A method and apparatus for cooperative network sensing
By establishing a collaborative mechanism in network perception, each functional branch shares intermediate data and perception results, solving the problems of incompleteness and inaccuracy caused by independent implementation, and achieving more efficient network perception.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- FIBERHOME TELECOMMUNICATION TECHNOLOGIES CO LTD
- Filing Date
- 2025-12-25
- Publication Date
- 2026-07-24
AI Technical Summary
In existing technologies, the various network sensing functional branches are independent of each other, leading to problems such as incomplete consideration of factors and insufficient precision in sensing operations.
The system collects raw data from each functional branch to generate intermediate data, and after data transformation and security processing, it shares the data with other branches to generate perception results and provide feedback on the operation execution results, thus establishing a trusted mechanism for collaborative perception.
Resource sharing among functional branches was achieved, improving the authenticity and real-time nature of the sensing results, reducing redundancy in repeated data collection and processing, and increasing resource utilization.
Smart Images
Figure CN121690827B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of data communication technology, specifically to a collaborative network sensing method and apparatus. Background Technology
[0002] The internet has experienced rapid development over the past few decades, significantly impacting people's lives, work, and studies. However, this development inevitably makes current and future networks increasingly complex, making network operation, deployment, control, management, optimization, and reconstruction more challenging. This creates an increasingly urgent need for network sensing. However, network sensing itself presents several problems and challenges that need to be addressed. On the one hand, if the network cannot achieve real-time, accurate, and comprehensive sensing, the foundation for providing matching services to users will be lost. On the other hand, as networks become more complex, implementing network sensing functions becomes increasingly difficult.
[0003] Currently, the implementation of various branches of network awareness (such as network service awareness, network status awareness, network security awareness, etc.) is independent of each other. These functional branches are largely unconnected, leading to duplication and waste in implementation and deployment. However, the network is actually an organic whole, and changes in the state of any one aspect can have a fundamental impact on others. Therefore, implementing functional branches independently without interrelationships is not a good solution.
[0004] Furthermore, it is important to emphasize that the rapid evolution of networks places increasingly higher demands on network sensing technologies. This makes it difficult and inefficient to implement network sensing functions solely based on a single network function branch. Moreover, relying on a single function branch to achieve specific network sensing functions can lead to insufficient consideration of factors, incomplete data usage, and imprecise post-sensing operations. Summary of the Invention
[0005] This application provides a collaborative network sensing method and apparatus, which can solve the technical problems in the prior art where each functional branch is independent of the others and relies on a single network functional branch, resulting in incomplete consideration of factors and insufficient accuracy of the operation after sensing.
[0006] In a first aspect, embodiments of this application provide a cooperative network sensing method, the method comprising: Each functional branch of the network-aware system collects raw data, performs preprocessing to generate intermediate data, and then shares the intermediate data with other functional branches after data transformation and security processing. Each functional branch generates perception results based on the received and its own intermediate data, and shares the perception results that can be used by other functional branches; at the same time, it generates operation suggestions based on the perception results and executes them, feeds back the operation execution results to itself, and shares them with other functional branches that have an impact.
[0007] In conjunction with the first aspect, in one implementation, the network awareness of each functional branch includes: The information stage is used to collect raw data and generate intermediate data. The perception phase is used to output its own perception results and perception results that can be used by other functional branches; The operation phase is used to generate and execute operation suggestions, as well as to feed back the results and impact of the operation to other functional branches.
[0008] In conjunction with the first aspect, in one implementation, the data conversion and security processing includes at least one of the following processes: de-identification processing, equivalence conversion processing, encryption processing, and two-branch negotiation processing.
[0009] In conjunction with the first aspect, in one implementation, the intermediate data is shared to other functional branches after undergoing equivalence conversion processing. The equivalence conversion processing method includes: Map the intermediate dataset of the source functional branch to the intermediate dataset of the destination functional branch; The source function branch converts the intermediate dataset to a third-party dataset, and the destination function branch maps the third-party dataset to the intermediate dataset of this branch. The source function branch's intermediate dataset is encoded and converted to an intermediate dataset that avoids data exposure. The destination function branch then receives this intermediate dataset and converts it into its own intermediate dataset.
