation values ​​of each candidate network management function by multiple ordinary users.

[0111] 3) Evaluation values ​​of multiple candidate network management functions for the relevant industry.

[0112] 4) Functional graph evaluation data corresponding to the candidate network management functions at each level.

[0113] The system can be divided into levels according to the order of function development, such as homepage functions, sub-functions of the homepage functions, etc., and so on.

[0114] In one possible implementation, candidate network management functions at the same level can be understood as functions that can be displayed simultaneously, such as functions displayed on the same display page.

[0115] In practical applications, within the same level of functions, after using one function, a user may use the next function. That is, there is a possibility of transfer between functions at the same level. The transfer process between functions can be abstracted into a directed graph, and then the relationship between function transfer can be extracted from the graph to form initial graph data and form an evaluation data model.

[0116] See Figure 4 and Figure 5 As shown, Figure 4 This is a schematic diagram illustrating the process of acquiring evaluation data for candidate network management functions at the same level. Figure 4 This is an example diagram of the function graph evaluation data for candidate network management functions at the same level. Since the processing is similar for each level, we will focus on one level as an example here.

[0117] Step 401: For multiple candidate network management functions at the same level, generate corresponding function transfer graphs based on the transfer relationships between each candidate network management function; wherein, in the function transfer graph, the edge between two nodes represents the transfer relationship between the two corresponding candidate network management functions.

[0118] Among them, see Figure 5 As shown, multiple candidate network management functions at the same level include four functional items: network optimization, intelligent analysis, security management, and base station management. Within the same level, a user can only use one function at a time. There is a probability transition process between functions at the same level. By abstracting the functional transition relationships, a corresponding functional transition graph can be obtained, and the transition relationships between each function can be organized into an initial graph data model. For example... Figure 5 As shown in the function transfer graph, each node corresponds to a candidate network management function, and each edge represents a transfer relationship between two nodes. The direction of the edge indicates the direction of the transfer. Taking node ① as an example, it corresponds to the network optimization function node. After a user uses the network optimization function, the second user may use ①, ②, ③, or ④. Assuming the user uses ② the second time, the third user may use ①, ②, ③, or ④. Therefore, there can be edges from node ① to any other node (including itself), and the same applies to other nodes. Of course, in real-world scenarios, there may be dependencies between functions, meaning that a prerequisite function must be executed before other functions can be executed. This means that the number of edges for each node may vary.

[0119] It should be noted that, in the embodiments of this application, unless otherwise specified, the connection referred to is usually a direct connection between two nodes.

[0120] Step 402: Based on the function transition graph, obtain multiple relation pairs, each relation pair consisting of two nodes connected by an edge in the function transition graph.

[0121] In this embodiment, a relationship pair consists of two nodes connected by an edge. By statistically analyzing the edge relationships in the function transfer graph, multiple (v, u) relationship pairs can be obtained, where v represents the outgoing node of the edge and u represents the incoming node. Similarly, taking node ① as an example, we can obtain four relationship pairs: (①, ①), (①, ②), (①, ③), and (①, ④), and so on. The type of relationship pair can be represented and labeled using a directed graph, i.e., the labeling of the function transfer graph. Different labels are used for function transfer graphs at different levels.

[0122] Step 403: Determine the obtained multiple relationship pairs as the functional graph evaluation data corresponding to the candidate network management functions at each level.

[0123] Please continue reading below. Figure 3.

[0124] In this embodiment of the application, the data processing and storage module can also preprocess the evaluation data obtained above, such as data cleaning and filtering.

[0125] Step 302: Based on the target function evaluation data set, determine the target evaluation value set corresponding to the target user type. Each evaluation value in the target evaluation value set is used to characterize the importance of a candidate network management function to the target user type.

[0126] In this embodiment of the application, the process of step 302 can be achieved through... Figure 2 The importance ranking module shown is used to achieve this. Similarly, the method for determining importance differs depending on the user type; the following sections will introduce each user type separately.

[0127] When the target user type is the first user type, which can be a regular user, the target function evaluation data set includes evaluation data of the above-mentioned multiple data types. Then, for each data type, based on the evaluation data of that data type, the evaluation value corresponding to each candidate network management function can be determined. Finally, the evaluation values ​​of multiple data types are aggregated to obtain the final evaluation value corresponding to each candidate network management function.

