Intention-aware path based routing method and device, computer device, readable storage medium and program product

Abstract

The application relates to an intention perception path-based routing method and device, computer equipment, a computer readable storage medium and a computer program product. By adopting the method, user behavior data can be processed by a multi-dimensional intention recognition model, target user intention of the user can be quickly and accurately obtained, screening is performed in a computing power routing network, an intention perception path is generated, low-delay guidance of service routing is realized based on the intention perception path, direct perception of computing power demand and direct analysis of high-level demand of the user are realized, resource utilization, safety and performance of a computing power scheduling system are improved, and user demand can be responded to more quickly and accurately.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of network communication, and in particular to a routing method and device based on an intention-aware path, a computer device, a computer readable storage medium, and a computer program product. BACKGROUND

[0002] With the rapid development of computing power networks, the problem of uneven allocation of computing resources between nodes is increasingly prominent. In order to better schedule computing power devices from a global perspective, it is necessary to schedule computing power across domains. In traditional technologies, computing power resources are generally allocated and scheduled based on traditional routing protocols. However, since the above traditional routing protocols do not have direct awareness of computing power requirements, the scheduling efficiency of computing power resources is low. SUMMARY

[0003] Therefore, it is necessary to provide a routing method, device, computer device, computer readable storage medium, and computer program product based on an intention-aware path that can efficiently and with low latency meet the routing requirements of computing power, in order to solve the above technical problems.

[0004] In a first aspect, the present application provides a routing method based on an intention-aware path, comprising:

[0005] Obtaining user behavior data, the user behavior data including access requirements and / or resource operation behaviors;

[0006] Processing the user behavior data through a multi-dimensional intention recognition model to obtain a plurality of first encoding results corresponding to the user behavior data;

[0007] For each node in a computing power routing network, determining initial candidate nodes of a next node of the node; and based on a node routing table of the node and the first encoding results, screening among the initial candidate nodes to obtain target candidate nodes;

[0008] Based on the target candidate nodes, generating an intention-aware path, and determining computing power resources corresponding to the intention-aware path in a computing power resource pool.

[0009] In one embodiment, the determination of the initial candidate nodes of the next node of the node and the screening among the initial candidate nodes based on the node routing table of the node and the first encoding results to obtain the target candidate nodes comprises:

[0010] Based on the topology of the computing power routing network, nodes having a direct connection relationship with the node are determined as the initial candidate nodes of the next node of the node;

[0011] In each of the initial candidate nodes, based on a node routing table of the node, a second encoding result of a user intent satisfied by each of the initial candidate nodes is determined;

[0012] Based on the second encoding result of the user intent satisfied by each of the initial candidate nodes, the plurality of first encoding results corresponding to the user behavior data are filtered to obtain a target candidate node.

[0013] In one embodiment, the filtering based on the second encoding result of the user intent satisfied by each of the initial candidate nodes and the plurality of first encoding results corresponding to the user behavior data to obtain a target candidate node comprises:

[0014] Based on the plurality of first encoding results corresponding to the user behavior data, each of the first candidate nodes matching the first encoding result is obtained by filtering based on the second encoding result of each of the initial candidate nodes.

[0015] Based on a preset mapping relationship between the encoding result and the user intent, a target user intent corresponding to each of the first encoding results is determined, and a cost value of each of the first candidate nodes is obtained by calculating the weight of the target user intent and the index value corresponding to each of the target user intents in each of the first candidate nodes.

[0016] The target candidate node is obtained by filtering based on the cost value of each of the first candidate nodes.

[0017] In one embodiment, the intent-aware path includes a plurality of paths; and determining the computing resource corresponding to the intent-aware path in the computing resource pool comprises:

[0018] In the computing resource pool containing a plurality of types of computing resources, the computing resource corresponding to each of the destination network endpoints of each of the paths is determined;

[0019] Based on the priority of each type of computing resource, the computing resource corresponding to each of the destination network endpoints is filtered to obtain the computing resource corresponding to the intent-aware path.

[0020] In one embodiment, the method further comprises:

[0021] Obtaining user feedback data, updating the mapping relationship based on the user feedback data to obtain an updated mapping relationship, and each of the mapping relationships is configured with version information.

[0022] In one embodiment, the encoding result is a color encoding result; the preset mapping relationship between the encoding result and the user intent is a preset mapping relationship between the color encoding result and the user intent; and the method further comprises:

[0023] collecting evaluation information of the user on the target user intention, determining a color coding result satisfying a preset confusion condition based on the evaluation information;

[0024] improving the mapping relationship based on each color coding result satisfying the preset confusion condition, to obtain an improved mapping relationship.

[0025] In a second aspect, the present application further provides a routing device based on an intention perception path, comprising:

[0026] a first acquisition module configured to acquire user behavior data, wherein the user behavior data comprises access demand and / or resource operation behavior;

[0027] a first determination module configured to process the user behavior data by using a multi-dimensional intention recognition model, to obtain a plurality of first coding results corresponding to the user behavior data;

[0028] a second determination module configured to determine, for each node in a computing power routing network, an initial candidate node of a next node of the node, and based on a node routing table of the node and the first coding results, to filter among the initial candidate nodes to obtain a target candidate node;

[0029] a third determination module configured to generate an intention perception path based on each target candidate node, and determine a computing power resource corresponding to the intention perception path in a computing power resource pool.

[0030] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0031] acquiring user behavior data, wherein the user behavior data comprises access demand and / or resource operation behavior; processing the user behavior data by using a multi-dimensional intention recognition model, to obtain a plurality of first coding results corresponding to the user behavior data; determining, for each node in a computing power routing network, an initial candidate node of a next node of the node, and based on a node routing table of the node and the first coding results, filtering among the initial candidate nodes to obtain a target candidate node; generating an intention perception path based on each target candidate node, and determining a computing power resource corresponding to the intention perception path in a computing power resource pool.