[0010] In conjunction with the first aspect, in one implementation, the perception results that can be utilized by other functional branches include: target perception results that are directly used by other functional branches, and basic perception results that are used for further processing by other functional branches.
[0011] In conjunction with the first aspect, in one implementation, sharing the results of the operation execution with other functional branches that have an impact includes: Share only the completion of this function branch operation, or share which network devices were affected by the operation.
[0012] In conjunction with the first aspect, in one embodiment, the method further includes: Data sharing between two or more functional branches follows a trusted mechanism, which includes zero-trust mechanism, federation mechanism, call home mechanism and third-party mechanism; The zero-trust mechanism is based on message authentication, the federation mechanism is based on group negotiation, the callHome mechanism is based on the authorization of the function owner, and the third-party mechanism is based on the verification of third-party authentication.
[0013] In conjunction with the first aspect, in one implementation, in the message authentication of the message, each message exchange is authorized by both parties; in the group negotiation, a mutually trusted group is established through negotiation between the two parties; in the authorization of the function master, both parties are authenticated by the function master; in the verification of the third-party authentication, both parties are authenticated by a third-party entity that has passed the mutual trust mechanism; wherein, the two parties are two functional branches exchanging data.
[0014] In conjunction with the first aspect, in one implementation, the functional branches of network awareness include a network traffic awareness functional branch, a network service awareness functional branch, a network status awareness functional branch, a demand awareness functional branch, and a network resource awareness functional branch.
[0015] Secondly, embodiments of this application provide a collaborative network sensing device, disposed in various functional branches of network sensing, the device comprising: The intermediate data module is used to collect raw data and preprocess it to generate intermediate data. It is also used to perform data transformation and security processing on the intermediate data and then share it to other functional branches. The perception module is used to generate perception results based on the received and its own intermediate data, and to share the perception results that can be used by other functional branches. The execution module is used to generate operation suggestions based on the perception results and execute them, feed back the operation execution results to its own functional branch, and share them with other functional branches that have an impact.
[0016] The beneficial effects of the technical solutions provided in this application include: Each functional branch of the network sensing system collects raw data, preprocesses it to generate intermediate data, and shares this intermediate data with other functional branches after data transformation and security processing. Each functional branch receives and processes sensing results from other functional branches, generates operation suggestions, executes them, and feeds back the operation execution results and their impact to other functional branches. This application breaks down the barriers between functional branches, enabling them to remain relatively independent while collaborating with each other. It solves the technical problems of incomplete consideration of factors and insufficient accuracy of post-sensing operations caused by current reliance on a single network functional branch.
[0017] Intermediate data and perception results can be shared among functional branches, avoiding repeated collection and preprocessing of the same raw data, eliminating data redundancy, and significantly improving resource utilization. After any branch performs an operation, the operation result and its impact range are fed back to other functional branches, triggering their processing, making the perception results more realistic, reliable, and real-time. Attached Figure Description
[0018] Figure 1 This is a schematic diagram of the collaborative network perception method according to an embodiment of this application; Figure 2 This diagram illustrates the three main stages of implementing the network sensing function in an embodiment of this application. Figure 3 This is a schematic diagram illustrating the implementation process of a single functional branch in an embodiment of this application; Figure 4 This is a schematic diagram illustrating the collaborative network perception method implemented by multiple functional branches in an embodiment of this application. Figure 5 This is a schematic diagram of the logical functional structure in the embodiments of this application; Figure 6 This is a schematic diagram of the deep learning model in the collaborative network perception method of this application; Figure 7 This is a schematic diagram illustrating the implementation process of the collaborative network sensing method in this application; Figure 8 This is a schematic diagram illustrating an embodiment of the security mechanism of this application; Figure 9 This is a schematic diagram of an embodiment of the trusted mechanism of this application. Detailed Implementation
[0019] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.
[0020] Network awareness is a set of technologies and methods that enable network operators, network owners, network service providers, and others to obtain information such as the distribution of network traffic, the network services carried in the network, network resources and their utilization, the current state of the network, real-time user demand in the network, and other relevant real-time network information.