[0128] Specifically, since the evaluation value calculation process is similar for each candidate network management function, we will take one candidate network management function as an example for introduction. For one candidate network management function, the evaluation value can include the following data types.

[0129] (1) When the data type is the user's historical interaction data, the first evaluation value can be determined based on the historical interaction data of multiple users on the candidate network management function, as well as the historical interaction data of all candidate network management functions at the same level as the candidate network management function.

[0130] In one possible implementation, taking a click operation as an example, the first evaluation value is the user click-through rate of the candidate network management function, which can be calculated as follows:

[0131]

[0132] Among them, func i If the i-th candidate network management function is represented, then characterizing func i User click-through rate, for func i The number of clicks, where N is the total number of clicks for candidate network management functions at the same level.

[0133] Generally speaking, the more frequently a user uses a feature, the more important it should be. Therefore, click-through rate can be used to help determine the importance of a feature.

[0134] (2) When the data type is the evaluation value of each candidate network management function by ordinary users, the second evaluation value can be determined based on the evaluation values ​​of multiple users for a candidate network management function.

[0135] In one possible implementation, for each candidate network management function, the average of the evaluation values ​​from various ordinary users can be used as a second evaluation value, denoted as...

[0136] (3) When the data type is the evaluation value of the industry for multiple candidate network management functions, the third evaluation value can be determined based on the evaluation value of the industry for a candidate network management function.

[0137] Among them, the functions that are important in the industry or in the users’ assessment are not necessarily the functions that are used frequently. Therefore, the importance of each function can be measured from different perspectives.

[0138] (4) When the data type is the functional graph evaluation data corresponding to the candidate network management function at each level, the fourth evaluation value can be determined based on the functional graph evaluation data corresponding to the candidate network management function at each level.

[0139] In one possible implementation, the PR value can be used to measure the importance of each candidate network management function; that is, the PR value of each candidate network management function can be calculated as a fourth evaluation value.

[0140] Specifically, the calculation of the PR value is an iterative process. It involves initializing the fourth evaluation value of multiple candidate network management functions, then iteratively updating the initialized fourth evaluation value of each node in the function graph evaluation data based on its out-degree and in-degree, until the iteration termination condition is met. For example, each function (func) can be... i The initial PR value is set to 1. Of course, other possible values ​​can also be set, and this application embodiment does not limit this.

[0141] See Figure 6 The diagram shown illustrates the process for calculating the PR value, which includes the following steps:

[0142] Step 601: Initialize the PR value for each candidate network management function.

[0143] Step 602: Update the PR value of each candidate network management function based on the out-degree and in-degree of each node in the functional graph evaluation data.

[0144] It should be noted that when the current iteration is the first update, the PR value is the initial value. If the current iteration is a subsequent update, the PR value is the PR value after the last update.

[0145] In each iteration update, for each candidate network management function, the fourth evaluation value of the candidate network management function can be updated based on the in-degree of the target node in the function transition graph and the out-degree of other nodes connected to the candidate network management function.

[0146] In one possible implementation, each function func can be performed using the following formula. i PR value update:

[0147]

[0148] in, It is func i The set of all in-degree functions, in order to Figure 5 Taking ① as an example, the in-degree function of ① includes other functions where there is a connecting edge and the connecting edge points to itself. It is func j The degree of output; N is the sum of all functions at the same level; α is the damping coefficient, which ranges from 0 to 1, and its empirical value is generally 0.85. Of course, it can also take other values, and this application embodiment does not limit this.

[0149] Step 603: Determine whether the updated PR meets the convergence criteria.

[0150] If the conditions are met, the process ends; otherwise, proceed to step 602 to continue execution.

[0151] by Figure 5 For example, each function can be represented by a function (func). i The initial PR value is set to 1. The updated PR value is calculated based on the above formula. After the update, it is necessary to determine whether the convergence condition is met. If it is met, the iteration stops. Otherwise, the iteration continues until the iteration reaches the convergence condition and the calculation stops. The final PR value is the final functional PR value, which is the fourth evaluation value.

[0152] Specifically, the convergence condition includes any one of the following conditions:

[0153] (1) The difference between the PR value in the previous iteration result and the current iteration result is less than the error threshold.