[0032] In a fourth aspect, the present application further provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the following steps:

[0033] The user behavior data includes access demand and / or resource operation behavior, the user behavior data is processed through a multi-dimensional intention recognition model to obtain a plurality of first encoding results corresponding to the user behavior data, for each node in the computing power routing network, an initial candidate node of a next node of the node is determined, and the target candidate node is obtained by screening in the initial candidate nodes based on the node routing table of the node and the first encoding result, an intention-aware path is generated based on the target candidate nodes, and the computing power resource corresponding to the intention-aware path is determined in the computing power resource pool.

[0034] In a fifth aspect, the present application further provides a computer program product comprising a computer program which, when executed by a processor, implements the following steps:

[0035] The user behavior data includes access demand and / or resource operation behavior, the user behavior data is processed through a multi-dimensional intention recognition model to obtain a plurality of first encoding results corresponding to the user behavior data, for each node in the computing power routing network, an initial candidate node of a next node of the node is determined, and the target candidate node is obtained by screening in the initial candidate nodes based on the node routing table of the node and the first encoding result, an intention-aware path is generated based on the target candidate nodes, and the computing power resource corresponding to the intention-aware path is determined in the computing power resource pool.

[0036] The above-mentioned routing method and device based on the intention-aware path, computer equipment, computer readable storage medium and computer program product, by using the method, the user behavior data is processed through a multi-dimensional intention recognition model, the target user intention of the user is quickly and accurately obtained, and the intention-aware path is generated by screening in the computing power routing network, the low-delay guidance of the business routing is realized based on the intention-aware path, the direct perception of the computing power demand and the direct analysis of the high-level demand of the user are realized, the resource utilization, security and performance of the computing power scheduling system are improved, and the user demand can be responded more quickly and accurately. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0038] Figure 1An application environment diagram for the routing method based on intention-aware path in one embodiment;

[0039] Figure 2 A flowchart for the routing method based on intention-aware path in one embodiment;

[0040] Figure 3 A flowchart for the step of determining target candidate nodes in one embodiment;

[0041] Figure 4 A flowchart for the step of determining target candidate nodes in another embodiment;

[0042] Figure 5 A flowchart for the step of allocating computing resource in one embodiment;

[0043] Figure 6 A flowchart for the step of improving mapping relationship in one embodiment;

[0044] Figure 7 A communication architecture diagram in one embodiment;

[0045] Figure 8 A structure diagram of computing resource routing node in one embodiment;

[0046] Figure 9 A flowchart for the routing method based on intention-aware path in another embodiment;

[0047] Figure 10 A flowchart for the step of transmitting data stream in one embodiment;

[0048] Figure 11 A structure block diagram of the routing device based on intention-aware path in one embodiment;

[0049] Figure 12 An internal structure diagram of the computer device in one embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical scheme and advantages of the present application clearer, further detailed description will be given to the present application in combination with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0051] The routing method based on intention-aware path provided by the embodiments of the present application can be applied to, for example, Figure 1The application environment of the system is shown. The system includes a user 102, a network device 104, a network 106, a computing power routing network 108, and a computing power resource pool 110. The network device 104 can communicate with each computing power routing node in the computing power routing network 108 through the network 106, and then allocate corresponding computing power resources in the computing power resource pool 110 for the user 102.

[0052] In an exemplary embodiment, a routing method based on intention perception path is provided. The method is applied to a system, which can be a server. Optionally, the server can be a standalone physical server, a server cluster composed of multiple physical servers, or a distributed system. It can also be a cloud server providing cloud computing services. The system includes at least a network device 104 and a computing power routing network 108. The network device 104 can include a user identity authentication module, a routing module, a computing power service routing encapsulation module, and an intention analysis module. The computing power routing network 108 can include multiple computing power routing nodes, each of which can include a computing resource perception module, a routing decision module, a BGP extension module, and a computing power service routing identification module. As shown, Figure 2 The method in this embodiment can include:

[0053] Step 202, obtaining user behavior data.

[0054] The user behavior data includes access demand and / or resource operation behavior.

[0055] Specifically, the user can first perform an identity authentication service. For example, the identity of the user accessing the system can be verified by a user identity authentication module. After verification, the user can access and operate in the system. The system can record the user's access to computing power network resources and operation behavior, i.e., obtain the user's operation behavior data. The system can store the above-mentioned user operation behavior data in the form of system logs or event tracking. The identity authentication service in the user identity authentication module can be OAuth, LDAP, or SAML.

[0056] Step 204, processing the user behavior data by a multi-dimensional intention recognition model to obtain a plurality of first encoding results corresponding to the user behavior data.

[0057] The multi-dimensional intent recognition model can be a multi-dimensional data model based on user demand features, used to map and analyze different user intents, such as low-latency transmission, low cost, and the like. The multi-dimensional deep model can construct multiple data dimensions through a multi-dimensional data set (data cube), determine each data dimension as a type of data feature, and query and filter data through multiple data dimensions. Correspondingly, the multi-dimensional intent recognition model can be a deep learning model or a machine learning model, such as a long short-term memory network, a BERT model, and the like.

[0058] Specifically, the system can input the user behavior data into the multi-dimensional intent recognition model, analyze and identify the user intent in the user behavior data through the multi-dimensional intent recognition model, and obtain the output result of the multi-dimensional intent recognition model. The output result can be multiple encoding results (hereinafter referred to as first encoding results). That is, the system can input the user behavior data into the multi-dimensional intent recognition model, and convert the user behavior data through the multi-dimensional intent recognition model to obtain multiple encoding results. The encoding result can be a color encoding result.

[0059] Step 206, for each node in the computing power routing network, determining an initial candidate node of a next node of the node; and based on the node routing table of the node and the first encoding result, screening among the initial candidate nodes to obtain a target candidate node.

[0060] The computing power routing network can include multiple computing power routing nodes, and each computing power routing node is connected through a network topology. Each computing power routing node can include a computing resource perception module, a routing decision module, a BGP extension module, and a computing power service routing identification module.