[0021] Therefore, network awareness also includes multiple functional branches, such as network traffic awareness, service awareness, security awareness, status awareness, resource awareness, demand awareness, and environment awareness. The implementation of these functional awarenesses requires corresponding technologies and methods.
[0022] Collaborative network sensing is reflected in the interaction and information sharing of the functional branches of network sensing at various stages, including intermediate data interaction, sensing result interaction, and post-sensing operation feedback.
[0023] Logically, the functional branches of network sensing mainly consist of an information phase, a sensing phase, and an operation phase. In the current implementation of network sensing functions, each functional branch is relatively independent, and the information interaction in these three phases does not involve information interaction with other functional branches.
[0024] This application provides a collaborative network sensing method, which aims to break down the barriers between functional branches in the current network sensing, so that each functional branch can cooperate with each other while maintaining relative independence.
[0025] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.
[0026] Firstly, such as Figure 1 As shown in the figure, this application provides a cooperative network sensing method, which includes: S1: Each functional branch of the network-aware system collects raw data, performs preprocessing to generate intermediate data, and then shares the intermediate data with other functional branches after data transformation and security processing.
[0027] S2: Each functional branch generates perception results based on the received and its own intermediate data, and shares the perception results that can be used by other functional branches; at the same time, it generates operation suggestions based on the perception results and executes them, feeds back the operation execution results to itself, and shares them with other functional branches that have an impact.
[0028] Specifically, the functional branches of network awareness include network traffic functional branch, network service functional branch, network status functional branch, demand functional branch, and network resource functional branch, etc.
[0029] The raw data collected by each branch of the network sensing system generally cannot be used by other branches. There are three limitations: data owner authorization, management measures, and technical mechanism constraints. Therefore, this application does not consider the processing mechanism for the raw data of each functional branch.
[0030] In this embodiment, connections are established between multiple functional branches of intelligent network perception. Intermediate data, after data conversion and security processing, and perception results can be shared. After the perception operation is executed, it can be applied to multiple functional branches, enabling resource sharing among the functional branches, improving resource utilization, and reducing implementation costs.
[0031] In this embodiment, the raw data collected by each functional branch is still limited to use within that functional branch and is not made available to other network awareness functional branches. Intermediate data cannot be directly shared to other network awareness functional branches either. However, after data transformation and security processing, intermediate data can be processed by the functional branch itself and submitted to other functional branches as needed, and can be shared with other functional branches.
[0032] In the above method, the original data is preprocessed to generate intermediate data. This preprocessing is done through ETL (Extraction Transformation Loading) of big data. ETL process extracts, transforms, and loads the original data to generate intermediate data.
[0033] The intermediate data undergoes data transformation and security processing, including at least one of the following: anonymization, equivalence conversion, encryption, and two-branch negotiation. Two-branch negotiation refers to a process defined and negotiated by the two functional branches that need to exchange data. In this embodiment, anonymization protects data privacy (e.g., removing user identifiers) and prevents privacy leaks. Equivalence conversion adapts data formats (e.g., converting business distribution data into QoS requirement data formats), making the data usable by other functional branches. Encryption ensures secure data transmission (e.g., encrypting intermediate data) and prevents man-in-the-middle attacks. Two-branch negotiation allows for the negotiation of specific security policies based on business needs, ensuring compliance of data sharing. Therefore, the intermediate data processed in the above way can be shared between different functional branches.
[0034] Furthermore, each functional branch sets up an intermediate dataset. After undergoing equivalence transformation, the intermediate data is shared with other functional branches. The equivalence transformation includes the following three methods: Map the intermediate dataset of the source function branch to the intermediate dataset of the destination function branch, and the destination function branch accepts it directly.
[0035] The intermediate dataset of the source functional branch is converted to a third-party dataset, and the third-party dataset is mapped to the intermediate dataset of the destination functional branch. The third-party dataset is set outside of all functional branches and can be set within the data platform or system.
[0036] The source function branch's intermediate dataset is encoded and converted to an intermediate dataset that avoids data exposure. The destination function branch then receives this intermediate dataset and converts it into its own intermediate dataset.
