Dynamic orchestration methods, devices, network equipment, and storage media

Abstract

This disclosure relates to the field of mobile communication technology, and more particularly to a dynamic orchestration method and apparatus. The method includes: responding to a received network configuration request, obtaining a service attribute identifier for each type of network resource information to be configured, wherein the network configuration request carries service information, device information, and network resource information to be configured; obtaining a configuration instruction set based on the device information, the network resource information to be configured, and an instruction library; extracting real-time configuration information and the configuration instruction set using a target neural network algorithm to obtain a configuration relationship structure corresponding to the network resource information to be configured; performing part-of-speech tagging and information retrieval on the real-time configuration information using the configuration instruction set and the service attribute identifier, completing the adjustment of the configuration relationship structure, and outputting a dynamic instruction model. Using this disclosure can improve the efficiency and accuracy of dynamic instruction acquisition and reduce the failure probability of dynamic instruction model issuance.

Description

Technical Field

[0001] This disclosure relates to the field of mobile communication technology, and in particular to a dynamic orchestration method and apparatus. Background Technology

[0002] With the development of science and technology, network orchestration has emerged. Network orchestration refers to the orderly arrangement and organization of various network service units based on user needs, generating services that meet those needs. For example, one could rely on manually analyzing pre-defined business models to determine their rules, and then designing an orchestration set for each business based on the analyzed topology. However, pre-defined business models cannot cover all scenarios or dynamically adapt to real-time network conditions, leading to a high failure rate. When there are many types of business models, the analysis workload is large and difficult to update, resulting in low efficiency in network orchestration. Summary of the Invention

[0003] This disclosure provides a dynamic orchestration method, apparatus, network device, and storage medium, which can improve the efficiency and accuracy of dynamic instruction acquisition and reduce the failure probability of dynamic instruction model issuance. The technical solution of this disclosure is as follows:

[0004] According to a first aspect of the present disclosure, a dynamic orchestration method is provided, comprising:

[0005] In response to a received network configuration request, the service attribute identifier of each type of network resource information to be configured is obtained, wherein the network configuration request carries service information, device information and network resource information to be configured;

[0006] Based on the device information, the network resource information to be configured, and the instruction library, obtain a set of configuration instructions;

[0007] A target neural network algorithm is used to extract real-time configuration information and the set of configuration instructions to obtain a configuration relationship structure corresponding to the network resource information to be configured.

[0008] The configuration instruction set and the business attribute identifier are used to perform part-of-speech tagging and information retrieval on the real-time configuration information, thereby adjusting the configuration relationship structure and outputting a dynamic instruction model.

[0009] According to some embodiments, the method further includes:

[0010] Based on the network resource information to be configured, the device information, and the service scenario information, the service attribute identifier of each type of network resource information to be configured is mapped to obtain the tokens data corresponding to the service attribute identifier.

[0011] According to some embodiments, obtaining the configuration instruction set based on the device information, the network resource information to be configured, and the instruction library includes:

[0012] Based on the device information and the network resource information to be configured, obtain a set of mapping relationships corresponding to the network resource information to be configured from the instruction library;

[0013] A set of configuration instructions is obtained using the device information, the network resource information to be configured, and the mapping relationship set.

[0014] According to some embodiments, the method further includes:

[0015] Acquire an initial neural network model and training data, wherein the training data includes configuration information of at least one managed device, a set of historical configuration instructions, and at least one historical dynamic instruction model;

[0016] Obtain the network weights and thresholds of the initial neural network at a first time step, wherein the first time step is the time when the initial neural network is initialized;

[0017] Obtain the input and output information of neurons in each layer of the initial neural network model;

[0018] Based on the output information of each layer of neurons, obtain the energy function corresponding to the initial neural network model;

[0019] Based on the energy function, the input information and output information of each layer of neurons, obtain the first adjustment amount of the network weights between two adjacent layers of neurons and the second adjustment amount of the threshold.

[0020] Based on the energy function, the first adjustment amount and the second adjustment amount, the network weights and thresholds at the second time are determined, wherein the second time is adjacent to the first time and close to the current time.

[0021] Based on the network weights and thresholds at the second time step, the initial neural network model is adjusted to obtain the target neural network model.

[0022] According to some embodiments, each layer of neurons includes three layers of neurons. The step of obtaining a first adjustment amount for the network weights between two adjacent layers of neurons and a second adjustment amount for the threshold based on the energy function, the input information, and the output information of each layer of neurons includes:

[0023] Based on the output data of the initial neural network model, the output information of the third layer neurons, the output information of the second layer neurons, and the adjustment coefficients, the first adjustment amount of the network weights between the second layer neurons and the third layer neurons is obtained;

[0024] Based on the output data of the initial neural network model, the output information of the third layer neurons, the all-1 vector, and the adjustment coefficient, a second adjustment amount of the threshold between the second layer neurons and the third layer neurons is obtained;

[0025] Based on the output data of the initial neural network model, the output information of the third layer neurons, the output information of the second layer neurons, the input data of the initial neural network model, and the adjustment coefficient, a first adjustment amount of the network weights between the second layer neurons and the first layer neurons is obtained;

[0026] Based on the output data of the initial neural network model, the output information of the third layer neurons, the output information of the second layer neurons, the input data of the initial neural network model, the all-1 vector, and the adjustment coefficient, a second adjustment amount of the threshold between the second layer neurons and the first layer neurons is obtained.

[0027] According to some embodiments, the step of using the configuration instruction set and the business attribute identifier to perform part-of-speech tagging and information retrieval on the real-time configuration information, adjusting the configuration relationship structure, and outputting a dynamic instruction model includes:

[0028] The real-time configuration information and the configuration relationship structure are input into the Word2Vec model to obtain the first word segmentation vector representation information and the first part-of-speech vector representation information corresponding to the real-time configuration information, and to obtain the second word segmentation vector representation information and the second part-of-speech vector representation information corresponding to the configuration relationship structure.