[0154] (2) Reach the maximum number of iterations set.

[0155] Furthermore, through the above process, the evaluation values ​​corresponding to each data type can be obtained. See Table 1 below for an example. Figure 5 Here is an example of the evaluation value for a given function.

[0156]

[0157] Table 1

[0158] Therefore, based on the evaluation values ​​of each candidate network management function for the aforementioned various data types, a corresponding set of target evaluation values ​​can be determined. For example, it can be calculated using the following formula:

[0159]

[0160] In one possible implementation, different data types have different degrees of influence on importance. Therefore, corresponding weights can be set for different data type dimensions. Then, based on the weights of each of the multiple data type dimensions and the evaluation values ​​corresponding to each of the multiple candidate network management functions, the target evaluation value set corresponding to the first user type can be determined. That is, based on the first evaluation value, second evaluation value, third evaluation value, and fourth evaluation value corresponding to each candidate network management function and the weights of each data type dimension, the target evaluation value set corresponding to the first user type can be determined.

[0161] When the target user type is the second user type, which can be professional operations and maintenance personnel or full lifecycle users, the target evaluation value set corresponding to the target function evaluation data set for the second user type is determined in the following way:

[0162] The target function evaluation dataset is preprocessed to obtain a preprocessed target function evaluation dataset. The preprocessed target function evaluation dataset includes evaluation values ​​of multiple users for multiple candidate network management functions. Then, for each candidate network management function, the evaluation value corresponding to the candidate network management function is determined based on the evaluation values ​​of multiple users, so as to obtain the target evaluation value set corresponding to the second user type.

[0163] In one possible implementation, the average of the evaluation values ​​of each user for each candidate network management function can be used as the final evaluation value.

[0164] In this embodiment, when the second user type can be a professional operations and maintenance personnel, the evaluation data obtained by the operations and maintenance personnel is organized into evaluation values ​​for each function to characterize the importance of each function (denoted as ). (See Table 2 below for details.) Figure 5The following is a ranking of the importance of each function when the user type is operations and maintenance personnel:

[0165]

[0166] Table 2

[0167] In this embodiment of the application, when the second user type can be a full-lifecycle user, the evaluation data of the full-lifecycle user is organized into evaluation values ​​for each function to characterize the importance of each function (denoted as ). (See Table 3 below for details.) Figure 5 The following is a ranking of the importance of each function when the user type is a full-lifecycle user:

[0168]

[0169] Table 3

[0170] Step 303: Based on the target evaluation value set, determine at least one target network management function from multiple candidate network management functions to generate a set of interactive functions for the target user type.

[0171] In this embodiment of the application, the process of step 303 can be implemented by the above-mentioned automated conversion algorithm in modules.

[0172] To automatically recommend network management functions to users, the evaluation values ​​of each network management function obtained above need to be transformed into an interactive data model through an automated algorithm. The automated transformation algorithm module converts these values ​​to create an interactive data model.

[0173] Specifically, the automated conversion algorithm module can pre-package a general tool for the quicksort algorithm, thereby obtaining the initial set of functions to be automatically displayed, as well as the importance ranking data corresponding to each candidate network management function in the set of functions, i.e. the target evaluation value set obtained above. Then, the general tool for the quicksort algorithm can be used to sort each evaluation value to obtain the display order of each candidate network management function, forming an automated set of interactive functions, i.e., the data model to be interacted with.

[0174] At this point, each user type can obtain the corresponding set of interactive functions through the above methods.

[0175] Step 304: In response to the function display request initiated by the target user, send the set of interactive functions for the target user type to the target user, so that the cloud management network client can display functions based on the set of interactive functions, and the user type corresponding to the target user is the target user type.

[0176] In this embodiment of the application, when it is necessary to present a corresponding interactive interface to the user, the various network management functions in the corresponding set of interactive functions can be displayed according to the user's user type.

[0177] It should be noted that feature display requests can be triggered in various situations. For example, when a user needs to implement a certain network management function, a page containing various network management functions needs to be presented to the user, which can trigger a feature display request. Alternatively, when a user clicks to enter a subpage of a certain network management function, and further display of the network management function of that function is required, then a corresponding page needs to be presented to the user, which can also trigger a feature display request.