[0037] The aforementioned source functional branch refers to the functional branch that shares data, while the destination functional branch refers to the functional branch that receives the shared data. These three methods implement a security mechanism for functional branches to perceive data.
[0038] Each functional branch generates a perception result based on the received intermediate data and its own intermediate data. If no intermediate data is received, it generates a perception result based on its own intermediate data. The generated perception results include the target perception results of this functional branch, such as the business distribution of the business perception functional branch and the potential user needs of the demand perception functional branch. In addition, the perception results also include perception results that can be used by other functional branches, which can be regarded as byproducts of this functional branch and submitted to the functional branches that can use them.
[0039] Furthermore, the perception results that can be utilized by other functional branches include two scenarios. One is the target perception results directly used by other functional branches. For example, functional branch A directly outputs the perception results needed by functional branch B. For instance, the service perception functional branch, while obtaining the service distribution, also outputs the QoS and resource requirements of the corresponding users, sharing this as a byproduct with functional branch B. The other scenario is the basic perception results used for further processing by other functional branches. For example, functional branch A obtains the service distribution and service transmission status of a certain user, and functional branch B can further perceive the corresponding user's QoS and resource requirements based on the shared user information.
[0040] In the above process, each functional branch generates and executes operation suggestions based on the perception results. Specifically, after confirming that the operation suggestions need to be executed, each functional branch will implement them on network devices or control systems. These operations not only directly affect the functional branch itself but may also have a significant impact on other functional branches. Therefore, in addition to feeding back the operation execution results to itself for iteration within the functional branch, the results are also shared with other affected functional branches, enabling each functional branch to take appropriate action and achieving collaboration and sharing of perception results.
[0041] Furthermore, sharing the operation execution results to other functional branches that have an impact includes two scenarios: one is sharing only the completion of the operation within the current functional branch; the other is sharing which network devices were affected by the operation. For the scenario where only the completion of the operation within the current functional branch is shared, the functional branch that receives the operation execution results executes the collaborative network awareness method from the beginning, i.e., it re-collects the original data and iterates the execution process of that functional branch once. For the scenario where the impact on which network devices is shared, only the original data of the affected network devices is updated, and then the execution process of that functional branch is iterated once. In this embodiment, after the operation suggestions of each functional branch are executed, in addition to being fed back to the current functional branch, they are also shared to other functional branches that have an impact, making the results of each functional branch more realistic, reliable, and real-time. This method introduces extra-model inputs to each functional branch and a model reconstruction mechanism based on extra-model inputs, significantly improving the overall model value / cost.
[0042] Furthermore, data sharing between two or more functional branches follows a trusted mechanism, which includes zero-trust, federation, call-home, and third-party mechanisms. Zero-trust is based on message authentication, federation on group negotiation, call-home on authorization by the functional master, and third-party mechanisms on verification by third-party authentication.
[0043] The corresponding processing methods for the above four trust mechanisms include: In message authentication, each message exchange is authorized by both parties. In group negotiation, a mutually trusted group is established through negotiation between the two parties. In the authorization of the function master, both parties are authenticated by the function master. In the verification of third-party authentication, both parties are authenticated by a third-party entity that has passed the mutual trust mechanism. In each processing method, the two parties are two functional branches sharing data.
[0044] Through the security and trust mechanisms of the aforementioned functional branches, the reuse of intermediate data and perception results does not affect the security and trustworthiness of the data, and the sharing of data will not cause privacy and security issues, nor will it infringe on data property rights.
[0045] Simulation analysis shows that the collaborative network perception method proposed in this application has significant improvements in perception matching degree, perception real-time performance, and perception resource utilization, with the perception matching degree being improved by more than 20%.
[0046] like Figure 2 As shown, the three main stages of network perception functionality implementation include the information stage, the perception stage, and the operation stage. These can be regarded as the high-level architecture and foundation for the functional branch design and implementation of network perception.
[0047] The information stage is used to collect raw data and generate intermediate data, focusing on the acquisition and preprocessing of data, information, and knowledge required for this functional branch.
[0048] In the perception phase, based on the acquired information, the corresponding perception results are obtained, which are used to output the perception results of the user and the perception results that can be used by other functional branches.