[0029] Based on the first word segmentation vector representation information, the first part-of-speech vector representation information, the second word segmentation vector representation information, and the second part-of-speech vector representation information, obtain the location information and similarity matrix corresponding to the real-time configuration information, as well as the location information and similarity matrix corresponding to the configuration relationship structure;

[0030] Based on the location information and similarity matrix corresponding to the real-time configuration information and the location information and similarity matrix corresponding to the configuration relationship structure, the target location corresponding to the real-time configuration information and the configuration relationship structure is obtained, wherein the target location is the location with the highest similarity between the location information corresponding to the real-time configuration information and the location information corresponding to the configuration relationship structure;

[0031] Obtain the word segmentation vector representation corresponding to the target position;

[0032] The resource conflict identification result is obtained based on the business attribute identifier corresponding to the word segmentation vector;

[0033] If the resource conflict identification result indicates that there is no resource conflict, the configuration relationship structure is adjusted and a dynamic instruction model is output.

[0034] According to some embodiments, the method further includes:

[0035] The configuration instruction set and the business attribute identifier are used to perform part-of-speech tagging and information retrieval on the real-time configuration information to obtain the processed real-time configuration information;

[0036] The configuration relationship structure is tagged with part-of-speech tags and information is retrieved using the configuration instruction set and the business attribute identifier to obtain the processed configuration relationship structure.

[0037] According to a second aspect of the embodiments of this disclosure, a

[0038] The identifier acquisition unit is used to acquire the service attribute identifier of each type of network resource information to be configured in response to the received network configuration request, wherein the network configuration request carries service information, device information and network resource information to be configured;

[0039] The set acquisition unit is used to acquire a set of configuration instructions based on the device information, the network resource information to be configured, and the instruction library;

[0040] The structure acquisition unit is used to extract real-time configuration information and the set of configuration instructions using a target neural network algorithm, and to obtain the configuration relationship structure corresponding to the network resource information to be configured;

[0041] A model output unit is used to perform part-of-speech tagging and information retrieval on the real-time configuration information using the configuration instruction set and the service attribute identifier, to complete the adjustment of the configuration relationship structure, and to output a dynamic instruction model. According to a third aspect of the embodiments of this disclosure, a network device is provided, comprising:

[0042] processor;

[0043] Memory used to store the processor's executable instructions;

[0044] The processor is configured to execute the instructions to implement the dynamic orchestration method described in any one of the preceding aspects.

[0045] According to a fourth aspect of the present disclosure, a storage medium is provided that, when instructions in the storage medium are executed by a processor of a network device, enables the network device to perform the dynamic orchestration method described in any one of the preceding aspects.

[0046] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method described in any one of the preceding aspects.

[0047] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects:

[0048] In some or related embodiments, in response to a received network configuration request, a service attribute identifier for each type of network resource information to be configured is obtained. The network configuration request carries service information, device information, and network resource information to be configured. Based on the device information, the network resource information to be configured, and an instruction library, a set of configuration instructions is obtained. A target neural network algorithm is used to extract the real-time configuration information and the set of configuration instructions to obtain a configuration relationship structure corresponding to the network resource information to be configured. The set of configuration instructions and the service attribute identifier are used to perform part-of-speech tagging and information retrieval on the real-time configuration information, completing the adjustment of the configuration relationship structure and outputting a dynamic instruction model. Therefore, an adaptive, self-optimizing, and self-learning instruction orchestration mechanism can be provided. This mechanism can dynamically orchestrate network resources to be configured through network configuration requests without requiring manual processing of pre-defined service models, reducing labor costs. Furthermore, it can dynamically adjust the network resource information of the existing network based on the network configuration request. When the number of services is large or the service model changes, it reduces the workload of manual analysis and the complexity of instruction orchestration. It can update the dynamic instruction model, improve the efficiency and accuracy of dynamic instruction acquisition, and reduce the failure probability of dynamic instruction model issuance.

[0049] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0050] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0051] Figure 1 This is a flowchart illustrating a dynamic orchestration method according to an exemplary embodiment;

[0052] Figure 2 This is a flowchart illustrating a dynamic orchestration method according to an exemplary embodiment;

[0053] Figure 3 This is a schematic diagram illustrating a dynamic orchestration system according to an exemplary embodiment;

[0054] Figure 4This is a schematic diagram illustrating the training of a network model according to an exemplary embodiment;

[0055] Figure 5 This is a block diagram illustrating a dynamic orchestration apparatus according to an exemplary embodiment;

[0056] Figure 6 This is a block diagram illustrating a network device according to an exemplary embodiment. Detailed Implementation

[0057] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0058] This disclosure provides a dynamic orchestration method and apparatus. In some embodiments, the terms "dynamic orchestration method" and "information processing method" and "communication method" can be used interchangeably; the terms "dynamic orchestration apparatus" and "information processing apparatus" and "communication apparatus" can be used interchangeably; and the terms "information processing system" and "communication system" can be used interchangeably.

[0059] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0060] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0061] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0062] In this disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular or a plural expression.

[0063] In the embodiments disclosed herein, "multiple" refers to two or more.

[0064] In some embodiments, the terms “at least one of,” “one or more,” “a plurality of,” and “multiple” may be used interchangeably.

[0065] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0066] In some embodiments, "terminal" or "terminal device" may be referred to as "user equipment (UE)," "user terminal," "mobile station (MS)," "mobile terminal (MT)," "subscriber station," "mobile unit," "subscriber unit," "wireless unit," "remote unit," "mobile device," "wireless device," "wireless communication device," "remote device," "mobile subscriber station," "access terminal," "mobile terminal," "wireless terminal," "remote terminal," "handset," "user agent," "mobile client," "client," etc.

[0067] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0068] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0069] Figure 1 This is a flowchart illustrating a dynamic orchestration method according to an exemplary embodiment, such as... Figure 1 As shown, this dynamic orchestration method can be used to determine the root cause information corresponding to the abnormal information when the system encounters abnormal information, including the following steps:

[0070] In step S11, in response to the received network configuration request, the service attribute identifier of each type of network resource information to be configured is obtained, wherein the network configuration request carries service information, device information and network resource information to be configured;

[0071] According to some embodiments, the execution subject of this disclosure is a network device. The name of the network device is not limited. For example, the network device may also be called a server, or a server cluster, etc.

[0072] In some embodiments, a network configuration request may be, for example, a request sent by a terminal to configure network resource information. This network configuration request is not specifically a fixed request. For example, the network configuration request may change if the sending end changes. For example, the terminal sending the network configuration request may specifically be a business order application. For example, the network configuration request may change if the time of the request changes. For example, the network configuration request may change if the information included in the network configuration request changes.