[0061] Specifically, after obtaining one or more first encoding results corresponding to the user behavior data, the system can obtain multiple target candidate nodes that can meet the target user intent based on each first encoding result. In one example, for each first encoding result corresponding to the user behavior data received in the computing power routing network, for each computing power routing node, the computing power routing node can determine a next computing power routing node to which the first encoding result or user traffic is transmitted. The specific determination process can be that the current computing power routing node can screen among multiple candidate nodes corresponding to the current computing power routing node to obtain a target candidate node, and determine the target candidate node as the next computing power routing node of the current computing power routing node.

[0062] Step 208, based on each target candidate node, generating an intent-aware path, and determining the computing power resources corresponding to the intent-aware path in the computing power resource pool.

[0063] The computing power resource pool can include multiple types of computing power resources, such as computing power resources of different models and computing power resources of different manufacturers.

[0064] Specifically, after determining the target candidate node of the current computing power routing node, the system can determine the target candidate node as the next computing power routing node of the current computing power routing node, and transmit the first encoding result corresponding to the user behavior data and the user traffic to the next computing power routing node. In this way, the system can determine the next computing power routing node of the current computing power routing node as the current computing power routing node by receiving the first encoding result corresponding to the user behavior data and the user traffic, re-executes the steps after the above embodiment, and obtains the next computing power routing node of the current computing power routing node until the current computing power routing node reaches the computing power resource pool, and generates the intent-aware path. In this way, the system can determine the computing power resource corresponding to the intent-aware path based on the computing power routing node at the end position of the generated intent-aware path, from the multiple types of computing power resources included in the computing power resource pool, and allocate the computing power resource to the user corresponding to the user behavior data and / or user traffic. The user can communicate based on the computing power resource, and the computing power resource is a computing power resource that can meet the user's access demand and / or resource operation behavior.

[0065] In the above routing method based on the intent-aware path, the user behavior data is processed by the multi-dimensional intent recognition model to quickly and accurately obtain each first encoding result corresponding to the target user intent of the user, and the intent-aware path is generated by screening in the computing power routing network. The intent-aware path is used to realize low-delay guidance of service routing, direct perception of computing power demand, and direct analysis of high-level needs of users, thereby improving the resource utilization, security, and performance of the computing power scheduling system, and enabling user demand to be responded to more quickly and accurately.

[0066] In an exemplary embodiment, as shown in FIG. 3, the specific implementation process of the step “determining the initial candidate nodes of the next node of the node; and screening in each initial candidate node based on the node routing table of the node and the first encoding result to obtain the target candidate node” can include: Figure 3

[0067] In step 302, based on the topology structure of the computing power routing network, the nodes having a direct connection relationship with the node are determined as the initial candidate nodes of the next node of the node.

[0068] The topology structure of the computing power routing network represents the connection relationship between each computing power routing node included in the computing power routing network.

[0069] ​Specifically, the system can filter out the nodes having a direct connection relationship with the current node (the current computing power routing node) based on the topology of the computing power routing network, and determine that the nodes having a direct connection relationship with the current node can be initial candidate nodes of the next node of the current node. That is, the system can filter among the multiple initial candidate nodes to determine the next node of the current node.

[0070] Step 304: Among the initial candidate nodes, the second encoding results of the user intents respectively satisfied by the initial candidate nodes are determined based on the node routing table of each node.

[0071] Each node can store a node routing table, which can include multiple IP address information and encoding results corresponding to the IP address information. The IP address information can be a complete IP address or a prefix information of an IP address. The node routing table is used to determine the next node satisfying the target user intent. The encoding result corresponding to the IP address information can represent that the IP address can satisfy the user intent corresponding to the encoding result.

[0072] Specifically, the system can determine the IP address information corresponding to each initial candidate node, and can query the node routing table stored in the current node based on the IP address information of the initial candidate node to obtain the encoding result (hereinafter referred to as the second encoding result) corresponding to each initial candidate node, and determine the user intent that can be satisfied by each initial candidate node and the second encoding result corresponding to the user intent that can be satisfied by each initial candidate node.

[0073] Step 306: Based on the second encoding results of the user intents respectively satisfied by the initial candidate nodes and the multiple first encoding results corresponding to the user behavior data, the target candidate node is obtained.

[0074] Specifically, the system can match the second encoding results of the user intents respectively satisfied by each initial candidate node with the first encoding results respectively corresponding to the user behavior data received by the current node, and filter out one target candidate node or multiple target candidate nodes that can satisfy the target user intent.

[0075] Optionally, the system can determine a plurality of first encoding results of the user behavior data received by the current node; the system can also determine second encoding results of the user intents that can be satisfied by each initial candidate node respectively, and match the plurality of first encoding results corresponding to the target user intent with the second encoding results of the user intents that can be satisfied by each initial candidate node respectively based on the target user intent, so as to determine the initial candidate node as the target candidate node if the plurality of first encoding results corresponding to the target user intent are contained in the second encoding results of the user intents that can be satisfied by the initial candidate node.

[0076] Optionally, the plurality of encoding results corresponding to the target user intent can include an encoding result A and an encoding result B. The system can first eliminate each initial candidate node of the user intents that cannot satisfy the encoding result A based on the first encoding results of the user intents that can be satisfied by each initial candidate node respectively, and then eliminate each initial candidate node of the user intents that cannot satisfy the encoding result B, so as to determine the target candidate node based on the remaining initial candidate nodes, for example, by determining the remaining initial candidate nodes as the target candidate node.

[0077] In this embodiment, different user intents are distinguished by encoding results, the initial screening of the routing nodes is performed based on the encoding results, the optimization of the computing power routing path selection is achieved, and the selection efficiency of the computing power routing nodes is improved.

