Physical network early warning method, device, electronic device, and storage medium

Abstract

The present invention provides a physical network early warning method, device, electronic device, storage medium and program product, which relate to the field of communication technology. The method comprises: obtaining historical network slice data of the physical network; analyzing the historical network slice data to obtain a transition probability matrix of the physical network; predicting the probability of abnormality of the physical network at the next moment according to the transition probability matrix; predicting the number of target users who purchase network slices of the physical network at the next moment, and obtaining the abnormal threshold corresponding to the number; and issuing an early warning when the probability exceeds the abnormal threshold.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to an early warning method, device, electronic equipment, storage medium and program product for a physical network. Background Art

[0002] Diversified scenarios put forward diverse performance and functional requirements for the network. Network slicing technology is a temporary logical network that divides the physical network into multiple virtual networks according to different service requirements, so as to flexibly respond to different network application scenarios, provide differentiated services, and meet different business needs.

[0003] However, when an abnormality occurs in the physical network, the network slicing technology provided based on the physical network may also fail, thus bringing a bad user experience. Summary of the invention

[0004] In view of the above problems, embodiments of the present invention provide an early warning method, device, electronic device, storage medium and program product for a physical network, so as to overcome the above problems or at least partially solve the above problems.

[0005] A first aspect of an embodiment of the present invention provides an early warning method for a physical network, including:

[0006] Get historical network slice data of the physical network;

[0007] Analyze the historical network slice data to obtain a transition probability matrix of the physical network;

[0008] Predicting the probability of an abnormality occurring in the physical network at the next moment according to the transition probability matrix;

[0009] Predicting the number of target users who will purchase network slices of the physical network at the next moment, and obtaining an abnormal threshold value corresponding to the number;

[0010] When the probability exceeds the abnormal threshold, an early warning is issued.

[0011] Optionally, the transition probability matrix includes the probability of normal data turning into abnormal data, and the probability of abnormal data remaining abnormal;

[0012] The predicting, according to the transition probability matrix, the probability of an abnormality occurring in the physical network at the next moment includes:

[0013] Obtaining a ratio of normal data and a ratio of abnormal data in the physical network at a current moment;

[0014] According to the proportion of normal data and the proportion of abnormal data in the physical network at the current moment and the transition probability matrix, predicting the proportion of abnormal data in the physical network at the next moment;

[0015] The proportion of abnormal data in the physical network at the next moment is determined as the probability of an abnormality occurring in the physical network at the next moment.

[0016] Optionally, the predicting the number of target users who purchase the network slice of the physical network at the next moment includes:

[0017] Obtain the types of network slices purchased by each of the historical users who have purchased the network slices of the physical network;

[0018] According to the types of network slices purchased by the historical users, predict the probability that each of the historical users will purchase each type of network slice at the next moment;

[0019] When the probability that any of the historical users purchases any type of network slice at the next moment exceeds a probability threshold, the historical user is determined as the target user, and the number of the target users is counted.

[0020] Optionally, after determining the target user, the method further includes:

[0021] Determine a network slice of a type whose probability of being purchased by the target user at the next moment exceeds the probability threshold as a target network slice to be purchased by the target user at the next moment;

[0022] Utilize the physical network to prepare the resource configuration required for the target network slice.

[0023] Optionally, the using the physical network to prepare resource configuration required for the target network slice includes:

[0024] Obtaining the service requirements corresponding to the target network slice;

[0025] Submitting the service demand to the communication service management function of the physical network to obtain the network slicing requirement obtained by the communication service management function according to the service demand;

[0026] Obtaining a feasibility result of the network slicing requirement evaluated by a slice management function;

[0027] When the feasibility result indicates feasibility, prepare the network slice entity required for the target network slice.

[0028] Optionally, the network slicing entity required for preparing the target network slice includes:

[0029] Determine whether the network slice entity requested by the business demand is shareable;

[0030] In the case where the service demand is not shared, obtaining a new network slice entity created by the slice management function;

[0031] When the business demand is shared, obtain an existing network slice entity.