[0073] According to some embodiments, network resource information can be used, for example, to indicate network resources. Here, network resource information does not specifically refer to any particular fixed resource. For example, when the type of resource included in the network resource information changes, the network resource information may also change accordingly. For example, when the amount of information corresponding to the network resource information changes, the network resource information may also change accordingly.

[0074] In some embodiments, a service attribute identifier can be used to uniquely identify a service attribute. This service attribute does not specifically refer to a particular fixed service attribute or a particular type of service attribute. For example, when the method of determining a service attribute changes, the service attribute identifier can also change accordingly. For example, when the method of classifying network resource information changes, the service attribute identifier can also change accordingly.

[0075] According to some embodiments, service information may be used to indicate the service information being executed by the current network configuration request sender, or to provide information about the service corresponding to the network resource information to be configured. This service information may include, for example, a service interface, a service interface description, and a physical gateway address.

[0076] In some embodiments, device information may be used to indicate information about the device sending the network configuration request. This device information includes, but is not limited to, device identifier, device type, and device manufacturer. This device information does not refer to any specific, fixed information. For example, the device information may change accordingly when the amount of information it includes changes. Similarly, the device information may change accordingly when the specific information corresponding to it changes.

[0077] According to some embodiments, the network resource information to be configured can be used, for example, to indicate network resources that have not been configured but need to be configured. This network resource information to be configured does not specifically refer to a single fixed network resource. For example, when the network configuration request changes, the network resource information to be configured can also change accordingly. Different categories can correspond to different network resource information to be configured.

[0078] According to some embodiments, in response to a received network configuration request, a service attribute identifier for each type of network resource information to be configured is obtained, wherein the network configuration request carries service information, device information, and network resource information to be configured.

[0079] In step S12, a set of configuration instructions is obtained based on the device information, the network resource information to be configured, and the instruction library;

[0080] In some embodiments, an instruction library may be a collection of at least one instruction. This instruction library is not specifically defined as a fixed library. For example, the instruction library may change when the number of instructions corresponding to it changes. Similarly, the instruction library may change when a particular instruction in the library changes. Furthermore, the instruction library may change when a modification instruction for the instruction library is received.

[0081] In some embodiments, the configuration instruction set may be a set of configuration instructions obtained after translating the network resource information to be configured. This configuration instruction set may be a collection of at least one configuration instruction. The configuration instruction set does not specifically refer to a fixed set. For example, when the configuration instructions included in the configuration instruction set change, the configuration instruction set may also change accordingly. For example, when a particular configuration instruction in the configuration instruction set changes, the configuration instruction set may also change accordingly.

[0082] In some embodiments, a set of configuration instructions is obtained based on the device information, the network resource information to be configured, and the instruction library.

[0083] In step S13, a target neural network algorithm is used to extract the real-time configuration information and the set of configuration instructions to obtain the configuration relationship structure corresponding to the network resource information to be configured.

[0084] In some embodiments, the target neural network algorithm may be, for example, a pre-trained algorithm ready for information extraction. This target neural network algorithm is not specifically defined by a single, fixed algorithm. For example, the target neural network algorithm may change accordingly when the parameters within it change. Similarly, the target neural network algorithm may change accordingly when the training method corresponding to it changes.

[0085] According to some embodiments, the real-time configuration information may be, for example, the factual configuration information of the device to be operated, obtained through an interface. This real-time configuration information does not specifically refer to any fixed information. For example, when the time point at which the real-time configuration information is obtained changes, the real-time configuration information also changes accordingly. For example, when the device to be operated changes, the real-time configuration information may also change accordingly.

[0086] In some embodiments, the mate relationship structure may consist of a set of ordered, hierarchical view configuration instructions. This mate relationship structure is not specifically defined by a fixed structure. For example, the mate relationship structure may change accordingly when the configuration instructions change.

[0087] According to some embodiments, a target neural network algorithm is used to extract real-time configuration information and the set of configuration instructions to obtain a configuration relationship structure corresponding to the network resource information to be configured.

[0088] In step S14, the configuration instruction set and the business attribute identifier are used to perform part-of-speech tagging and information retrieval on the real-time configuration information, thereby adjusting the configuration relationship structure and outputting a dynamic instruction model.

[0089] According to some embodiments, part-of-speech tagging can be a process of analyzing real-time configuration information and configuration relationship structures before performing part-of-speech tagging. This part-of-speech tagging process is not specifically defined by any particular method. For example, different tagging methods will yield different part-of-speech tagging results.

[0090] According to some embodiments, information retrieval may be, for example, a process of retrieving real-time configuration information and configuration relationship structures.

[0091] In some embodiments, the configuration instruction set and the business attribute identifier can be used to perform part-of-speech tagging and information retrieval on the real-time configuration information, thereby adjusting the configuration relationship structure and outputting a dynamic instruction model.

[0092] In some or related embodiments, in response to a received network configuration request, a service attribute identifier for each type of network resource information to be configured is obtained. The network configuration request carries service information, device information, and network resource information to be configured. Based on the device information, the network resource information to be configured, and an instruction library, a configuration instruction set is obtained. A target neural network algorithm is used to extract the real-time configuration information and the configuration instruction set to obtain a configuration relationship structure corresponding to the network resource information to be configured. The configuration instruction set and the service attribute identifier are used to perform part-of-speech tagging and information retrieval on the real-time configuration information, completing the adjustment of the configuration relationship structure and outputting a dynamic instruction model. Therefore, network resources to be configured can be dynamically orchestrated through network configuration requests without the need for manual sorting of preset service models, reducing labor costs. Furthermore, the network resource information of the existing network can be dynamically adjusted according to the network configuration request. When the number of services is large or the service model changes, the workload of manual analysis is reduced. The dynamic instruction model can be updated, improving the efficiency and accuracy of dynamic instruction acquisition and reducing the failure probability of dynamic instruction model issuance.

[0093] Figure 2 This is a flowchart illustrating a dynamic orchestration method according to an exemplary embodiment, such as... Figure 2 As shown, this dynamic orchestration method can be used in dynamic orchestration scenarios, and includes the following steps:

[0094] In step S21, in response to the received network configuration request, the service attribute identifier of each type of network resource information to be configured is obtained, wherein the network configuration request carries service information, device information and network resource information to be configured;

[0095] The specific process is as described above and will not be repeated here.