[0078] In one embodiment, as shown in Figure 4 The specific processing process of the step of "screening the plurality of first encoding results corresponding to the user behavior data based on the second encoding results of the user intents that can be satisfied by each initial candidate node respectively, to obtain the target candidate node" can include:

[0079] At step 402, based on the plurality of first encoding results corresponding to the user behavior data, each first candidate node is obtained by screening the plurality of initial candidate nodes based on the second encoding results of the user intents that can be satisfied by each initial candidate node respectively.

[0080] Specifically, the system can determine a plurality of first encoding results corresponding to the user behavior data received by the current node; the system can also determine second encoding results of the user intents that can be satisfied by each initial candidate node respectively, and match the plurality of first encoding results corresponding to the target user intent with each initial candidate node respectively based on the target user intent, so as to determine the initial candidate node as the first candidate node if the plurality of first encoding results corresponding to the target user intent are contained in the second encoding results of the user intents that can be satisfied by the initial candidate node. Based on this, the system can perform the steps in this embodiment on each initial candidate node respectively to obtain a plurality of first candidate nodes.

[0081] At step 404, based on the preset mapping relationship between the encoding result and the user intent, the target user intent corresponding to each first encoding result is determined, and the cost value of each first candidate node is obtained by calculating the weight of the target user intent and the index value corresponding to each target user intent in each first candidate node.

[0082] The color encoding result can be multi-bit color encoding, for example, 32-bit color encoding. The preset mapping relationship between the color encoding result and the user intent can be a dynamic mapping relationship between the color encoding result and the user intent. Each encoding result can correspond to a different user intent, for example, a mapping relationship between the encoding result and the user intent can be preconfigured, the user intent corresponding to the encoding result A can be low-delay network transmission, the user intent corresponding to the encoding result B can be low-cost network transmission, and the user intent corresponding to the third encoding result C can be a request for computing resources, etc. Based on this, the system can determine the user intent corresponding to each encoding result in the output result by querying the preset mapping relationship between the encoding result and the user intent, i.e., the target user intent represented by the user behavior data.

[0083] Optionally, the weights of the preconfigured user intents respectively represent the importance of different performance indicators. For example, the user intent can be a request for low-delay network transmission, the performance indicator corresponding to this user intent can be delay, and the corresponding index value can be the performance indicator value, i.e., the delay value. The index value corresponding to the user intent satisfied by each first candidate node is the index value of the performance indicator related to the target user intent on the first candidate node. For example, the performance indicator related to the target user intent can be delay, and the index value corresponding to the user intent satisfied by the first candidate node can be the delay value on the first candidate node.

[0084] Specifically, the system can determine the performance indicator related to the target user intent, and after determining each first candidate node, for each candidate node, the system can collect the index value corresponding to the performance indicator related to the target user intent on the first candidate node, and calculate the index value and the weight of each performance indicator by a preset cost algorithm to obtain the cost value corresponding to the first candidate node.

[0085] At step 406, the target candidate node is obtained by screening based on the cost value of each first candidate node.

[0086] Specifically, the system can calculate the indicator value corresponding to each first candidate node and the weight of the performance indicator based on a preset cost algorithm, respectively, to obtain the cost value corresponding to each first candidate node. Based on this, the system can filter based on the cost value of each first candidate node to obtain the first candidate node that meets the preset filtering condition, and determine the first candidate node that meets the preset filtering condition as the target candidate node.

[0087] Optionally, the preset filtering condition can be to filter out the node with the lowest cost value, or to filter out the target number of nodes with the lowest cost value. Correspondingly, the system can determine the first candidate node with the lowest cost value as the target candidate node. The system can also filter out the target number of first candidate nodes with the lowest cost value, and determine the first candidate node as the target candidate node.

[0088] Optionally, the system can calculate the cost value corresponding to the first candidate node by the following formula:

[0089]

[0090] Wherein, the performance indicators related to the target user intent can include latency, bandwidth, and packet loss rate; P represents the path, which can also represent the nodes in the path, i.e. the first candidate node; Cost represents the cost value, Delay represents the latency value on the first candidate node P; Bandwidth represents the bandwidth on the first candidate node P, and Loss represents the packet loss rate on the first candidate node P. w1 represents the weight of the latency, w2 represents the weight of the bandwidth, and w3 represents the weight of the packet loss rate.

[0091] In this embodiment, the cost corresponding to each first candidate node is calculated by the pre-configured weight, which can provide the user with multiple low-cost paths, better adapt to the user demand, and improve the efficiency of the computing power routing.

[0092] In one exemplary embodiment, the intent-aware path includes multiple paths. Specifically, the system can generate multiple paths based on each target candidate node. For example, the target candidate nodes corresponding to the current node can include node 1 and node 2, and correspondingly, the system determines the target candidate node corresponding to the node 1, and then generates the first path, and the system also determines the target candidate node corresponding to the node 2, and then generates the second path. In this way, the system can obtain the intent-aware path based on each path.

[0093] As shown in Figure 5 The specific processing process of the step "determining the computing power resources corresponding to the intent-aware path in the computing power resource pool" includes:

[0094] Step 502, in the computing resource pool containing multiple types of computing resources, respectively determine the computing resources corresponding to the destination network end points of each path.

[0095] Among them, the computing resource pool can contain multiple types of computing resources, for example, it can include computing resources of different models and computing resources of different manufacturers.

[0096] Specifically, the system can determine the destination network port corresponding to each path included in the intention-aware path, that is, determine the computing routing node at the end position of each path. For each path, the system can determine the computing routing node at the end position of the path, and based on the pre-configured correspondence between each computing routing node and computing resource, obtain the computing resource corresponding to the end computing routing node. Based on this, the system can obtain the computing resource corresponding to each path.

[0097] Step 504, based on the priority of each type of computing resource, filtering the computing resources corresponding to each destination network end point to obtain the computing resource corresponding to the intention-aware path.

[0098] Among them, the priority of each type of computing resource can be pre-configured based on the actual application scenario.