[0032] Optionally, after issuing the warning, the method further includes:

[0033] Predict the probability of abnormalities occurring in multiple candidate physical networks at the next moment;

[0034] One of the candidate physical networks whose probability of an abnormality occurring at the next moment does not exceed the abnormality threshold is determined as the target physical network that provides the target resource configuration, and the target resource configuration is the resource configuration required for the target user to purchase the network slice at the next moment.

[0035] A second aspect of an embodiment of the present invention provides an early warning device for a physical network, including:

[0036] A data acquisition module, configured to acquire historical network slice data of a physical network;

[0037] A matrix acquisition module is configured to analyze the historical network slice data to obtain a transition probability matrix of the physical network;

[0038] An abnormality prediction module is configured to predict the probability of an abnormality occurring in the physical network at the next moment according to the transition probability matrix;

[0039] a quantity prediction module, configured to predict the number of target users who will purchase the network slice of the physical network at the next moment, and obtain an abnormal threshold value corresponding to the number;

[0040] The early warning module is configured to issue an early warning when the probability exceeds the abnormal threshold.

[0041] Optionally, the transition probability matrix includes the probability of normal data turning into abnormal data, and the probability of abnormal data turning into normal data; the abnormality prediction module includes:

[0042] A ratio acquisition submodule, configured to acquire a ratio of normal data and a ratio of abnormal data in the physical network at a current moment;

[0043] A proportion prediction submodule, configured to predict the proportion of abnormal data in the physical network at the next moment according to the proportion of normal data and the proportion of abnormal data in the physical network at the current moment and the transition probability matrix;

[0044] The probability acquisition submodule is configured to determine the proportion of abnormal data in the physical network at the next moment as the probability of an abnormality occurring in the physical network at the next moment.

[0045] Optionally, the quantity prediction module includes:

[0046] A type acquisition submodule, configured to acquire types of network slices purchased by respective historical users who have purchased network slices of the physical network;

[0047] A probability prediction submodule, configured to predict the probability of each of the historical users purchasing each type of network slice at the next moment according to the types of network slices purchased by the historical users;

[0048] The quantity statistics submodule is configured to determine any historical user as the target user and count the number of the target users when the probability that any historical user purchases any type of network slice at the next moment exceeds a probability threshold.

[0049] Optionally, after determining the target user, the method further includes:

[0050] A slice determination module, configured to determine a network slice of a type whose probability of being purchased by the target user at the next moment exceeds the probability threshold as a target network slice to be purchased by the target user at the next moment;

[0051] The preparation module is configured to utilize the physical network to prepare the resource configuration required for the target network slice.

[0052] Optionally, the preparation module includes:

[0053] A demand acquisition submodule is configured to obtain the service demand corresponding to the target network slice;

[0054] A requirement acquisition submodule is configured to submit the business requirement to the communication service management function of the physical network, and obtain the network slicing requirement obtained by the communication service management function according to the business requirement;

[0055] An evaluation submodule, configured to obtain a feasibility result of the network slice requirement evaluated by a slice management function;

[0056] The preparation submodule is configured to prepare the network slice entity required for the target network slice when the feasibility result indicates that it is feasible.

[0057] Optionally, the preparation submodule includes:

[0058] A judging unit configured to judge whether the network slice entity requested by the service demand is shareable;

[0059] A first entity acquisition unit is configured to acquire a new network slice entity created by the slice management function when the service demand is not shared;

[0060] The second entity unit is configured to obtain an existing network slice entity when the business demand is shared.

[0061] Optionally, after issuing the warning, the method further includes:

[0062] A probability prediction module, configured to predict the probability of abnormality occurring in multiple candidate physical networks at the next moment;

[0063] The target determination module is configured to determine one of the candidate physical networks whose probability of an anomaly occurring at the next moment does not exceed the anomaly threshold as the target physical network that provides target resource configuration, and the target resource configuration is the resource configuration required for the target user to purchase a network slice at the next moment.

[0064] According to a third aspect of an embodiment of the present invention, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the early warning method for a physical network as described in the first aspect.

[0065] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the early warning method of the physical network as described in the first aspect.

[0066] According to a fifth aspect of an embodiment of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the early warning method of the physical network as described in the first aspect is implemented.