[0096] According to some embodiments, Figure 3 This is a schematic diagram illustrating a dynamic orchestration system according to an exemplary embodiment. For example... Figure 3 As shown, after receiving business information, device information, and network resource information to be configured, the business order application forwards the network configuration request to the resource identification module of the network device through the northbound interface to complete the business attribute identification of the network resource to be configured.

[0097] In step S22, based on the device information and the network resource information to be configured, a set of mapping relationships corresponding to the network resource information to be configured is obtained from the instruction library;

[0098] The specific process is as described above and will not be repeated here.

[0099] In step S23, the device information, the network resource information to be configured, and the mapping relationship set are used to obtain a set of configuration instructions;

[0100] The specific process is as described above and will not be repeated here.

[0101] According to some embodiments, the method further includes:

[0102] Based on the network resource information to be configured, the device information, and the service scenario information, the service attribute identifier of each type of network resource information to be configured is mapped to obtain the tokens data corresponding to the service attribute identifier.

[0103] According to some embodiments, the resource identification layer of a network device can identify the service attributes of each type of network resource to be configured, so that the instruction configuration model can process and understand them. The classification dimensions corresponding to the network resource information to be configured may include service interfaces, gateway interfaces, physical gateway addresses, customer IP addresses, VLANs, etc. For the same type of network resource, the corresponding service attributes will differ depending on the service scenario and the device type. For example, regarding "service interfaces," device A can support multiple customers' configuration data accessing the same "service interface," while device B only supports a single customer having only one "service interface." To enable the instruction configuration model to calculate and process these service attributes, these near-natural language service attributes can be mapped to token data, for example, using the following mapping method:

[0104] BIZ i ={R j D k S p},(i,j,k,p∈[1,2,3...N]}

[0105] Among them, BIZ i Represents a set of business attributes; R j D represents a set of network resources; k Represents a set of device types; S p This represents a set of business scenarios.

[0106] According to some embodiments, a set of configuration instructions is mapped from an instruction library based on device information and network resource information to be configured; wherein, the instruction library is used to store configuration instructions for various types of devices across the entire network; the set of configuration instructions can, for example, be a set of unordered, hierarchical, and undefined instructions, and its mapping method is as follows:

[0107] INS q1 ={R j1 D k}={<Network Resource Configuration Instruction 1>};

[0108] INS q2 ={R j2 D k} = {<Network Resource Configuration Instruction 2.1> | <Network Resource Configuration Instruction 2.2>};

[0109] INS q3 ={R j3 D k} = {<Network resource configuration instruction 3>, <Network resource configuration instruction 4>};

[0110] Wherein, INSq is the configuration command set for the network resource to be configured; Rj represents the network resource set; Dk represents the device type set; "|" indicates that the network resource corresponds to multiple configuration commands;

[0111] For example, for a service accessed by device A, the network resources to be configured on the BNG side include the service interface, service interface description, physical gateway address, VLAN, customer IP address, direct connection routing policy, etc. The configuration instruction set mapped from the device information and the network resource information to be configured is as follows:

[0112] INS1={R1, D1}={<interface [Eth-Trunk108.1603]>};

[0113] INS2={R2, D1}={<description [FoShanSanShui]>};

[0114] INS3={R3, D1}={<ip address [183.238.198.33 255.255.255.248]|ip address[183.238.198.33 255.255.255.248]secondary>};

[0115] INS4={R4, D1}={<qinq termination pe-vid

[1603] ce-vid

[3004] >};

[0116] INS5={R5, D1}={<dhcp snooping bind-table static ip-address[183.238.198.34] vlan

[1603] ce-vlan

[3004] >};

[0117] INS6={R6, D1}={<ip ip-prefix [Direct_Route] index []permit[183.233.6.228 32]>};

[0118] It should be noted that, under the same device, the same type of network resource may correspond to multiple configuration commands. For example, device A may have the following commands for configuring the physical gateway:<ip address []> and<ip address []secondary> There are two types. The instruction policy library is only responsible for mapping the configuration instructions for network resources, and is not responsible for specifying unique instructions.

[0119] In step S24, a target neural network algorithm is used to extract the real-time configuration information and the set of configuration instructions to obtain the configuration relationship structure corresponding to the network resource information to be configured.

[0120] The specific process is as described above and will not be repeated here.

[0121] According to some embodiments, the method further includes:

[0122] Acquire an initial neural network model and training data, wherein the training data includes configuration information of at least one managed device, a set of historical configuration instructions, and at least one historical dynamic instruction model;

[0123] Obtain the network weights and thresholds of the initial neural network at a first time step, wherein the first time step is the time when the initial neural network is initialized;

[0124] Obtain the input and output information of neurons in each layer of the initial neural network model;

[0125] Based on the output information of each layer of neurons, obtain the energy function corresponding to the initial neural network model;

[0126] Based on the energy function, the input information and output information of each layer of neurons, obtain the first adjustment amount of the network weights between two adjacent layers of neurons and the second adjustment amount of the threshold.

[0127] Based on the energy function, the first adjustment amount and the second adjustment amount, the network weights and thresholds at the second time are determined, wherein the second time is adjacent to the first time and close to the current time.

[0128] Based on the network weights and thresholds at the second time step, the initial neural network model is adjusted to obtain the target neural network model. Therefore, the target neural network model can be obtained based on the initial neural network model and training data, improving the accuracy of model acquisition.

[0129] According to some embodiments, each layer of neurons includes three layers of neurons. The step of obtaining a first adjustment amount for the network weights between adjacent layers of neurons and a second adjustment amount for the threshold based on the energy function, the input information, and the output information of each layer of neurons includes...

[0130] Based on the output data of the initial neural network model, the output information of the third layer neurons, the output information of the second layer neurons, and the adjustment coefficients, the first adjustment amount of the network weights between the second layer neurons and the third layer neurons is obtained;

[0131] Based on the output data of the initial neural network model, the output information of the third layer neurons, the all-1 vector, and the adjustment coefficient, a second adjustment amount of the threshold between the second layer neurons and the third layer neurons is obtained;

[0132] Based on the output data of the initial neural network model, the output information of the third layer neurons, the output information of the second layer neurons, the input data of the initial neural network model, and the adjustment coefficient, a first adjustment amount of the network weights between the second layer neurons and the first layer neurons is obtained;

[0133] Based on the output data of the initial neural network model, the output information of the third layer neurons, the output information of the second layer neurons, the input data of the initial neural network model, the all-1 vector, and the adjustment coefficient, a second adjustment amount of the threshold between the second layer neurons and the first layer neurons is obtained.