[0099] Specifically, the system can filter the computing resources corresponding to the destination network end points of each path based on the pre-configured priority of each type of computing resource, and extract the computing resource corresponding to the intention-aware path.

[0100] Optionally, the system can determine the computing resource with the highest priority as the computing resource corresponding to the intention-aware path. Alternatively, the system can determine the target computing resource with the highest priority as the computing resource corresponding to the intention-aware path and output it to the user. The user can select the target computing resource based on actual needs to obtain the actual use computing resource that meets the user's needs.

[0101] In this embodiment, by pre-configuring different path priorities, automatic selection in the case of multiple intentions and multiple paths is realized, and more flexible path steering and load balancing is realized.

[0102] In one exemplary embodiment, the intention-aware path-based routing method further comprises:

[0103] Obtain user feedback data, update the mapping relationship based on the user feedback data to obtain the updated mapping relationship.

[0104] Among them, each mapping relationship is configured with version information; obtaining the updated mapping relationship can also update the version information of the updated mapping relationship, and can be based on the version information for backtracking.

[0105] Specifically, the system can obtain the data of the real-time feedback of the user, update the mapping relationship between the preset color coding result and the user intention, obtain the updated mapping relationship, for example, the version information of the original mapping relationship can be the first version information, the original mapping relationship is updated to obtain the updated mapping relationship, and the version information of the updated mapping relationship can be the second version information. The mapping relationship can be dynamic, for example, the mapping relationship can be stored through various data storage mechanisms such as databases, and the mapping relationship is adjusted based on the real-time data of the user feedback to obtain the updated new version of the mapping relationship, and each version of the mapping relationship is retained in the database.

[0106] In this embodiment, the mapping relationship can be adjusted in time, which is more in line with the needs of actual application scenarios, and each version of the mapping relationship can be retained for easy traceability, which is conducive to efficiently and accurately analyzing the source and reason of the change of the mapping relationship.

[0107] In one exemplary embodiment, the coding result is a color coding result; and the mapping relationship between the preset coding result and the user intention is a mapping relationship between the preset color coding result and the user intention. As shown in Figure 6 The routing method based on the intention perception path further includes:

[0108] Step 602, collecting evaluation information of the user for the target user intention, and determining a color coding result that meets a preset confusion condition based on the evaluation information.

[0109] The evaluation information of the user for the target user intention can be evaluation feedback information of the target user intention corresponding to the user behavior data output by the system, for example, the evaluation information of the user for the target user intention can be evaluation feedback information for each target user intention, which can include correct identification of the intention or incorrect identification of the intention; in the case of incorrect identification of the intention, the evaluation feedback information can further include the correct intention feedback by the user; and the preset confusion condition can be a color coding result corresponding to a target number of user intentions. The system can obtain the evaluation information feedback by the user in the form of a user log, a feedback form, or the like.

[0110] Specifically, the system can output an evaluation request to the user when allocating computing power resources to the user, so that the system can obtain the evaluation information feedback of the user for the target user intention. If the number of times of incorrect identification of the target user intention exceeds a preset number threshold, the system can determine that the color coding result corresponding to the target user intention is a color coding result that meets the preset confusion condition.

[0111] At step 604, the mapping relationship is improved based on the color coding result satisfying the preset confusion condition to obtain an improved mapping relationship.

[0112] Specifically, the system can adjust the mapping relationship of the color coding result satisfying the preset confusion condition in the preset mapping relationship between the color coding result and the user intent based on the correct intent of the user feedback contained in the evaluation information for the error-identified intent. For example, the system can add a new corresponding relationship between a new color coding result and a new user intent in the mapping relationship, or adjust the color coding result and the user intent, and the like. Based on this, the system can obtain an improved mapping relationship.

[0113] In this embodiment, the color coding result that is misinterpreted and confused multiple times can be quickly determined and adjusted in time, improving the mapping accuracy of the mapping relationship and ensuring the accuracy of intent analysis.

[0114] In the following, a specific implementation process of the above-mentioned routing method based on the intent perception path is described in detail in combination with a specific embodiment:

[0115] The embodiment provides a more flexible and intelligent computing power routing solution that can simultaneously perceive network state and computing resources to achieve more efficient resource management and optimization. The patent proposes a computing power routing method and device based on an intent perception path, which guides the traffic of services requiring a specific intent using BGP intent perception paths, thereby improving the resource utilization and security of the computing power scheduling system and optimizing the performance of the computing power scheduling system.

[0116] As shown in Figure 7 , it is an intent perception computing power routing scheme framework applied in the embodiment, which includes a user, a network device, a computing power routing node, and a computing power resource pool. The network device and the computing power routing node communicate with each other through a network. The network device includes a user identity authentication module, a routing module, a computing power service routing encapsulation, and an intent analysis module. The computing power routing node includes a computing resource perception module, a routing decision module, a BGP extension module, and a computing power service routing identification module, which can better meet the needs of computing power networks in resource scheduling and supply-demand balance. Specifically, as shown in Figure 8 , it can be a specific structure diagram of the computing power routing node, which includes a computing resource perception module, a routing decision module, a BGP extension module, and a computing power service routing identification module. The resource scheduling is realized through the computing resource perception module, the routing decision is realized through the routing decision module, the BGP extension is realized through the BGP extension module, and the routing identification is realized through the computing power service routing identification module.

[0117] The intention analysis module is a key functional module of the intention perception computing power routing scheme framework, which can automatically analyze the high-level intention of the user. Specifically, by constructing a data model, the user's intention is converted into a specific network and computing power service request, and finally the routing is encapsulated and delivered to the next node. The intention analysis module can automatically analyze the high-level intention of the user and convert it into a specific computing power network demand, reducing manual intervention and improving the intelligent level of computing power scheduling.

[0118] In one example, the intention perception routing specific process can be as shown in Figure 9 The user is authenticated by the user identity authentication module, the user intention is analyzed by the intention analysis module, the routing request is processed by the computing power service routing encapsulation module, and the request is forwarded to the computing power routing node by the routing module.