[0178] Of course, in addition to feature demonstration requests, in other situations, a set of interactive features can also be pushed to the user. For example, when recommending a network service to the user, a recommendation request can be triggered to push the network management functions related to that network service to the user; or when the user needs to customize the display of function columns, a request can also be triggered to push the set of interactive functions of the user's type to the user so that the user can make a selection.

[0179] In one possible implementation, after obtaining the set of interactive functions as described above, the set of interactive functions corresponding to each user type can be distributed to each cloud management network client. In this way, the client can present the corresponding network management functions according to the currently logged-in user type.

[0180] In one possible implementation, when it is necessary to present a corresponding interactive interface to the user, the client can also send a function display request to the cloud management server. Then, the cloud management server can send the corresponding set of interactive functions to the target user based on the user type of the target user logged in by the client, so that the cloud management network client can display functions based on the set of interactive functions.

[0181] See Figure 7 The image shown is a schematic diagram illustrating one of the functionalities of an interface. Here, it still refers to the above. Figure 5 Taking the functions involved as an example, we can see that the interface displays them in descending order of importance, as mentioned above, so that users can quickly find the functions they need.

[0182] In this embodiment of the application, in addition to the above-mentioned automated recommendation function, customized interaction is also provided for users. That is, on the basis of automated interaction, users can also customize the function display.

[0183] Specifically, the initial functional interface can be displayed using the automated recommendation method described above. If a less experienced user is not satisfied with the currently displayed functions, they can choose to customize them, thereby triggering the client to send a function customization request to the cloud management server. The function customization request instructs the display to follow a specified order of network management functions. The cloud management server can then update the target user's set of interactive functions based on the order of network management functions specified in the function customization request. In this way, when the interface is displayed subsequently, the cloud management network client can display functions based on the updated set of interactive functions.

[0184] See Figure 8 The image shows a schematic of a user-defined interface. The automated recommendation interface displays buttons for custom functions. Clicking these buttons leads to the customization interface, where users can select desired functions, adjust their display order, and save their settings for future updates.

[0185] In summary, this embodiment of the application differentiates user types within the cloud management network and uses different evaluation metrics as support to customize and highlight network management functions that relevant users care about. Furthermore, users can customize their interaction methods, thereby achieving a hybrid interaction of automation and customization. This covers different cloud management network user types, including general users, professional operations and maintenance personnel, and users throughout the entire lifecycle, effectively catering to user preferences and accurately and quickly identifying the needs of different users. It allows users to quickly find target functions in a complex system, significantly improving the usability of the cloud management network system while greatly enhancing the user experience. Specifically, the customization for general users of the cloud management network not only considers user click-through rate as an evaluation metric but also integrates three major evaluation metrics: industry evaluation, general user evaluation, and feature PR value. By selecting evaluation data from different perspectives, the needs of general users of the cloud management network can be analyzed more accurately.

[0186] Furthermore, by adding datasets to customize interactions for other user types, or by modifying datasets to apply them to other types of network management systems, the applicability can be broadened.

[0187] Please see Figure 9 Based on the same inventive concept, embodiments of this application also provide a network management function recommendation device 90, which includes:

[0188] The data acquisition unit 901 is used to acquire a target function evaluation data set corresponding to the target user type. The target function evaluation data set includes the evaluation data required to evaluate multiple candidate network management functions in the dimension of the target user type.

[0189] The determining unit 902 is used to determine a set of target evaluation values ​​corresponding to the target user type based on the target function evaluation data set, wherein each evaluation value in the target evaluation value set is used to characterize the importance of a candidate network management function to the target user type;

[0190] The function set generation unit 903 is used to determine at least one target network management function from the plurality of candidate network management functions based on the target evaluation value set, so as to generate the interaction function set of the target user type;

[0191] The function display unit 904, in response to a function display request initiated by a target user, sends a set of interactive functions for the target user type to the target user, so that the cloud management network client displays functions based on the set of interactive functions, and the user type corresponding to the target user is the target user type.