[0134] According to some embodiments, the model adaptive layer based on network devices can learn and extract the configuration relationship structure of the network resources to be configured through neural network algorithms; and automatically realize the routing selection between the devices to be configured by outputting an ordered set of configuration instructions through the neural network.

[0135] According to some embodiments, the BP neural network learns from the configuration schemes of a large number of existing network devices, and for the configuration information of a certain device, it can extract the configuration relationship structure of the corresponding network resources; the training process of the BP neural network is as follows:

[0136] 1. Determine the BP network structure and training data:

[0137] The configuration information of all network-managed devices is obtained. The device configuration information and configuration instruction set are used as input samples for the BP neural network, and the dynamic instruction model is used as the output sample, forming a 5-input, 1-output training network. The maximum number of training iterations is set to 5000, the number of hidden layer neurons is 5, the network learning rate is 0.035, the target training error is 0.65x10⁻³, and a momentum factor is added by default. The obtained training data can be shown in Table 1, for example.

[0138] Table 1

[0139]

[0140] 2. Initialize network weights and thresholds

[0141] Network devices can set preconditions: ① Set training steps: train in batches; ② Set the threshold to a form similar to the weights, that is, treat the threshold as a random number where the sample input is 1; ③ Transpose the original training data into row-by-row input; ④ Initialize the network and assign random number matrices to the network's weights and thresholds.

[0142] Since the network has 2 input factors, 3 hidden layer neurons, and 1 output, the weights Wij(t) of the first and second layers are set to 2. A random number matrix of 3; set the threshold Bij(t) of the second layer neurons to 3. A matrix of 1; set the weight Wjk(t) between the second and third layers to 3. A random matrix of 1; set the threshold Bjk(t) of the third layer to 1. A matrix of 1.

[0143] 3. Calculate the input and output of the neuron.

[0144] The input and output of the first layer are equal to the values ​​of the actual input samples, O1=X (where X is the input sample and O1 is the first layer output sample), which is a 2^32^2 ... A matrix of size 30.

[0145] The input I2 to the second layer of neurons is equal to the sum of the values ​​of all neurons in the first layer and the threshold, i.e.: I2 = Wij X+Bij ones, is a 3 A matrix of size 30, where ones is a matrix consisting entirely of 1s;

[0146] The output of the second layer of neurons, It is a 2 A data matrix of 3;

[0147] The input to the third layer of neurons, I3=Wjk O2+Bjk ones, is a 1 A matrix of 30;

[0148] The output of the third layer of neurons is O3=I3.

[0149] 4. Calculate the energy function E

[0150] The purpose of calculating the energy function (the sum of squared errors between the network output and the actual output samples) is to stop training the network once a predetermined error is reached. Assuming the actual output sample is Y, then according to the definition of E:

[0151]

[0152] 5. Calculate the adjustment amount of weights and thresholds between the second and third layers.

[0153]

[0154]

[0155] 6. Calculate the weight and threshold adjustment amounts between the first and second layers.

[0156] Based on the idea of ​​backpropagation of errors, first calculate the weight and threshold adjustment between the second and third layers, and then calculate the weight and threshold adjustment between the first and second layers.

[0157]

[0158]

[0159] 7. Calculate the adjusted weights and thresholds to obtain the optimal BP neural network model.

[0160] Add the respective adjustment amounts to the weights and thresholds of each layer at time t, and assign them to the weights and thresholds at time t+1:

[0161]

[0162]

[0163]

[0164]

[0165] In step S25, the configuration instruction set and the business attribute identifier are used to perform part-of-speech tagging and information retrieval on the real-time configuration information, thereby adjusting the configuration relationship structure and outputting a dynamic instruction model.

[0166] The specific process is as described above and will not be repeated here.

[0167] According to some embodiments, real-time configuration information of the device to be operated can be obtained through the southbound interface; the real-time configuration information and configuration instruction set of the device to be operated are input into a trained BP neural network to extract the configuration relationship structure of the network resources to be configured; the configuration relationship structure consists of a batch of ordered configuration instructions with view hierarchy.

[0168] According to some embodiments, Figure 4 This is a schematic diagram illustrating the training of a network model according to an exemplary embodiment. For example... Figure 4 As shown, in order to improve the accuracy of configuration relationship structure extraction, the configuration of all network devices is collected on a daily basis, the training samples are updated, and the BP network is relearned.

[0169] According to some embodiments, the step of using the configuration instruction set and the business attribute identifier to perform part-of-speech tagging and information retrieval on the real-time configuration information, adjusting the configuration relationship structure, and outputting a dynamic instruction model includes:

[0170] The real-time configuration information and the configuration relationship structure are input into the Word2Vec model to obtain the first word segmentation vector representation information and the first part-of-speech vector representation information corresponding to the real-time configuration information, and to obtain the second word segmentation vector representation information and the second part-of-speech vector representation information corresponding to the configuration relationship structure.

[0171] Based on the first word segmentation vector representation information, the first part-of-speech vector representation information, the second word segmentation vector representation information, and the second part-of-speech vector representation information, obtain the location information and similarity matrix corresponding to the real-time configuration information, as well as the location information and similarity matrix corresponding to the configuration relationship structure;

[0172] Based on the location information and similarity matrix corresponding to the real-time configuration information and the location information and similarity matrix corresponding to the configuration relationship structure, the target location corresponding to the real-time configuration information and the configuration relationship structure is obtained, wherein the target location is the location with the highest similarity between the location information corresponding to the real-time configuration information and the location information corresponding to the configuration relationship structure;

[0173] Obtain the word segmentation vector representation corresponding to the target position;

[0174] The resource conflict identification result is obtained based on the business attribute identifier corresponding to the word segmentation vector;

[0175] If the resource conflict identification result indicates that there is no resource conflict, the configuration relationship structure is adjusted and a dynamic instruction model is output.