[0067] The embodiments of the present invention include the following advantages:

[0068] In this embodiment, the historical network slice data of the physical network is analyzed to obtain the transition probability matrix of the physical network, so as to predict the probability of an abnormality in the physical network at the next moment according to the transition probability matrix. The number of target users who purchase network slices of the physical network at the next moment is predicted, and different numbers of target users correspond to different abnormal thresholds. If the probability of an abnormality in the physical network at the next moment exceeds the abnormal threshold corresponding to the number of target users who purchase network slices of the physical network at the next moment, an early warning is issued. In this way, different abnormal thresholds are provided for different numbers of target users, so it is possible to more accurately determine whether an early warning needs to be issued, and an early warning can be issued in advance to avoid using an abnormal physical network to provide network slicing services to users, which brings a bad user experience to users. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0070] Figure 1 is a flowchart of a physical network early warning method according to an embodiment of the present invention;

[0071] Figure 2 is a flowchart of the steps of a method for predicting the probability of an abnormality occurring in a physical network at the next moment in an embodiment of the present invention;

[0072] Figure 3 It is a structural schematic diagram of an early warning device for a physical network in an embodiment of the present invention;

[0073] Figure 4 It is a block diagram of a device for early warning of a physical network in an embodiment of the present invention. DETAILED DESCRIPTION

[0074] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0075] On-demand networking means providing the right network control function and performance guarantee for each business scenario. Network slicing technology is a way to implement on-demand networking. Network slicing technology refers to dividing the network provided by a physical device into multiple virtual networks to flexibly respond to different network application scenarios and provide differentiated services to meet different business needs. On-demand networking based on network slicing technology has changed the traditional network planning, deployment, operation and maintenance model, and put forward new requirements for network development planning and network operation and maintenance.

[0076] From the operator's perspective, the implementation process of network slicing is orchestration and deployment. The corresponding functional entities include communication service management function (CSMF, Communication Service Management Function), slice management function (NSMF, Network Slice Management Function), sub-slice management function (NSSMF, Network Slice Subnet Management Function), and management and orchestration function (MANO, Management and Network Orchestration).

[0077] Among them, CSMF is responsible for converting communication business-related service requirements into network slicing-related requirements; NSMF is responsible for the management and orchestration of NSI (Network Slice Instance, network slicing entity), and deriving network slicing subnet-related requirements from network slicing-related requirements; NSSMF is responsible for the management and orchestration of network slicing subnet instances; MANO is used to form network slices.

[0078] The embodiment of the present invention analyzes historical data and intelligently warns whether an abnormality occurs in the physical network, thereby ensuring the provision of high-quality network slicing services.

[0079] Reference Figure 1 As shown, a flowchart of a method for early warning of a physical network in an embodiment of the present invention is shown. Figure 1 As shown, the early warning method of the physical network may specifically include steps S11 to S15.

[0080] Step S11: Obtain historical network slice data of the physical network.

[0081] A physical network refers to a network composed of physical devices, and a historical network slice of a physical network refers to the network slices into which the physical network was historically divided. The historical network slice data of a physical network will be stored in the physical devices that constitute the physical network. Therefore, the historical network slice data of the physical network can be obtained from the physical devices.

[0082] The network slice data includes at least one or more of the following: the type of network slice, the performance of the network slice, the business scenarios suitable for the network slice, and the user attributes of the user who purchases the network slice.

[0083] Types of network slices include eMBB (Enhanced Mobile Broadband), uRLLC (Ultra-Reliable Low-Latency Communications) and mMTC (Massive Machine Type Communication). The performance of network slices may include latency, bandwidth, reliability (number of fault records) and geographic location. The business scenarios suitable for network slices can be obtained by analyzing the types of network slices and the performance of network slices, or by investigating users who purchase network slices. The user attributes of users who purchase network slices may be whether the user is a newly registered user or an old user who has already registered.

[0084] Step S12: Analyze the historical network slice data to obtain a transition probability matrix of the physical network.

[0085] The transition probability matrix is ​​a matrix used to predict how the state of a physical network will change. Predicting the state of a physical network is actually predicting the state of the physical devices that make up the physical network. The transition probability matrix includes the probability that normal data turns to abnormal data, the probability that abnormal data turns to normal data, the probability that abnormal data remains abnormal, and the probability that normal data remains normal.