[0192] Optionally, if the multiple candidate network management functions include multiple levels of candidate network management functions, then the data acquisition unit 901 is specifically used for:

[0193] For the candidate network management functions at the multiple levels, the following operations are performed respectively:

[0194] For each level of candidate network management function, a corresponding function transfer graph is generated based on the transfer relationship between each candidate network management function; wherein, in the function transfer graph, the edge between two nodes represents the transfer relationship between the two corresponding candidate network management functions.

[0195] Based on the functional transition graph, multiple relationship pairs are obtained, each relationship pair including two nodes that are connected by an edge in the functional transition graph;

[0196] The obtained multiple relationship pairs are determined as the functional graph evaluation data corresponding to the candidate network management functions at each level.

[0197] Optionally, when the target user type is the first user type, the target function evaluation dataset includes evaluation data of multiple data types and dimensions;

[0198] Unit 902 is then determined to be used specifically for:

[0199] For each type of evaluation data, determine the evaluation value corresponding to each of the multiple candidate network management functions;

[0200] The target evaluation value set is determined based on the weights of the various data types and the evaluation values ​​corresponding to the various candidate network management functions.

[0201] Optionally, unit 902 is specifically used for:

[0202] For each of the multiple candidate network management functions, the following operations are performed respectively:

[0203] For a candidate network management function, a first evaluation value is determined based on the historical interaction data of multiple users with the candidate network management function, as well as the historical interaction data of all candidate network management functions at the same level as the candidate network management function.

[0204] A second evaluation value is determined based on the evaluation values ​​of the multiple users for the candidate network management function;

[0205] A third evaluation value is determined based on the industry-specific evaluation value of the candidate network management function.

[0206] The fourth evaluation value is determined based on the functional graph evaluation data corresponding to the candidate network management functions at each level.

[0207] Optionally, unit 902 is specifically used for:

[0208] Initialize the fourth evaluation value for multiple candidate network management functions;

[0209] Based on the out-degree and in-degree of each node in the functional graph evaluation data, the fourth evaluation value after initialization of multiple candidate network management functions is iteratively updated until the iteration termination condition is met; wherein each iteration update includes:

[0210] For a candidate network management function, the fourth evaluation value of the candidate network management function is updated based on the in-degree of the target node in the function transition graph and the out-degree of the edges pointing to other nodes of the candidate network management function.

[0211] Optionally, unit 902 is specifically used for:

[0212] Based on the first evaluation value, second evaluation value, third evaluation value, and fourth evaluation value corresponding to each candidate network management function, as well as the weights of each data type dimension, the target evaluation value set corresponding to the first user type is determined.

[0213] Optionally, when the target user type is the second user type, the target function evaluation dataset includes the evaluation values ​​of multiple users belonging to the second user type for at least one candidate network management function.

[0214] Unit 902 is then determined to be used specifically for:

[0215] The target function evaluation dataset is preprocessed to obtain the preprocessed target function evaluation dataset, which includes the evaluation values ​​of multiple users for multiple candidate network management functions.

[0216] For each candidate network management function, an evaluation value corresponding to the candidate network management function is determined based on the evaluation values ​​corresponding to multiple users, so as to obtain the target evaluation value set corresponding to the second user type.

[0217] Optionally, the device also includes a function customization unit 905 for:

[0218] Receive a feature customization request sent by the target user. The feature customization request is used to instruct the network management functions to be displayed in the specified order.

[0219] Based on the order of network management functions specified in the function customization request, the set of interactive functions for the target user is updated, so that the cloud management network client can display functions based on the updated set of interactive functions.

[0220] The aforementioned device can generate corresponding sets of interactive functions based on different user types. The network management functions in these sets are selected based on their importance to this type of user, thus making them more suitable for this type of user. Consequently, when using these functions, users can find the functions they need more quickly, improving the interactive efficiency of network management functions.

[0221] This device can be used to execute the methods shown in the various embodiments of this application. Therefore, the functions that each functional module of this device can achieve can be referred to the description of the foregoing embodiments, and will not be repeated here.

[0222] Please see Figure 10 Based on the same technical concept, embodiments of this application also provide a computer device. In one embodiment, the computer device can be... Figure 1 The cloud management server shown is a computer device such as Figure 10 As shown, it includes a memory 1001, a communication module 1003, and one or more processors 1002.