[0049] During the operation phase, after obtaining the perception results, some suggested operations will be obtained. This phase will execute these suggested operations, report and evaluate the results of the execution, generate operation suggestions and execute them, and feed back the operation execution results and impacts to other functional branches.
[0050] like Figure 3 The diagram shows the implementation flow of a single functional branch, which includes the following steps: a1: Functional branch performs raw data probing and collects raw data.
[0051] a2: Preprocess the raw data to generate intermediate data.
[0052] a3: Functional branches generate perception results through intermediate data.
[0053] a4: Generate operation suggestions based on the perception results.
[0054] a5: Execute the operation and return the result to itself.
[0055] In the above steps, both a2 and a3 are implemented based on machine learning methods, with intermediate data as input and perception results as output.
[0056] like Figure 4 The diagram illustrates a collaborative network perception method implemented across multiple functional branches. As can be seen from the steps described above, the intermediate data generated in step a2, after data transformation and security processing, can be shared with other functional branches.
[0057] In step a3 above, if the current functional branch receives intermediate data from other functional branches, it generates a perception result together with its own intermediate data. In addition to the target perception result of this functional branch, the generated perception result may also include perception results that can be used by other functional branches and shared with available functional branches.
[0058] In step a5 above, in addition to feeding back the operation execution results to itself, the functional branch will also share them with other functional branches that have an impact.
[0059] In this embodiment, the various functional branches of network perception achieve collaboration and cooperation through the sharing of processed intermediate data, perception results, operation execution results, etc.
[0060] like Figure 5 The diagram shown is a schematic of the logical functional structure in this embodiment, based on the three stages (information stage, perception stage, and operation stage) of the network perception functional branch. Information input from other functional branches includes processed intermediate data, perception results, and operation execution results. Simultaneously, the processed intermediate data, perception results, and operation execution results can also be shared with other functional branches (external branches). In the collaborative perception network, each functional branch also includes a network functional branch model and mechanisms for reuse, transformation, security, trustworthiness, and feedback.
[0061] like Figure 6 The diagram shown is a schematic representation of a deep learning model embodiment in the collaborative network perception method of this application. In this embodiment, the input layer information of the model can come from other functional branches in addition to the current functional branch, including intermediate data from the current functional branch, as well as intermediate data from other functional branches that has undergone data transformation and security processing. Figure 6 The data includes intermediate data from both internal and external branches, as well as perception results from other functional branches and execution results from external branch operations. The model's input layer information can also be submitted to other functional branches. In this embodiment, each functional branch introduces external input and model reconstruction mechanisms, ensuring that model building and optimization match the corresponding data without significant changes in overhead, thus significantly improving the overall model value.
[0062] like Figure 7 As shown, a more specific implementation flow of the cooperative network perception method is provided, illustrating the basic functional flow of a functional branch under the premise of implementing cooperative network perception, including the following steps: b1: The network-aware functional branch uses a data collection engine to collect raw data.
[0063] b2: The functional branch uses the analysis engine to preprocess the raw data to obtain intermediate data.
[0064] b3: Determine whether intermediate data is shared with other functional branches. If yes, proceed to b4; otherwise, proceed to b5.
[0065] b4: After intermediate data undergoes data transformation and security processing, it is shared to other functional branches.
[0066] b5: Has intermediate data been received after processing by other functional branches? If yes, proceed to b6; otherwise, proceed to b7.
[0067] b6: Combine intermediate data for processing to generate perception results.
[0068] b7: Generate perception results and determine whether perception results from other functional branches have been received. If yes, proceed to b8; otherwise, proceed to b9.
[0069] b8: Process the received perception results.
[0070] b9: Has the operation execution result been received from other functional branches? If yes, proceed to b1; otherwise, proceed to b10.
[0071] b10: The network perception function branch performs network perception through the perception engine and generates perception results.
[0072] b11: Does the perception result need to be shared with other functional branches? (If there is a perception result that can be used by other functional branches, it will be shared with other functional branches.) If yes, proceed to b12; if no, proceed to b13.