[0086] The historical network slice data can be analyzed by AI (Artificial Intelligence) to obtain the transition probability matrix of the physical network. The historical network slice data can also be input into the neural network model, and the neural network model predicts the transition probability matrix of the physical network. The neural network model can be obtained through deep learning training or supervised training. The training process of the neural network model can refer to related technologies.

[0087] Step S13: predicting the probability of an abnormality occurring in the physical network at the next moment according to the transition probability matrix.

[0088] According to the transition probability matrix, it is possible to predict how the state of the physical network will change. Therefore, the current state of the physical network can be obtained, and the probability of an abnormality in the physical network at the next moment can be predicted using the transition probability matrix.

[0089] Optionally, refer to Figure 2 As shown, a flowchart of the steps of a method for predicting the probability of an abnormality occurring in a physical network at the next moment in an embodiment of the present invention is shown, such as Figure 2 As shown, the method for predicting the probability of an abnormality occurring in the physical network at the next moment may specifically include steps S131 to S1311:

[0090] Step S131: obtaining the ratio of normal data and the ratio of abnormal data in the physical network at the current moment;

[0091] Step S132: predicting the proportion of abnormal data in the physical network at the next moment according to the proportion of normal data and the proportion of abnormal data in the physical network at the current moment and the transition probability matrix;

[0092] Step S133: Determine the proportion of abnormal data in the physical network at the next moment as the probability of an abnormality occurring in the physical network at the next moment.

[0093] By multiplying the proportion of normal data in the physical network at the current moment by the probability that normal data turns to abnormal data, the first proportion of abnormal data in the physical network at the next moment can be obtained. By multiplying the proportion of abnormal data in the physical network at the current moment by the probability that abnormal data remains abnormal, the second proportion of abnormal data in the physical network at the next moment can be obtained. The first proportion and the second proportion are added together to obtain the proportion of abnormal data in the physical network at the next moment.

[0094] The following formula can be used to calculate the proportion of abnormal data in the physical network at the next moment:

[0095] X(k+1)=X(k)×P

[0096] Among them, X(k) represents the state vector of the physical network at time k, P represents the transition probability matrix, and X(k+1) represents the state vector of the physical network at time k+1.

[0097] For example, consider the total amount of data in the physical network as 1, of which abnormal data accounts for 30% and normal data accounts for 70%. According to historical data analysis, it can be concluded that in the transition probability matrix corresponding to the current moment, the probability of normal data turning into abnormal data is 30%, the probability of abnormal data turning into normal data is 40%, the probability of abnormal data remaining abnormal is 60%, and the probability of normal data remaining normal is 70%. Then, in the next moment, the proportion of normal data is: 70%×70%+30%×40%=61%; the proportion of abnormal data is: 70%×30%+30%×60%=39%.

[0098] The proportion of abnormal data in the physical network at the next moment is determined as the probability of an abnormality occurring in the physical network at the next moment.

[0099] In this way, based on the transition probability matrix, the proportion of abnormal data in the physical network at the next moment can be calculated, and then the probability of abnormality in the physical network at the next moment can be determined.

[0100] Step S14: predict the number of target users who will purchase network slices of the physical network at the next moment, and obtain the abnormal threshold corresponding to the number.

[0101] The number of target users who will purchase network slices of the physical network at the next moment can also be predicted. The target user can be any user. The target user is a potential user who will purchase network slices. The number of target users who will purchase network slices of the physical network at the next moment can be predicted by performing trend analysis on users who have purchased network slices of the physical network in the past.

[0102] The number of target users is different, and the corresponding abnormal threshold is also different. It is understandable that the more target users who purchase network slices, the higher the requirements for the physical network, because when the number of target users is large, once the physical network is abnormal, the loss will be greater. In addition, the more target users there are, the greater the pressure on the physical network, and the more likely the physical network will be abnormal.

[0103] The corresponding relationship between the number of target users and the abnormal threshold may be obtained by analyzing historical data, by big data statistics, or by AI analysis.