[0223] The memory 1001 is used to store computer programs executed by the processor 1002. The memory 1001 may mainly include a program storage area and a data storage area. The program storage area may store the operating system and programs required to run instant messaging functions, etc.; the data storage area may store various instant messaging information and operation instruction sets, etc.

[0224] Memory 1001 may be volatile memory, such as random-access memory (RAM); memory 1001 may also be non-volatile memory, such as read-only memory, flash memory, hard disk drive (HDD), or solid-state drive (SSD); or memory 1001 may be any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory 1001 may be a combination of the above-described memories.

[0225] The processor 1002 may include one or more central processing units (CPUs) or digital processing units, etc. The processor 1002 is used to implement the recommended method for the aforementioned network management functions when calling computer programs stored in the memory 1001.

[0226] The communication module 1003 is used to communicate with terminal devices and other servers.

[0227] This application embodiment does not limit the specific connection medium between the memory 1001, communication module 1003, and processor 1002. This application embodiment... Figure 10 The memory 1001 and the processor 1002 are connected via a bus 1004, and the bus 1004 is in Figure 10 The diagram uses thick lines to describe the connections between other components; these are for illustrative purposes only and should not be considered limiting. Bus 1004 can be divided into address bus, data bus, control bus, etc. For ease of description, Figure 10 It is described using only a thick line, but does not indicate that there is only one bus or one type of bus.

[0228] The memory 1001 stores a computer storage medium containing computer-executable instructions for implementing the network management function recommendation method of this application embodiment. The processor 1002 is used to execute some or all of the steps of the network management function recommendation method of the above embodiments.

[0229] In another embodiment, the computer device can also be other computer devices, such as... Figure 1 The terminal device shown. In this embodiment, the structure of the computer device can be as follows. Figure 11As shown, it includes components such as: communication component 1110, memory 1120, display unit 1130, camera 1140, sensor 1150, audio circuit 1160, Bluetooth module 1170, processor 1180, etc.

[0230] The communication component 1110 is used to communicate with the server. In some embodiments, it may include a Circuit-Based Wireless Fidelity (WiFi) module. WiFi is a short-range wireless transmission technology, and computer devices can use WiFi modules to help users send and receive information.

[0231] The memory 1120 can be used to store software programs and data. The processor 1180 executes various functions of the terminal device and data processing by running the software programs or data stored in the memory 1120. The memory 1120 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. The memory 1120 stores an operating system that enables the terminal device to run. In this application, the memory 1120 may store the operating system and various applications, and may also store code that executes the recommended method for network management functions in the embodiments of this application.

[0232] The display unit 1130 can also be used to display information input by the user or information provided to the user, as well as various menus of the terminal device, in a graphical user interface (GUI). Specifically, the display unit 1130 may include a display screen 1132 disposed on the front of the terminal device. The display screen 1132 may be configured as a liquid crystal display, a light-emitting diode, or the like. The display unit 1130 can be used to display various network management function recommendations or interactive pages in the embodiments of this application.

[0233] The display unit 1130 can also be used to receive input digital or character information and generate signal inputs related to user settings and function control of the terminal device. Specifically, the display unit 1130 may include a touch screen 1131 disposed on the front of the terminal device, which can collect touch operations of the user on or near it, such as clicking a button, dragging a scroll box, etc.

[0234] The touchscreen 1131 can be placed over the display screen 1132, or the touchscreen 1131 and the display screen 1132 can be integrated to realize the input and output functions of the terminal device. After integration, it can be referred to as a touch display screen. In this application, the display unit 1130 can display the application program and the corresponding operation steps.

[0235] Camera 1140 can be used to capture still images, which users can then post comments on via an application. There can be one or multiple cameras 1140. An object is projected onto a photosensitive element through a lens, generating an optical image. This photosensitive element can be a charge-coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the light signal into an electrical signal, which is then transmitted to a processor 1180 to be converted into a digital image signal.

[0236] The terminal device may also include at least one sensor 1150, such as an accelerometer 1151, a proximity sensor 1152, a fingerprint sensor 1153, and a temperature sensor 1154. The terminal device may also be equipped with other sensors such as a gyroscope, barometer, hygrometer, thermometer, infrared sensor, light sensor, and motion sensor.