[0119] The implementation process of effectively converting the user's intention into the routing demand of network traffic can include the following steps:

[0120] S1. User authentication and intention collection module; specifically, the identity is verified by the identity authentication module, and after the verification is passed, the system identifies and records the user's access to the computing power network resource demand and operation intention, for example, the user requests computing resources, hopes for low delay transmission of the network, or requires lower cost, etc.; for example, the user's identity can be confirmed through a user authentication service (such as OAuth, LDAP or SAML), and after the verification is confirmed to be passed, the user's access demand and operation behavior can be recorded during the session process, and these operation behavior data are stored through a log or event tracking system, i.e. user behavior data is obtained.

[0121] S2. Intention perception; specifically, the user's operation intention is analyzed by the intention analysis module (intention perception module) to convert into a specific network and computing power demand, for example, the user behavior data can be analyzed to construct a data model, and natural language processing (NLP) and machine learning (ML) techniques are used to automatically identify the user's high-level intention. After the module analyzes the high-level intention, a computing resource request matching the user's demand is generated;

[0122] Optionally, a multi-dimensional data model based on user demand characteristics is constructed for mapping and analyzing different intentions. Each dimension is constructed using a multi-dimensional data set (data cube) and is considered as an independent axis, each axis representing a type of data characteristic. Through such a data structure, data can be quickly queried and filtered in different dimensions. For example, a data cube can be constructed, where each dimension represents user demand, service quality, cost, resource type, etc., so that slicing or aggregation can be performed on any combination of dimensions. Multidimensional indexing (Multidimensional Indexing): To support fast access to data in different dimensions, multidimensional indexing (such as R-tree, KD-tree, Bitmap Index, etc.) is introduced to achieve efficient data retrieval in high dimensions, which is suitable for querying low-latency paths, low-cost paths, and other specific intentions.

[0123] Optionally, the intention can be extracted and classified from user behavior data through a machine learning or deep learning model (such as LSTM, BERT, etc.), and the demand is mapped to computing power and network resource requests through intention classification. In the model, the parsed intention is converted into a 32-bit color coding result, each color coding result corresponds to a different user intention (such as low latency corresponding to color 1, low cost corresponding to color 2), and is assigned a corresponding network identifier. The mapping relationship between the color coding result and the user intention can be updated, for example, a database or other data storage mechanism can be used to ensure that the mapping relationship can be automatically updated according to real-time data and user feedback; a version control mechanism is introduced in the mapping relationship, a new version is generated after each update, and historical records are preserved to allow backtracking to previous versions when needed, which helps to track the source and reason of changes; collect user behavior data and user feedback evaluation information when using the system, get the color coding result that meets the preset confusion condition, and then determine the mapping relationship that needs to be improved, and obtain user evaluation information based on user logs, feedback forms, etc. In addition, when the user's demand or intention changes, the system can quickly adjust the mapping relationship.

[0124] S3. BGP CACR (Color-Aware Computing Routing) mechanism; specifically, the system can match computing power service intentions with specific paths by extending the SAFI (Subsequent Address Family Identifier) in the BGP protocol. Each color-coded route request is transmitted to the computing power node according to the intention.

[0125] Optionally, two new SAFI types are defined in the BGP protocol, BGP CACR SAFI for network infrastructure path transmission, and VPN CACR SAFI for distinguishing different intent routes of customer networks. Each computing power routing node can store a node routing table, each routing table entry in the node routing table contains an IP prefix and a color code, and the router device selects and forwards the path according to the color identification, and forwards the user traffic to the next computing power routing node corresponding to the current computing power routing node, that is, the target candidate node. The computing power resources allocated by the intent-aware path generated by the above embodiment can meet the demand intent of the user. Correspondingly, the multi-path policy can be supported by the BGP extension module, and the traffic scheduling priority of different intents can be defined in combination with the color coding. The intent is routed to different paths through color, which realizes more accurate path selection, and the new mechanism can also be tested and simulated in advance in a preset small range to ensure that it can effectively operate in the existing infrastructure.

[0126] S4. Path selection and forwarding strategy; specifically, each router node selects a path according to the color identification configured by BGP CACR. The ingress PE or ASBR node guides the intent path with color to the computing power routing node, and ensures that the user request reaches the optimal path. For example, MPLS labels or SRv6 SIDs are used, and color coding is used to set a stack for the routing path, so that different intent paths are automatically parsed and the best path is selected in cross-domain transmission;

[0127] Optionally, each node verifies whether the path meets the intent (such as delay requirement) when forwarding, and automatically adjusts the path in the forwarding process through SR (Segment Routing) or Flex-Algo strategy; in the color verification process, Flex-Algo is used to select the optimal path according to the color identification of the user intent, and to adjust in real time when the path condition changes, for example, when the delay of a certain path exceeds the preset threshold, Flex-Algo can dynamically select other paths that meet the conditions, and Flex-Algo uses a weighted algorithm to calculate the cost value of the path:

[0128]

[0129] wherein the performance indicators related to the target user intent can include latency, bandwidth, and packet loss rate; P represents a path, which can also represent a node in the path, that is, a first candidate node; Cost represents a cost value, Delay represents a latency value on the first candidate node P; Bandwidth represents a bandwidth on the first candidate node P, and Loss represents a packet loss rate on the first candidate node P. w1 represents the weight of the latency, w2 represents the weight of the bandwidth, and w3 represents the weight of the packet loss rate.

[0130] Optionally, as shown in Figure 10 The computing power routing network can include multiple regions, for example, domain 1, domain 2 and domain 3; the correspondence between the color coding result in each region and the user intention can be different, the user intention of the user's service flow N1 received by the E1 interface can be low latency, and the user intention of the service flow N2 can be low latency and avoid some resources. When routing and forwarding between multiple domains, the color-to-intention mapping across the domain boundary is used to redefine the intention label of the cross-domain path, and the intention transmission between different network domains is ensured to be consistent. In this way, the service flow N1 can be distributed to the computing power resource C1 through the interface E2, and the service flow N2 can be distributed to the computing power resource C2.