[0104] Step S15: When the probability exceeds the abnormal threshold, an early warning is issued.

[0105] When the probability of an abnormality in the physical network exceeds the abnormality threshold corresponding to the number of target users, an early warning is issued. The early warning can be used to remind the administrators of the physical network to adjust the network slice and / or physical network in a timely manner to avoid using the abnormal physical network to provide network slice services to users, resulting in failure of the network slice service, thereby bringing a bad user experience.

[0106] By adopting the technical solution of the embodiment of the present invention, the historical network slicing data of the physical network is analyzed to obtain the transition probability matrix of the physical network, so as to predict the probability of an abnormality in the physical network at the next moment according to the transition probability matrix. The number of target users who purchase network slices of the physical network at the next moment is predicted, and different numbers of target users correspond to different abnormality thresholds. If the probability of an abnormality in the physical network at the next moment exceeds the abnormality threshold corresponding to the number of target users who purchase network slices of the physical network at the next moment, an early warning is issued. In this way, different abnormality thresholds are provided for different numbers of target users, so it is possible to more accurately determine whether an early warning needs to be issued, and an early warning can be issued in advance to avoid using an abnormal physical network to provide network slicing services to users, which brings a bad user experience to users.

[0107] Optionally, based on the above technical solution, the number of target users who will purchase network slices of the physical network at the next moment can be predicted by the following steps: obtaining the types of network slices purchased by each historical user who has purchased the network slices of the physical network; predicting the probability of each of the historical users purchasing each type of network slice at the next moment based on the types of network slices purchased by the historical users; when the probability of any of the historical users purchasing any type of network slice at the next moment exceeds a probability threshold, determining the historical user as the target user, and counting the number of the target users.

[0108] A historical user is a user who has purchased a network slice of a physical network in the past. The type of network slice purchased by each historical user can be obtained from the historical network slice data of the physical network.

[0109] According to the types of network slices that historical users have purchased, the probability of each historical user purchasing each type of network slice at the next moment can be predicted. Specifically, the probability of each historical user purchasing each type of network slice at the next moment can be calculated by the following formula:

[0110]

[0111] Among them, P represents probability, H represents a certain type of network slice, and X represents the type of network slice that the user has purchased in the past.

[0112] When the probability that a historical user purchases any type of network slice at the next moment exceeds a probability threshold, the historical user is considered to be a target user, where the probability threshold can be set according to actual needs.

[0113] For example, the probability of a historical user purchasing type A network slices is 0.7, the probability of purchasing type B network slices is 0.6, the probability of purchasing type C network slices is 0.8, and the probability threshold is 0.75. Because the probability of the historical user purchasing a type (type C) of network slices exceeds the probability threshold, the historical user is considered to be a target user.

[0114] Among multiple historical users, multiple target users are counted, thereby obtaining the number of target users.

[0115] Optionally, based on the above technical solution, after determining the target user, the type of network slice that the target user will purchase at the next moment can also be predicted. Specifically: the type of network slice that the probability of the target user purchasing at the next moment exceeds the probability threshold is determined as the target network slice purchased by the target user at the next moment; and the resource configuration required for the target network slice is prepared using the physical network.

[0116] If the probability of a certain type of network slice purchased by the target user at the next moment exceeds the probability threshold, it is considered that the target user will purchase the network slice of this type, and the network slice of the type that the target user will purchase is determined as the target network slice. For example, if the probability of the target user purchasing a type C network slice is 0.8 and the probability threshold is 0.75, it is considered that the target user will purchase a type C network slice at the next moment, and the target network slice is a type C network slice. The type of network slice that a target user will purchase at the next moment can be one type or multiple types.

[0117] Different types of network slices require different resource configurations. After determining the target network slice that the target user will purchase at the next moment, the physical network can be used to prepare the resource configuration required for the target network slice.

[0118] In this way, the resource configuration required for the target network slice can be prepared in advance to improve the efficiency of providing network slicing services.