[0237] Audio circuitry 1160, speaker 1161, and microphone 1162 provide an audio interface between the user and the terminal device. Audio circuitry 1160 converts received audio data into electrical signals, which are then transmitted to speaker 1161, where they are converted into sound signals for output. The terminal device can also be equipped with volume buttons for adjusting the volume of the sound signal. Conversely, microphone 1162 converts collected sound signals into electrical signals, which are received by audio circuitry 1160, converted into audio data, and then output to communication component 1110 for transmission to, for example, another terminal device, or to memory 1120 for further processing.

[0238] The Bluetooth module 1170 is used to interact with other Bluetooth devices that also have a Bluetooth module via the Bluetooth protocol. For example, a terminal device can establish a Bluetooth connection with a wearable computer device (such as a smartwatch) that also has a Bluetooth module through the Bluetooth module 1170, thereby exchanging data.

[0239] The processor 1180 is the control center of the terminal device, connecting various parts of the terminal through various interfaces and lines. It executes various functions and processes data by running or executing software programs stored in the memory 1120 and calling data stored in the memory 1120. In some embodiments, the processor 1180 may include one or more processing units; the processor 1180 may also integrate an application processor and a baseband processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the baseband processor mainly handles wireless communication. It is understood that the baseband processor may not be integrated into the processor 1180. In this application, the processor 1180 can run the operating system, applications, user interface display and touch response, as well as the network management function recommendation method of this application embodiment. Furthermore, the processor 1180 is coupled to the display unit 1130.

[0240] In some possible implementations, various aspects of the network management function recommendation method provided in this application can also be implemented as a program product, which includes program code. When the program product is run on a computer device, the program code is used to cause the computer device to perform the steps in the network management function recommendation method according to the various exemplary embodiments of this application described above. For example, the computer device can perform the steps of the various embodiments.

[0241] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0242] The program product of the embodiments of this application may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a computing device. However, the program product of this application is not limited thereto. In this application, the readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with a command execution system, apparatus, or device.

[0243] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. This propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting a program for use by or in conjunction with a command execution system, apparatus, or device.

[0244] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0245] The program code for performing the operations of this application can be written in any combination of one or more programming languages. For example, the program code executed in the aforementioned cloud management server can use object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code for the client in the aforementioned terminal device can use programming languages ​​such as JavaScript, front-end frameworks React and Vue. The program code can be executed entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0246] It should be noted that although several units or sub-units of the device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units.

[0247] Furthermore, although the operations of the method of this application are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0248] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0249] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0250] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for recommending network management functions, characterized in that, The method includes: Obtain the target function evaluation data set corresponding to the target user type. The target function evaluation data set includes the evaluation data required to evaluate multiple candidate network management functions in the dimension of the target user type. Based on the target function evaluation data set, a target evaluation value set corresponding to the target user type is determined. Each evaluation value in the target evaluation value set is used to characterize the importance of a candidate network management function to the target user type. Based on the target evaluation value set, at least one target network management function is determined from the plurality of candidate network management functions to generate the interaction function set for the target user type; In response to a function display request initiated by a target user, a set of interactive functions for the target user type is sent to the target user, so that the cloud management network client displays functions based on the set of interactive functions, and the user type corresponding to the target user is the target user type; The plurality of candidate network management functions include multiple levels of candidate network management functions, and the acquisition of the target function evaluation data set includes: For the candidate network management functions at the multiple levels, the following operations are performed respectively: For each level of candidate network management function, a corresponding function transfer graph is generated based on the transfer relationship between each candidate network management function; wherein, in the function transfer graph, the edge between two nodes represents the transfer relationship between the two corresponding candidate network management functions. Based on the functional transition graph, multiple relationship pairs are obtained, each relationship pair including two nodes that are connected by an edge in the functional transition graph; The obtained multiple relationship pairs are determined as the functional graph evaluation data corresponding to the candidate network management functions at each level.

2. The method as described in claim 1, characterized in that, When the target user type is the first user type, the functional evaluation data set includes evaluation data of multiple data types; The step of determining the target evaluation value set corresponding to the target user type based on the target function evaluation data set includes: For each type of evaluation data, determine the evaluation value corresponding to each of the multiple candidate network management functions; The target evaluation value set is determined based on the weights of the various data types and the evaluation values ​​corresponding to the various candidate network management functions.