[0131] S5. Service automatic steering mechanism; specifically, according to the color label generated by the intention analysis module, each entry node automatically steers the service flow to the color-aware path that meets the intention. At each forwarding hop, the system performs path label exchange to realize multi-level analysis and forwarding of labels and intentions. Combined with IGP Flex-Algo and BGP CACR path priority, automatic path selection of multiple intentions is realized. In the SR strategy, the path priority of different intentions is specified, and combined with the BGP CACR path selection module, more flexible path steering and load balancing is realized.

[0132] The intention-aware path-based routing provided by the embodiment can be used in a large-scale network, and the routing strategy is decomposed in different domains through flat and hierarchical design. Each domain realizes the intention transmission of cross-domain routing through color boundary identification, and the entry BR reduces the core resource consumption through self-hierarchical design of the next hop. For example, different color-to-intention mapping tables can be set through the hierarchical routing structure to ensure the intention consistency of cross-domain path selection. Figure 1 In addition, the path intention identification can be synchronized between different color domains through signaling to ensure that the path selection of each domain meets the user demand. That is, the service automatic steering mechanism can automatically steer the service flow to the path that meets the intention according to the color label generated by the intention analysis module. The IGP Flex-Algo and BGP CACR path priority are used to realize automatic path selection of multiple intentions. In a multi-domain environment, the routing strategy is decomposed through hierarchical design, and different color-to-intention mapping tables are set to ensure the intention consistency of cross-domain path selection. Figure 1 The support of the signaling protocol enables the synchronization of the path intention between different color domains, thereby improving the utilization efficiency of network resources and the quality of service.

[0133] Based on this, by introducing the color concept to distinguish different computing intentions or needs, the optimization of computing power routing selection is realized in combination with the BGP protocol. By integrating user identity authentication module, intention analysis module and computing power service routing encapsulation, the efficiency of resource scheduling and supply and demand balance of the computing power network is effectively improved. The intention analysis module can automatically analyze the user's high-level needs and convert them into specific computing power and network service requests, thereby reducing manual intervention and reducing the complexity of resource allocation. Through this automated process, the user's needs can be responded to more quickly and accurately, significantly improving the utilization of computing power resources.

[0134] The color coding result in the embodiment is a 32-bit numerical value associated with a specific user intention. Network devices can package and analyze different intentions of user operations. By implementing intention-aware routing, users can directly express their specific needs for computing power network resources after identity authentication. The system automatically collects and analyzes these needs and converts them into executable requests, reducing user participation costs in resource scheduling and improving overall experience. The system can intelligently process requests to ensure that network services can meet user needs in a timely manner.

[0135] In the embodiment, the BGP CACR (Color-Aware Computing Routing) mechanism is used to match user intentions with specific paths, achieving more accurate routing selection. Each routing request is assigned a color code corresponding to the user's intention, and the router can select the optimal path based on the color identifier. This intention-based routing configuration method allows the network to flexibly respond to the needs of different users while ensuring optimal transmission of network traffic, reducing latency and cost.

[0136] It should be understood that although each step in the flowchart involved in the above embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in the above embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately executed with other steps or steps or stages in other steps.

[0137] Based on the same inventive concept, the embodiments of the present application also provide an intention-aware path-based routing device for implementing the intention-aware path-based routing method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific definition in one or more intention-aware path-based routing device embodiments provided below can refer to the definition of the intention-aware path-based routing method in the above, which will not be repeated here.

[0138] In one exemplary embodiment, as shown in Figure 11 An intention-aware path-based routing device 1100 is provided, comprising:

[0139] A first acquisition module 1102 is configured to acquire user behavior data, wherein the user behavior data comprises access demand and / or resource operation behavior;

[0140] A first determination module 1104 is configured to process the user behavior data by using a multi-dimensional intention recognition model to obtain a plurality of first encoding results corresponding to the user behavior data;

[0141] A second determination module 1106 is configured to determine, for each node in the computing power routing network, an initial candidate node of a next node of the node, and based on the node routing table of the node and the first encoding results, screen among the initial candidate nodes to obtain a target candidate node;

[0142] A third determination module 1108 is configured to generate an intention-aware path based on each target candidate node, and determine a computing power resource corresponding to the intention-aware path in the computing power resource pool.

[0143] In one embodiment, the second determination module is specifically configured to:

[0144] Based on the topology structure of the computing power routing network, the nodes having a direct connection relationship with the node are determined as the initial candidate nodes of the next node of the node;

[0145] Based on the node routing table of the node, the second encoding results of the user intentions satisfied by each initial candidate node are determined among the initial candidate nodes;

[0146] Based on the second encoding results of the user intentions satisfied by each initial candidate node and the plurality of first encoding results corresponding to the user behavior data, the target candidate node is screened.

[0147] In one embodiment, the second determination module is specifically configured to:

[0148] Based on the plurality of first encoding results corresponding to the user behavior data, each initial candidate node is filtered based on a second encoding result satisfied by the initial candidate node, to obtain each first candidate node matching the first encoding result;

[0149] Based on a preset mapping relationship between the encoding result and the user intent, a target user intent corresponding to each first encoding result is determined, and a cost value of each first candidate node is calculated by a weight of the target user intent and an index value corresponding to each target user intent in each first candidate node.

[0150] Each first candidate node is filtered based on the cost value to obtain a target candidate node.

[0151] In one of the embodiments, the intent-aware path includes a plurality of paths; the third determining module is specifically configured to:

[0152] In the case where the computing resource pool includes a plurality of types of computing resources, computing resources corresponding to each destination network endpoint of each path are determined respectively;

[0153] Based on the priority of each type of computing resource, the computing resources corresponding to each destination network endpoint are filtered to obtain the computing resources corresponding to the intent-aware path.