[0176] According to some embodiments, the method further includes:

[0177] The configuration instruction set and the business attribute identifier are used to perform part-of-speech tagging and information retrieval on the real-time configuration information to obtain the processed real-time configuration information;

[0178] The configuration relationship structure is tagged with part-of-speech tags and information is retrieved using the configuration instruction set and the business attribute identifier to obtain the processed configuration relationship structure.

[0179] According to some embodiments, the model self-optimization layer based on network devices can combine the service attributes and configuration instruction sets of the network resources to be configured to perform part-of-speech tagging and information retrieval on the real-time configuration information of the devices to be operated, complete the adjustment of the configuration relationship structure, and output a dynamic instruction model. Therefore, combining AI algorithms, part-of-speech tagging, and information retrieval technologies for instruction orchestration can improve the matching between the dynamic instruction model and the existing network configuration, enhance the adaptiveness of the existing network during service activation, achieve high configuration accuracy, and reduce the new service launch cycle.

[0180] The real-time configuration information and configuration relationship structure of the device to be operated are segmented and tagged with parts of speech. Then, the real-time configuration information and configuration relationship structure are input into a Word2Vec model to obtain segmented vector representations and part-of-speech vector representations of the real-time configuration information and configuration relationship structure. Based on these representations, the corresponding positional information and similarity matrix are obtained. Finally, the similarity between the real-time configuration information and configuration relationship structure is judged to identify positions in the real-time configuration information that are highly similar to the configuration relationship structure. Highly similar segmented words are extracted for business attribute judgment. If a resource conflict is determined based on the business attribute, a conflict warning is output and the dynamic instruction model is rejected. If no resource conflict is determined based on the business attribute, the configuration relationship structure is further adjusted.

[0181] According to some embodiments, in the Internet leased line shared gateway service scenario, the service interface of device A supports access to the configuration information of multiple customers, and the service interface to be configured is determined to be configured on the device to be operated based on word segmentation and service attributes.

[0182] According to some embodiments, the configuration model for device A is as follows:

[0183] INS1={R1, D1}={<interface [Eth-Trunk108.1603]>}

[0184] INS2={R2, D1}={<description [FoShanSanShui]>}

[0185] INS3={R3, D1}={<ip address [183.238.198.33 255.255.255.248]|ip address[183.238.198.33 255.255.255.248]secondary>}

[0186] INS4={R4, D1}={<qinq termination pe-vid

[1603] ce-vid

[3004] >}

[0187] INS5={R5, D1}={<dhcp snooping bind-table static ip-address[183.238.198.34] vlan

[1603] ce-vlan

[3004] >}

[0188] INS6={R6, D1}={<ip ip-prefix [Direct_Route] index []permit[183.233.6.228 32]>};

[0189] According to some embodiments, the vector model fine-tunes the instructions and the corresponding operation data, and then converts the above instructions into vectors, as shown in Table 2.

[0190] Table 2

[0191]

[0192] According to some embodiments, device A has been configured with the following instructions:

[0193] INS1={R1, D1}={<interface [Eth-Trunk108.1603]>}

[0194] INS2={R2, D1}={<description [FoShanSanShui]>}

[0195] Then, to identify if the operation requires entering a sub-interface, the conflict configuration in the instruction set needs to be set as INS2={R2, D1}={<description []> Discarding the incorrect instructions, the optimal dynamic instruction model is finally output, as follows:

[0196] INS1={R1, D1}={<interface [Eth-Trunk108.1603]>}

[0197] INS3={R3, D1}={<ip address [183.238.198.33 255.255.255.248]|ip address[183.238.198.33 255.255.255.248]secondary>}

[0198] INS4={R4, D1}={<qinq termination pe-vid

[1603] ce-vid

[3004] >}

[0199] INS5={R5, D1}={<dhcp snooping bind-table static ip-address[183.238.198.34] vlan

[1603] ce-vlan

[3004] >}

[0200] INS6={R6, D1}={<ip ip-prefix [Direct_Route] index []permit[183.233.6.228 32]>}

[0201] In one or related embodiments, a set of mapping relationships corresponding to the network resource information to be configured can be obtained from the instruction library based on the device information and the network resource information to be configured; a set of configuration instructions can be obtained using the device information, the network resource information to be configured, and the set of mapping relationships; therefore, the set of mapping relationships can be filtered according to the instruction library to improve configuration efficiency and accuracy, reduce order blocking, improve the accuracy of obtaining the set of configuration instructions, and improve the accuracy of obtaining the dynamic orchestration model.

[0202] A block diagram of a dynamic orchestration apparatus is shown according to an exemplary embodiment. (Refer to...) Figure 5 The device 500 includes:

[0203] The identifier acquisition unit 501 is used to acquire the service attribute identifier of each type of network resource information to be configured in response to the received network configuration request, wherein the network configuration request carries service information, device information and network resource information to be configured;

[0204] The set acquisition unit 502 is used to acquire a set of configuration instructions based on the device information, the network resource information to be configured, and the instruction library;

[0205] The structure acquisition unit 503 is used to extract real-time configuration information and the set of configuration instructions using a target neural network algorithm, and to obtain the configuration relationship structure corresponding to the network resource information to be configured;

[0206] The model output unit 504 is used to perform part-of-speech tagging and information retrieval on the real-time configuration information using the configuration instruction set and the business attribute identifier, to complete the adjustment of the configuration relationship structure, and to output a dynamic instruction model.

[0207] According to some embodiments, the identifier acquisition unit 501 is further configured to:

[0208] Based on the network resource information to be configured, the device information, and the service scenario information, the service attribute identifier of each type of network resource information to be configured is mapped to obtain the tokens data corresponding to the service attribute identifier.

[0209] According to some embodiments, when the set acquisition unit 502 acquires a set of configuration instructions based on the device information, the network resource information to be configured, and the instruction library, it is specifically used for:

[0210] Based on the device information and the network resource information to be configured, obtain a set of mapping relationships corresponding to the network resource information to be configured from the instruction library;

[0211] A set of configuration instructions is obtained using the device information, the network resource information to be configured, and the mapping relationship set.