[0119] Optionally, on the basis of the above technical solution, the physical network is used to prepare the resource configuration required for the target network slice, including: obtaining the business requirements corresponding to the target network slice; submitting the business requirements to the communication service management function of the physical network to obtain the network slice requirements obtained by the communication service management function according to the business requirements; obtaining the feasibility results of the network slice requirements evaluated by the slice management function; and preparing the network slice entity required for the target network slice when the feasibility results indicate feasibility.

[0120] The resource configuration required for network slicing mainly refers to the network slicing entities required for network slicing.

[0121] Submit the business requirements to the communication service management function, which is responsible for translating the business requirements into network slice requirements, completing the conversion of user requirements to service level agreements (SLA) and submitting them to the slice management function. The slice management function can evaluate the feasibility of network slice requirements and obtain feasibility results. If the feasibility results indicate that it is feasible, the network slice entity required for the target network slice can be prepared.

[0122] Optionally, based on the above technical solution, preparing the network slice entity required for the target network slice may include: determining whether the network slice entity requested by the business demand is shared; if the business demand is not shared, obtaining a new network slice entity created by the slice management function; if the business demand is shared, obtaining an existing network slice entity.

[0123] Analyze whether the network slice entity requested by the target network slice can be shared with other communication services. If it can be shared and the existing network slice entity is available, the slice management function uses the existing network slice entity; otherwise, the slice management function creates a new network slice entity according to the service level agreement. At the same time, the slice management function extracts the network slice subnet related requirements from the network slice related requirements and sends them to the sub-slice management function.

[0124] In this way, the orchestration and deployment of the target network slice can be realized, and the resource configuration required for the target network slice can be prepared for the target user.

[0125] Optionally, based on the above technical solution, an early warning is issued to prove that the current physical network cannot support the target user at the next moment. Therefore, other physical networks can be selected to provide network slices for the target user.

[0126] Predict the probability of abnormalities occurring in multiple candidate physical networks at the next moment; determine one of the candidate physical networks whose probability of abnormalities occurring at the next moment does not exceed the abnormality threshold as the target physical network providing target resource configuration, where the target resource configuration is the resource configuration required for the target user to purchase network slices at the next moment.

[0127] A candidate physical network refers to a physical network composed of physical devices whose network area covers the target user and can provide network slicing services to the target user. The probability of abnormality occurring in each of multiple candidate physical networks at the next moment can be predicted. The historical network slicing data of the candidate physical network can be obtained; the historical network slicing data of the candidate physical network can be analyzed to obtain the transition probability matrix of the candidate physical network; based on the transition probability matrix of the candidate physical network, the probability of abnormality occurring in the candidate physical network at the next moment can be predicted.

[0128] After determining the probability of each candidate physical network having an abnormality at the next moment, a physical network whose probability of an abnormality at the next moment does not exceed an abnormality threshold can be determined from multiple candidate physical networks. One of the candidate physical networks whose probability of an abnormality at the next moment does not exceed the abnormality threshold is determined as the target physical network for providing target resource configuration.

[0129] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0130] Figure 3is a schematic diagram of the structure of an early warning device for a physical network according to an embodiment of the present invention. Figure 3 As shown, the device includes a data acquisition module, a matrix acquisition module, an abnormality prediction module, a quantity prediction module and an early warning module, wherein:

[0131] A data acquisition module, configured to acquire historical network slice data of a physical network;

[0132] A matrix acquisition module is configured to analyze the historical network slice data to obtain a transition probability matrix of the physical network;

[0133] An abnormality prediction module is configured to predict the probability of an abnormality occurring in the physical network at the next moment according to the transition probability matrix;

[0134] a quantity prediction module, configured to predict the number of target users who will purchase the network slice of the physical network at the next moment, and obtain an abnormal threshold value corresponding to the number;

[0135] The early warning module is configured to issue an early warning when the probability exceeds the abnormal threshold.

[0136] Optionally, the transition probability matrix includes the probability of normal data turning into abnormal data, and the probability of abnormal data turning into normal data; the abnormality prediction module includes:

[0137] A ratio acquisition submodule, configured to acquire a ratio of normal data and a ratio of abnormal data in the physical network at a current moment;

[0138] A proportion prediction submodule, configured to predict the proportion of abnormal data in the physical network at the next moment according to the proportion of normal data and the proportion of abnormal data in the physical network at the current moment and the transition probability matrix;

[0139] The probability acquisition submodule is configured to determine the proportion of abnormal data in the physical network at the next moment as the probability of an abnormality occurring in the physical network at the next moment.