[0154] In one of the embodiments, the device further includes:

[0155] The second obtaining module is configured to obtain user feedback data, update the mapping relationship based on the user feedback data to obtain an updated mapping relationship, and each mapping relationship is configured with version information.

[0156] In one of the embodiments, the encoding result is a color encoding result; the preset mapping relationship between the encoding result and the user intent is a preset mapping relationship between the color encoding result and the user intent; the device further includes:

[0157] The acquisition module is configured to acquire evaluation information of the target user intent by the user, and determine a color encoding result satisfying a preset confusion condition based on the evaluation information;

[0158] The improvement module is configured to improve the mapping relationship based on each color encoding result satisfying the preset confusion condition to obtain an improved mapping relationship.

[0159] Each module in the above routing device based on the intent-aware path can be realized by software, hardware, and a combination thereof, in whole or in part. Each module can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.

[0160] In an example embodiment, a computer device is provided, which can be a server, and an internal structure diagram thereof can be as shown in FIG. 1. Figure 12 The computer device includes a processor, a memory, an input / output interface, and a communication interface. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store intent data. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with terminals outside through a network connection. The computer program is executed by the processor to implement a routing method based on intent perception path.

[0161] Those skilled in the art can understand that Figure 12 The structure shown in FIG. 1 is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0162] In an example embodiment, a computer device is provided, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the embodiments of the present application.

[0163] In an embodiment, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the steps in the embodiments of the present application.

[0164] In an embodiment, a computer program product is provided, which includes a computer program. The computer program is executed by a processor to implement the steps in the embodiments of the present application.

[0165] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use, and processing of related data need to comply with relevant regulations.

[0166] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing relevant hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, the processes of the above-mentioned embodiment methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., and is not limited thereto. The processor involved in the embodiments provided in the present application can be a general processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., and is not limited thereto.

[0167] The technical features of the above embodiments can be combined arbitrarily. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combinations of the technical features do not exist contradictory, it should be considered as the scope of the present application.

[0168] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A method for routing based on intent-aware path, characterized in that, The method comprises: obtaining user behavior data, the user behavior data comprising access demand and / or resource operation behavior; processing the user behavior data through a multi-dimensional intention recognition model to obtain a plurality of first encoding results corresponding to the user behavior data; for each node in a computing power routing network, determining initial candidate nodes of a next node of the node, and based on a node routing table of the node and the first encoding results, screening among the initial candidate nodes to obtain target candidate nodes; based on the target candidate nodes, generating an intention-aware path and determining computing power resources corresponding to the intention-aware path in a computing power resource pool.

2. The method of claim 1, wherein, The determination of the initial candidate nodes of the next node of the node and the screening among the initial candidate nodes based on the node routing table of the node and the first encoding results to obtain the target candidate nodes comprise: based on the topology structure of the computing power routing network, determining nodes having a direct connection relationship with the node as the initial candidate nodes of the next node of the node; based on the node routing table of the node, determining second encoding results of user intentions respectively satisfied by the initial candidate nodes among the initial candidate nodes; based on the second encoding results of the user intentions respectively satisfied by the initial candidate nodes and the plurality of first encoding results corresponding to the user behavior data, screening to obtain the target candidate nodes.

3. The method of claim 2, wherein, The screening based on the second encoding results of the user intentions respectively satisfied by the initial candidate nodes and the plurality of first encoding results corresponding to the user behavior data to obtain the target candidate nodes comprise: based on the plurality of first encoding results corresponding to the user behavior data, screening among the initial candidate nodes based on the second encoding results respectively satisfied by the initial candidate nodes to obtain first candidate nodes matching the first encoding results; based on a preset mapping relationship between encoding results and user intentions, determining target user intentions respectively corresponding to the first encoding results, and calculating target user intentions through a weight of the target user intentions and an index value corresponding to each target user intention in the first candidate nodes to obtain a cost value of each first candidate node; based on the cost values of the first candidate nodes, screening to obtain the target candidate nodes.

4. The method of claim 1, wherein, The intention-aware path comprises a plurality of paths. The determination of the computing power resources corresponding to the intention-aware path in the computing power resource pool comprises: in a computing power resource pool containing a plurality of types of computing power resources, respectively determining computing power resources corresponding to destination network end points of each path; based on priorities of each type of computing power resource, screening the computing power resources corresponding to each destination network end point to obtain the computing power resources corresponding to the intention-aware path.

5. The method of claim 3, wherein, The method further comprises: obtaining user feedback data, updating the mapping relationship based on the user feedback data to obtain an updated mapping relationship, and each mapping relationship is configured with version information.

6. The method of claim 3, wherein, The encoding result is a color encoding result; and the mapping relationship between the preset encoding result and the user intention is a mapping relationship between a preset color encoding result and a user intention. The method further includes: collecting evaluation information of the user on the target user intention, and determining a color encoding result satisfying a preset confusion condition based on the evaluation information; improving the mapping relationship based on each color encoding result satisfying the preset confusion condition, to obtain an improved mapping relationship.

7. An intent-aware path-based routing apparatus, comprising: The apparatus includes: a first obtaining module configured to obtain user behavior data, the user behavior data including access demand and / or resource operation behavior; a first determining module configured to process the user behavior data by using a multi-dimensional intention recognition model to obtain a plurality of first encoding results corresponding to the user behavior data; a second determining module configured to determine, for each node in a computing power routing network, an initial candidate node of a next node of the node, and filter among the initial candidate nodes based on a node routing table of the node and the first encoding results to obtain a target candidate node; a third determining module configured to generate an intention perception path based on each target candidate node, and determine computing power resources corresponding to the intention perception path in a computing power resource pool.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor, when executing the computer program, implements the steps of the method of any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the method of any one of claims 1 to 6.

Images