3. The method as described in claim 2, characterized in that, The process of determining the evaluation values ​​for each of the multiple candidate network management functions, for each type of evaluation data, includes: For each of the multiple candidate network management functions, the following operations are performed respectively: For a candidate network management function, a first evaluation value is determined based on the historical interaction data of multiple users with the candidate network management function, as well as the historical interaction data of all candidate network management functions at the same level as the candidate network management function. A second evaluation value is determined based on the evaluation values ​​of the multiple users for the candidate network management function; A third evaluation value is determined based on the industry-specific evaluation value of the candidate network management function. The fourth evaluation value is determined based on the functional graph evaluation data corresponding to the candidate network management functions at each level.

4. The method as described in claim 3, characterized in that, Based on the function graph evaluation data corresponding to the candidate network management functions at each level, a fourth evaluation value is determined, including: The fourth evaluation value of the plurality of candidate network management functions is initialized; Based on the out-degree and in-degree of each node in the functional graph evaluation data, the fourth evaluation value after initialization of the multiple candidate network management functions is iteratively updated until the iteration termination condition is met; wherein, each iteration update includes: For a candidate network management function, the fourth evaluation value of the candidate network management function is updated based on the in-degree of the target node in the function transition graph and the out-degree of the edges pointing to other nodes of the candidate network management function.

5. The method as described in claim 3, characterized in that, Based on the weights of the various data types and the evaluation values ​​corresponding to the various candidate network management functions, the target evaluation value set is determined, including: The target evaluation value set is determined based on the first evaluation value, the second evaluation value, the third evaluation value, the fourth evaluation value, and the weights of each data type dimension corresponding to each candidate network management function.

6. The method according to any one of claims 1 to 5, characterized in that, When the target user type is the second user type, the target function evaluation data set includes the evaluation values ​​of multiple users belonging to the second user type for at least one candidate network management function; Based on the target function evaluation data set, a target evaluation value set corresponding to the target user type is determined, including: The target function evaluation dataset is preprocessed to obtain a preprocessed target function evaluation dataset, which includes the evaluation values ​​of the multiple users for the multiple candidate network management functions. For each candidate network management function, an evaluation value corresponding to that candidate network management function is determined based on the evaluation values ​​corresponding to the multiple users, so as to obtain the target evaluation value set corresponding to the second user type.

7. The method according to any one of claims 1 to 5, characterized in that, After sending the set of interactive functions for the target user type to the target user in response to a function display request initiated by the target user, the method further includes: Receive a function customization request sent by the target user, the function customization request being used to instruct that network management functions be displayed in a specified order; Based on the network management function order specified in the function customization request, the set of interactive functions for the target user is updated, so that the cloud management network client displays functions based on the updated set of interactive functions.

8. A network management function recommendation device, characterized in that, The device includes: The data acquisition unit is used to acquire a target function evaluation data set corresponding to the target user type. The target function evaluation data set includes the evaluation data required to evaluate multiple candidate network management functions in the dimension of the target user type. The determining unit is configured to determine a set of target evaluation values ​​corresponding to the target user type based on the target function evaluation data set, wherein each evaluation value in the target evaluation value set is used to characterize the importance of a candidate network management function to the target user type; The function set generation unit is used to determine at least one target network management function from the plurality of candidate network management functions based on the target evaluation value set, so as to generate the interaction function set of the target user type; The function display unit is used to respond to a function display request initiated by a target user and send the set of interactive functions of the target user type to the target user, so that the cloud management network client displays functions based on the set of interactive functions, and the user type corresponding to the target user is the target user type; The plurality of candidate network management functions include multiple levels of candidate network management functions, and the acquisition of the target function evaluation data set includes: For the candidate network management functions at the multiple levels, the following operations are performed respectively: For each level of candidate network management function, a corresponding function transfer graph is generated based on the transfer relationship between each candidate network management function; wherein, in the function transfer graph, the edge between two nodes represents the transfer relationship between the two corresponding candidate network management functions. Based on the functional transition graph, multiple relationship pairs are obtained, each relationship pair including two nodes that are connected by an edge in the functional transition graph; The obtained multiple relationship pairs are determined as the functional graph evaluation data corresponding to the candidate network management functions at each level.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 7.

Images