[0212] According to some embodiments, the model output unit 504 is also used for:

[0213] Acquire an initial neural network model and training data, wherein the training data includes configuration information of at least one managed device, a set of historical configuration instructions, and at least one historical dynamic instruction model;

[0214] Obtain the network weights and thresholds of the initial neural network at a first time step, wherein the first time step is the time when the initial neural network is initialized;

[0215] Obtain the input and output information of neurons in each layer of the initial neural network model;

[0216] Based on the output information of each layer of neurons, obtain the energy function corresponding to the initial neural network model;

[0217] Based on the energy function, the input information and output information of each layer of neurons, obtain the first adjustment amount of the network weights between two adjacent layers of neurons and the second adjustment amount of the threshold.

[0218] Based on the energy function, the first adjustment amount and the second adjustment amount, the network weights and thresholds at the second time are determined, wherein the second time is adjacent to the first time and close to the current time.

[0219] Based on the network weights and thresholds at the second time step, the initial neural network model is adjusted to obtain the target neural network model.

[0220] According to some embodiments, each layer of neurons includes three layers of neurons. The model output unit 504 is used to obtain a first adjustment amount of the network weights between two adjacent layers of neurons and a second adjustment amount of the threshold based on the energy function, the input information and output information of each layer of neurons, including:

[0221] Based on the output data of the initial neural network model, the output information of the third layer neurons, the output information of the second layer neurons, and the adjustment coefficients, the first adjustment amount of the network weights between the second layer neurons and the third layer neurons is obtained;

[0222] Based on the output data of the initial neural network model, the output information of the third layer neurons, the all-1 vector, and the adjustment coefficient, a second adjustment amount of the threshold between the second layer neurons and the third layer neurons is obtained;

[0223] Based on the output data of the initial neural network model, the output information of the third layer neurons, the output information of the second layer neurons, the input data of the initial neural network model, and the adjustment coefficient, a first adjustment amount of the network weights between the second layer neurons and the first layer neurons is obtained;

[0224] Based on the output data of the initial neural network model, the output information of the third layer neurons, the output information of the second layer neurons, the input data of the initial neural network model, the all-1 vector, and the adjustment coefficient, a second adjustment amount of the threshold between the second layer neurons and the first layer neurons is obtained.

[0225] According to some embodiments, the model output unit 504, when using the configuration instruction set and the business attribute identifier to perform part-of-speech tagging and information retrieval on the real-time configuration information, and to complete the adjustment of the configuration relationship structure, outputs a dynamic instruction model, specifically for:

[0226] The real-time configuration information and the configuration relationship structure are input into the Word2Vec model to obtain the first word segmentation vector representation information and the first part-of-speech vector representation information corresponding to the real-time configuration information, and to obtain the second word segmentation vector representation information and the second part-of-speech vector representation information corresponding to the configuration relationship structure.

[0227] Based on the first word segmentation vector representation information, the first part-of-speech vector representation information, the second word segmentation vector representation information, and the second part-of-speech vector representation information, obtain the location information and similarity matrix corresponding to the real-time configuration information, as well as the location information and similarity matrix corresponding to the configuration relationship structure;

[0228] Based on the location information and similarity matrix corresponding to the real-time configuration information and the location information and similarity matrix corresponding to the configuration relationship structure, the target location corresponding to the real-time configuration information and the configuration relationship structure is obtained, wherein the target location is the location with the highest similarity between the location information corresponding to the real-time configuration information and the location information corresponding to the configuration relationship structure;

[0229] Obtain the word segmentation vector representation corresponding to the target position;

[0230] The resource conflict identification result is obtained based on the business attribute identifier corresponding to the word segmentation vector;

[0231] If the resource conflict identification result indicates that there is no resource conflict, the configuration relationship structure is adjusted and a dynamic instruction model is output.

[0232] According to some embodiments, the model output unit 504 is also used to perform part-of-speech tagging and information retrieval on the real-time configuration information using the configuration instruction set and the business attribute identifier, so as to obtain the processed real-time configuration information;

[0233] The configuration relationship structure is tagged with part-of-speech tags and information is retrieved using the configuration instruction set and the business attribute identifier to obtain the processed configuration relationship structure.

[0234] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0235] In some or related embodiments, an identifier acquisition unit is used to acquire a service attribute identifier for each type of network resource information to be configured in response to a received network configuration request, wherein the network configuration request carries service information, device information, and network resource information to be configured; a set acquisition unit is used to acquire a configuration instruction set based on the device information, the network resource information to be configured, and an instruction library; a structure acquisition unit is used to extract the real-time configuration information and the configuration instruction set using a target neural network algorithm to acquire a configuration relationship structure corresponding to the network resource information to be configured; and a model output unit is used to perform part-of-speech tagging and information retrieval on the real-time configuration information using the configuration instruction set and the service attribute identifier, complete the adjustment of the configuration relationship structure, and output a dynamic instruction model. Therefore, the network resources to be configured can be dynamically orchestrated through network configuration requests without the need for manual sorting of preset service models, which can reduce labor costs. Furthermore, the network resource information of the existing network can be dynamically adjusted according to the network configuration request. When the number of services is large or the service model changes, the workload of manual analysis is reduced. The dynamic instruction model can be updated, which can improve the efficiency and accuracy of dynamic instruction acquisition and reduce the failure probability of dynamic instruction model issuance.

[0236] Figure 6 This is a block diagram of a network device 600 provided in an embodiment of this disclosure. For example, network device 600 can be provided as a network device. See also... Figure 6 The network device 600 includes a processing component 622, which further includes at least one processor, and memory resources represented by memory 632 for storing instructions, such as application programs, that can be executed by the processing component 622. The application programs stored in memory 632 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 622 is configured to execute instructions to perform any of the methods described above applied to the network device.

[0237] Network device 600 may also include a power supply component 627 configured to perform power management of network device 600, a wired or wireless network interface 650 configured to connect network device 600 to a network, and an input / output (I / O) interface 658. Network device 600 can operate on an operating system stored in memory 632, such as Windows Server™, Mac OS X™, Unix™, Linux™, Free BSD™, or similar.