[0140] Optionally, the quantity prediction module includes:

[0141] A type acquisition submodule, configured to acquire types of network slices purchased by respective historical users who have purchased network slices of the physical network;

[0142] A probability prediction submodule, configured to predict the probability of each of the historical users purchasing each type of network slice at the next moment according to the types of network slices purchased by the historical users;

[0143] The quantity statistics submodule is configured to determine any historical user as the target user and count the number of the target users when the probability that any historical user purchases any type of network slice at the next moment exceeds a probability threshold.

[0144] Optionally, after determining the target user, the method further includes:

[0145] A slice determination module, configured to determine a network slice of a type whose probability of being purchased by the target user at the next moment exceeds the probability threshold as a target network slice to be purchased by the target user at the next moment;

[0146] The preparation module is configured to utilize the physical network to prepare the resource configuration required for the target network slice.

[0147] Optionally, the preparation module includes:

[0148] A demand acquisition submodule is configured to obtain the service demand corresponding to the target network slice;

[0149] A requirement acquisition submodule is configured to submit the business requirement to the communication service management function of the physical network, and obtain the network slicing requirement obtained by the communication service management function according to the business requirement;

[0150] An evaluation submodule, configured to obtain a feasibility result of the network slice requirement evaluated by a slice management function;

[0151] The preparation submodule is configured to prepare the network slice entity required for the target network slice when the feasibility result indicates that it is feasible.

[0152] Optionally, the preparation submodule includes:

[0153] A judging unit configured to judge whether the network slice entity requested by the service demand is shareable;

[0154] A first entity acquisition unit is configured to acquire a new network slice entity created by the slice management function when the service demand is not shared;

[0155] The second entity unit is configured to obtain an existing network slice entity when the business demand is shared.

[0156] Optionally, after issuing the warning, the method further includes:

[0157] A probability prediction module, configured to predict the probability of abnormality occurring in multiple candidate physical networks at the next moment;

[0158] The target determination module is configured to determine one of the candidate physical networks whose probability of an anomaly occurring at the next moment does not exceed the anomaly threshold as the target physical network that provides target resource configuration, and the target resource configuration is the resource configuration required for the target user to purchase a network slice at the next moment.

[0159] It should be noted that the device embodiment is similar to the method embodiment, so the description is relatively simple, and the relevant parts can be referred to the method embodiment.

[0160] Figure 4 4 is a block diagram of an apparatus 400 for early warning of a physical network in an embodiment of the present invention. For example, the apparatus 400 may be provided as a server. Figure 4 The apparatus 400 includes a processing component 422, which further includes one or more processors, and a memory resource represented by a memory 432 for storing instructions executable by the processing component 422, such as a computer program product. The computer program product stored in the memory 432 may include one or more modules each corresponding to a set of instructions. In addition, the processing component 422 is configured to execute instructions to perform the above-mentioned early warning method of the physical network.

[0161] The device 400 may also include a power supply component 426 configured to perform power management of the device 400, a wired or wireless network interface 450 configured to connect the device 400 to a network, and an input / output (I / O) interface 458. The device 400 may operate based on an operating system stored in the memory 432, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or the like.

[0162] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0163] It will be appreciated by those skilled in the art that the embodiments of the present invention may be provided as methods, devices or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0164] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, apparatuses, electronic devices, and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0165] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0166] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0167] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0168] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0169] The above is a detailed introduction to the early warning method, device, electronic device, storage medium and program product of a physical network provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A physical network early warning method, characterized in that: include: Get historical network slice data of the physical network; Analyze the historical network slice data to obtain a transition probability matrix of the physical network; According to the transition probability matrix, predict the probability of abnormality of the physical network at the next moment; wherein the transition probability matrix includes the probability of normal data turning into abnormal data, and the probability of abnormal data remaining abnormal; Predicting the number of target users who will purchase network slices of the physical network at the next moment, and obtaining an abnormality threshold corresponding to the number; wherein the abnormality threshold is used to compare with the probability of an abnormality occurring in the physical network to determine whether the probability of an abnormality occurring in the physical network exceeds the abnormality threshold; When the probability exceeds the abnormal threshold, issuing an early warning; The predicting, according to the transition probability matrix, the probability of an abnormality occurring in the physical network at the next moment includes: Obtaining a ratio of normal data and a ratio of abnormal data in the physical network at a current moment; According to the proportion of normal data and the proportion of abnormal data in the physical network at the current moment and the transition probability matrix, predicting the proportion of abnormal data in the physical network at the next moment; The proportion of abnormal data in the physical network at the next moment is determined as the probability of an abnormality occurring in the physical network at the next moment.