[0073] b12: Share the perception results with other functional branches that can utilize the perception results.
[0074] b13: The network-aware functional branch executes operations through the operation engine based on the perception results.
[0075] b14: Should the operation execution result be shared with other functional branches (if it affects other functional branches, it needs to be shared with those branches)? If yes, proceed to b15; otherwise, proceed to b1.
[0076] b15: Share the results of the operation to other functional branches that have an impact.
[0077] It is important to emphasize that information from other feature branches entering this feature branch must be processed in accordance with the method agreed upon by this feature branch and other feature branches before being committed to this feature branch. Similarly, information that this feature branch needs to share with other feature branches must also be processed in accordance with the method agreed upon by this feature branch and other feature branches before being committed to other feature branches.
[0078] like Figure 8 As shown, an embodiment of the security mechanism of this application is provided. Cooperative network awareness requires ensuring the security of information sharing mechanisms among functional branches; therefore, before other functional branches share information with this functional branch, it needs to undergo processing that meets security requirements. After the intermediate dataset is generated, it is used in the following three scenarios according to different security configurations: In the homogeneous collaboration scenario, the intermediate dataset of the source functional branch is mapped to the intermediate dataset of the destination functional branch. This is mainly applicable to scenarios where the implementation of the source functional branch and the destination functional branch is based on mutual trust (e.g., both functions are implemented by the same manufacturer).
[0079] In heterogeneous standard interface scenarios, the intermediate dataset of the source functional branch is converted to a third-party dataset, and the third-party dataset is mapped to the intermediate dataset of the target functional branch. This is mainly applicable to scenarios where the implementations of the source functional branch and the target functional branch do not have a mutually trusting basis, but there are already standards for the interaction between the source functional branch and the target functional branch.
[0080] In heterogeneous collaboration scenarios, the intermediate dataset of the source functional branch is encoded and transformed into an intermediate dataset that avoids data exposure. The destination functional branch then receives this intermediate dataset and converts it into its own intermediate dataset. This approach is primarily suitable for scenarios where the implementations of the source and destination functional branches lack a mutually trusting foundation and where there is no standard for interaction between the source and destination functional branches.
[0081] like Figure 9 As shown, an embodiment of the trusted mechanism of this application is provided. Cooperative network perception also needs to ensure that the corresponding functional entities within each functional branch have a trusted judgment mechanism. The implementation of other functions can rely on the trusted judgment results of each functional branch. Trusted configuration is judged through trusted operation requests. The trusted judgment mechanism mainly includes the following four categories: Call Home mechanism: This mechanism obtains reliable information from the manufacturer of the system or device corresponding to each functional branch and determines whether the functional branches are trustworthy. It is primarily applicable to scenarios where both the source and destination functional branches are implemented by the same manufacturer. In this way, both functional branches can obtain reliable information from the manufacturer.
[0082] Federation mechanism: A trusted alliance or group is established among the manufacturers of the systems or devices corresponding to the functional branches. Trust information is obtained from the group to determine whether the functional branches are trustworthy. It is mainly applicable to scenarios where the source functional branch and the destination functional branch are not implemented by the same manufacturer, but multiple manufacturers have established a federation mechanism to achieve a trustworthy state with each other.
[0083] Third-party mechanism: The manufacturers of the systems or devices corresponding to the functional branches are all trusted with a third party. Trust information is obtained from the third party to determine whether the functional branches are trustworthy. This is mainly applicable to scenarios where the source and destination functional branches are not implemented by the same manufacturer, but multiple manufacturers have reached a trust relationship with the third party.
[0084] Zero-trust mechanism: There is currently no trust guarantee between functional branches. They need to start from a zero-trust state and negotiate with each other to determine whether they are trustworthy. It is mainly applicable to scenarios where the source functional branch and the destination functional branch are not implemented by the same vendor, and multiple vendors cannot achieve a trustworthy state through other methods.
[0085] Secondly, this application provides a collaborative network sensing device, which is set in various functional branches of network sensing. The device includes an intermediate data module, a sensing module, and an execution module.