[0238] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0239] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0240] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0241] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0242] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0243] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0244] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0245] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A dynamic arrangement method, characterized in that, include: In response to a received network configuration request, the service attribute identifier of each type of network resource information to be configured is obtained, wherein the network configuration request carries service information, device information and network resource information to be configured; Based on the device information, the network resource information to be configured, and the instruction library, obtain a set of configuration instructions; A target neural network algorithm is used to extract real-time configuration information and the set of configuration instructions to obtain a configuration relationship structure corresponding to the network resource information to be configured. The configuration instruction set and the business attribute identifier are used to perform part-of-speech tagging and information retrieval on the real-time configuration information, thereby adjusting the configuration relationship structure and outputting a dynamic instruction model; The step of obtaining the configuration instruction set based on the device information, the network resource information to be configured, and the instruction library includes: Based on the device information and the network resource information to be configured, obtain a set of mapping relationships corresponding to the network resource information to be configured from the instruction library; A set of configuration instructions is obtained using the device information, the network resource information to be configured, and the mapping relationship set.

2. The method according to claim 1, characterized in that, The method further includes: Based on the network resource information to be configured, the device information, and the service scenario information, the service attribute identifier of each type of network resource information to be configured is mapped to obtain the tokens data corresponding to the service attribute identifier.

3. The method according to claim 1, characterized in that, The method further includes: Acquire an initial neural network model and training data, wherein the training data includes configuration information of at least one managed device, a set of historical configuration instructions, and at least one historical dynamic instruction model; Obtain the network weights and thresholds of the initial neural network at a first time step, wherein the first time step is the time when the initial neural network is initialized; Obtain the input and output information of neurons in each layer of the initial neural network model; Based on the output information of each layer of neurons, obtain the energy function corresponding to the initial neural network model; Based on the energy function, the input information and output information of each layer of neurons, obtain the first adjustment amount of the network weights between two adjacent layers of neurons and the second adjustment amount of the threshold. Based on the energy function, the first adjustment amount and the second adjustment amount, the network weights and thresholds at the second time are determined, wherein the second time is adjacent to the first time and close to the current time. Based on the network weights and thresholds at the second time step, the initial neural network model is adjusted to obtain the target neural network model.

4. The method according to claim 3, characterized in that, in, Each layer of neurons comprises three layers of neurons. The step of obtaining a first adjustment amount for the network weights and a second adjustment amount for the threshold between adjacent layers of neurons, based on the energy function, the input information, and the output information of each layer of neurons, includes: Based on the output data of the initial neural network model, the output information of the third layer neurons, the output information of the second layer neurons, and the adjustment coefficients, the first adjustment amount of the network weights between the second layer neurons and the third layer neurons is obtained. Based on the output data of the initial neural network model, the output information of the third layer neurons, the all-1 vector, and the adjustment coefficient, a second adjustment amount of the threshold between the second layer neurons and the third layer neurons is obtained; Based on the output data of the initial neural network model, the output information of the third layer neurons, the output information of the second layer neurons, the input data of the initial neural network model, and the adjustment coefficient, the first adjustment amount of the network weights between the second layer neurons and the first layer neurons is obtained; Based on the output data of the initial neural network model, the output information of the third layer neurons, the output information of the second layer neurons, the input data of the initial neural network model, the all-1 vector, and the adjustment coefficient, a second adjustment amount of the threshold between the second layer neurons and the first layer neurons is obtained.

5. The method according to claim 1, characterized in that, The process of using the configuration instruction set and the business attribute identifier to perform part-of-speech tagging and information retrieval on the real-time configuration information, adjusting the configuration relationship structure, and outputting a dynamic instruction model includes: The real-time configuration information and the configuration relationship structure are input into the Word2Vec model to obtain the first word segmentation vector representation information and the first part-of-speech vector representation information corresponding to the real-time configuration information, and to obtain the second word segmentation vector representation information and the second part-of-speech vector representation information corresponding to the configuration relationship structure. Based on the first word segmentation vector representation information, the first part-of-speech vector representation information, the second word segmentation vector representation information, and the second part-of-speech vector representation information, obtain the location information and similarity matrix corresponding to the real-time configuration information, as well as the location information and similarity matrix corresponding to the configuration relationship structure; Based on the location information and similarity matrix corresponding to the real-time configuration information and the location information and similarity matrix corresponding to the configuration relationship structure, the target location corresponding to the real-time configuration information and the configuration relationship structure is obtained, wherein the target location is the location with the highest similarity between the location information corresponding to the real-time configuration information and the location information corresponding to the configuration relationship structure; Obtain the word segmentation vector representation corresponding to the target position; The resource conflict identification result is obtained based on the business attribute identifier corresponding to the word segmentation vector; If the resource conflict identification result indicates that there is no resource conflict, the configuration relationship structure is adjusted and a dynamic instruction model is output.

6. The method according to claim 5, characterized in that, The method further includes: The configuration instruction set and the business attribute identifier are used to perform part-of-speech tagging and information retrieval on the real-time configuration information to obtain the processed real-time configuration information; The configuration relationship structure is tagged with part-of-speech tags and information is retrieved using the configuration instruction set and the business attribute identifier to obtain the processed configuration relationship structure.

7. A dynamic orchestration device, characterized in that, include: The identifier acquisition unit is used to acquire the service attribute identifier of each type of network resource information to be configured in response to the received network configuration request, wherein the network configuration request carries service information, device information and network resource information to be configured; The set acquisition unit is used to acquire a set of configuration instructions based on the device 3 information, the network resource information to be configured, and the instruction library; The structure acquisition unit is used to extract real-time configuration information and the set of configuration instructions using a target neural network algorithm, and to obtain the configuration relationship structure corresponding to the network resource information to be configured; The model output unit is used to perform part-of-speech tagging and information retrieval on the real-time configuration information using the configuration instruction set and the business attribute identifier, to complete the adjustment of the configuration relationship structure, and to output a dynamic instruction model; The set acquisition unit, when acquiring the configuration instruction set based on the device information, the network resource information to be configured, and the instruction library, specifically performs the following functions: Based on the device information and the network resource information to be configured, obtain a set of mapping relationships corresponding to the network resource information to be configured from the instruction library; A set of configuration instructions is obtained using the device information, the network resource information to be configured, and the mapping relationship set.

8. A network device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the dynamic orchestration method as described in any one of claims 1 to 6.

9. A storage medium storing instructions, characterized in that, When the instruction is executed on the communication device, the communication device performs the dynamic orchestration method as described in any one of claims 1 to 6.

Images