2. The method according to claim 1, characterized in that: The predicting the number of target users who will purchase the network slice of the physical network at the next moment includes: Obtain the types of network slices purchased by each of the historical users who have purchased the network slices of the physical network; According to the types of network slices purchased by the historical users, predict the probability that each of the historical users will purchase each type of network slice at the next moment; When the probability that any of the historical users purchases any type of network slice at the next moment exceeds a probability threshold, the historical user is determined as the target user, and the number of the target users is counted.

3. The method according to claim 2, characterized in that After determining the target user, the method further includes: Determine a network slice of a type whose probability of being purchased by the target user at the next moment exceeds the probability threshold as a target network slice to be purchased by the target user at the next moment; Utilize the physical network to prepare the resource configuration required for the target network slice.

4. The method according to claim 3, characterized in that The using the physical network to prepare resource configuration required for the target network slice includes: Obtaining the service requirements corresponding to the target network slice; Submitting the service demand to the communication service management function of the physical network to obtain the network slicing requirement obtained by the communication service management function according to the service demand; Obtaining feasibility results of the network slicing requirements evaluated by the slice management function; When the feasibility result indicates feasibility, prepare the network slice entity required for the target network slice.

5. The method according to claim 4, characterized in that The network slicing entity required for preparing the target network slice includes: Determine whether the network slice entity requested by the business demand is shareable; In the case where the service demand is not shared, obtaining a new network slice entity created by the slice management function; When the business demand is shared, obtain an existing network slice entity.

6. The method according to any one of claims 1 to 5, characterized in that: After issuing the warning, it also includes: Predict the probability of abnormalities occurring in multiple candidate physical networks at the next moment; One of the candidate physical networks whose probability of an abnormality occurring at the next moment does not exceed the abnormality threshold is determined as the target physical network that provides the target resource configuration, and the target resource configuration is the resource configuration required for the target user to purchase the network slice at the next moment.

7. A physical network early warning device, characterized in that: include: A data acquisition module, configured to acquire historical network slice data of a physical network; A matrix acquisition module is configured to analyze the historical network slice data to obtain a transition probability matrix of the physical network; wherein the transition probability matrix includes a probability that normal data turns into abnormal data, and a probability that abnormal data remains abnormal; An abnormality prediction module is configured to predict the probability of an abnormality occurring in the physical network at the next moment according to the transition probability matrix; A quantity prediction module is configured to predict the number of target users who will purchase network slices of the physical network at the next moment, and obtain an abnormality threshold corresponding to the number; wherein the abnormality threshold is used to compare with the probability of an abnormality of the physical network to determine whether the probability of an abnormality of the physical network exceeds the abnormality threshold; An early warning module is configured to issue an early warning when the probability exceeds the abnormal threshold; The abnormality prediction module comprises: A ratio acquisition submodule, configured to acquire a ratio of normal data and a ratio of abnormal data in the physical network at a current moment; A proportion prediction submodule, configured to predict the proportion of abnormal data in the physical network at the next moment according to the proportion of normal data and the proportion of abnormal data in the physical network at the current moment and the transition probability matrix; The probability acquisition submodule is configured to determine the proportion of abnormal data in the physical network at the next moment as the probability of an abnormality occurring in the physical network at the next moment.

8. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the early warning method for a physical network as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the early warning method for a physical network as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the early warning method for a physical network as claimed in any one of claims 1 to 6 is implemented.

Images