[0086] The intermediate data module is used to collect raw data and preprocess it to generate intermediate data. It is also used to perform data transformation and security processing on the intermediate data and then share it to other functional branches. The perception module is used to generate perception results based on the received and its own intermediate data, and to share the perception results that can be used by other functional branches. The execution module is used to generate operation suggestions based on the perception results and execute them, feed back the operation execution results to its own functional branch, and share them with other functional branches that have an impact.
[0087] The functions of each module in the above-mentioned collaborative network sensing device correspond to the steps in the above-mentioned collaborative network sensing method embodiment, and their functions and implementation processes will not be described in detail here.
[0088] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0089] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.
[0090] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.
[0091] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.
[0092] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.
[0093] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.
[0094] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.
Claims
1. A cooperative network sensing method, characterized in that, The method includes: Each functional branch of the network-aware system collects raw data, performs preprocessing to generate intermediate data, and then shares the intermediate data with other functional branches after data transformation and security processing. Each functional branch generates perception results based on the received and its own intermediate data, and shares the perception results that can be used by other functional branches; at the same time, it generates operation suggestions based on the perception results and executes them, feeds back the operation execution results to itself, and shares them with other functional branches that have an impact.
2. The collaborative network sensing method as described in claim 1, characterized in that, The network awareness of each functional branch includes: The information stage is used to collect raw data and generate intermediate data. The perception phase is used to output its own perception results and perception results that can be used by other functional branches; The operation phase is used to generate and execute operation suggestions, as well as to feed back the results and impact of the operation to other functional branches.
3. The collaborative network sensing method as described in claim 1, characterized in that, The data conversion and security processing includes at least one of the following: de-identification processing, equivalence conversion processing, encryption processing, and two-branch negotiation processing.
4. The collaborative network sensing method as described in claim 3, characterized in that, The intermediate data is shared to other functional branches after undergoing equivalence transformation. The equivalence transformation methods include: Map the intermediate dataset of the source functional branch to the intermediate dataset of the destination functional branch; The source function branch converts the intermediate dataset to a third-party dataset, and the destination function branch maps the third-party dataset to the intermediate dataset of this branch. The source function branch's intermediate dataset is encoded and converted to an intermediate dataset that avoids data exposure. The destination function branch then receives this intermediate dataset and converts it into its own intermediate dataset.
5. The collaborative network sensing method as described in claim 1, characterized in that, The perception results that can be used by other functional branches include: target perception results that are directly used by other functional branches, and basic perception results that are used for further processing by other functional branches.
6. The collaborative network sensing method as described in claim 1, characterized in that, Share the results of the operation to other functional branches that have an impact, including: Share only the completion of this function branch operation, or share which network devices were affected by the operation.
7. The cooperative network sensing method as described in claim 1, characterized in that, The method further includes: Data sharing between two or more functional branches follows a trusted mechanism, which includes zero-trust mechanism, federation mechanism, call home mechanism and third-party mechanism; The zero-trust mechanism is based on message authentication, the federation mechanism is based on group negotiation, the call home mechanism is based on the authorization of the function owner, and the third-party mechanism is based on the verification of third-party authentication.
8. The collaborative network sensing method as described in claim 7, characterized in that, In the message authentication of the message, each message exchange is authorized by both parties; in the group negotiation, a mutually trusted group is established through negotiation between the two parties; in the authorization of the function master, both parties are authenticated by the function master; in the verification of the third-party authentication, both parties are authenticated by a third-party entity that has passed the mutual trust mechanism; wherein, the two parties are two functional branches exchanging data.
9. The cooperative network sensing method as described in claim 1, characterized in that, The network awareness functional branches include network traffic awareness, network service awareness, network status awareness, demand awareness, and network resource awareness.
10. A collaborative network sensing device, characterized in that, The device, located in various functional branches of network awareness, includes: The intermediate data module is used to collect raw data and preprocess it to generate intermediate data. It is also used to perform data transformation and security processing on the intermediate data and then share it to other functional branches. The perception module is used to generate perception results based on the received and its own intermediate data, and to share the perception results that can be used by other functional branches. The execution module is used to generate operation suggestions based on the perception results and execute them, feed back the operation execution results to its own functional branch, and share them with other functional branches that have an impact.