CN114866460B

CN114866460B - Path planning method based on artificial intelligence and related equipment

Info

Publication number: CN114866460B
Application number: CN202210459440.8A
Authority: CN
Inventors: 温业逵; 周健
Original assignee: Jitter Technology Shenzhen Co ltd
Current assignee: Jitter Technology Shenzhen Co ltd
Priority date: 2022-04-27
Filing date: 2022-04-27
Publication date: 2024-06-04
Anticipated expiration: 2042-04-27
Also published as: CN114866460A

Abstract

The application provides a path planning method, a device, electronic equipment and a storage medium based on artificial intelligence, wherein the path planning method based on the artificial intelligence comprises the following steps: constructing a server cluster, wherein the server cluster comprises a plurality of server nodes; calculating the receiving cost of each server node; calculating the sending cost of each server node; calculating the communication priority of the server node according to the receiving cost and the sending cost; combining the server nodes to construct a path set, wherein the path set comprises a plurality of communication paths, and calculating a priority index of each communication path according to the communication priority; and screening target paths and alternative paths from the path set according to the priority index to complete path planning. According to the method, the target path and the alternative path can be screened according to the priority of the server nodes and the number of the server nodes in the communication path, so that the cost performance and fault tolerance of path planning can be improved.

Description

Path planning method based on artificial intelligence and related equipment

Technical Field

The present application relates to the field of artificial intelligence technologies, and in particular, to a path planning method, apparatus, electronic device, and storage medium based on artificial intelligence.

Background

With the development of information technology, the demands of various industries for stable and rapid data transmission are increasing, and enterprises generally need to utilize multiple server nodes in a server cluster to perform data transfer transmission, so that the advantages and disadvantages of a data transmission path directly affect the efficiency of data transmission.

At present, an enterprise usually plans a data transmission path with smaller communication cost from a server cluster to serve as a target path for data transmission, and the method does not find an alternative path with higher opposite direction to the target path from the server cluster, so that the fault tolerance of the data transmission process is difficult to ensure, and the method does not consider the cost of the target path in combination with the number of nodes in the target path, so that the cost performance of the target path is possibly lower.

Disclosure of Invention

In view of the foregoing, it is necessary to provide a path planning method based on artificial intelligence and related devices, so as to solve the technical problem of how to improve the cost performance and fault tolerance of path planning, where the related devices include a path planning device based on artificial intelligence, an electronic device and a storage medium.

The embodiment of the application provides a path planning method based on artificial intelligence, which comprises the following steps:

Constructing a server cluster, wherein the server cluster comprises a plurality of server nodes, each server node is used for transmitting data, and the plurality of server nodes comprise a sending node and a receiving node;

Calculating the receiving cost of each server node, wherein the receiving cost is used for representing the difficulty of the server node to receive the data sent by the sending node;

Calculating the sending cost of each server node, wherein the sending cost is used for representing the difficulty of the server node to send data to the receiving node;

Calculating the communication priority of the server node according to the receiving cost and the sending cost, wherein the communication priority is used for representing the degree of priority calling of the server node when transmitting data;

Combining the server nodes to construct a path set, wherein the path set comprises a plurality of communication paths, each communication path comprises a plurality of server nodes, and calculating a priority index of each communication path according to the communication priority;

and screening target paths and alternative paths from the path set according to the priority index to complete path planning.

According to the path planning method based on artificial intelligence, a plurality of server nodes are obtained by constructing a server cluster, the plurality of server nodes comprise a sending node and a last receiving node, the receiving cost and the sending cost of each server node are further calculated, the communication priority of the server nodes is calculated according to the receiving cost and the sending cost, the server nodes are further combined randomly to obtain a plurality of communication paths, the priority index of the communication paths is calculated based on the communication priority, and finally the target paths and the alternative paths are selected according to the priority index and the number of nodes in the communication paths, so that the cost performance and the accuracy of path planning can be improved, and the fault tolerance of the path planning can be improved.

In some embodiments, the calculating the cost of receipt for each server node comprises:

Querying a physical distance between the server node and the sending node to calculate a first reception cost;

Inquiring the hardware information of each server node to calculate the performance index of the server node, and taking the reciprocal of the performance index as a second receiving cost, wherein the hardware information at least comprises the disk writing speed, the cache frequency, the core number and the frequency of the central processing unit;

and calculating the receiving cost of the server node according to the first receiving cost and the second receiving cost.

In this way, the first receiving cost of the server node is calculated by inquiring the physical distance between the server node and the target node, and the second receiving cost of each server node is calculated by inquiring the hardware information of each server node, so that the receiving cost of the server node is calculated according to the first receiving cost and the second receiving cost, and data support is provided for the follow-up calculation of the priority of the server node and the planning of the communication path, thereby improving the rationality of the communication path planning.

In some embodiments, the calculating the transmission cost for each server node includes:

inquiring the maximum node number of the server node to jump to the receiving node to be used as the jumping node number;

normalizing the jump node number to obtain a normalized jump node number;

Inputting the normalized number of jump nodes into a custom mapping model to obtain a mapping result and taking the mapping result as the sending cost of the server node, wherein the higher the sending cost is, the harder the receiving node receives the data sent by the server node, and the custom mapping model satisfies the following relation:

Wherein x represents the server node; h (x) represents a transmission cost of the server node represented by x, and the higher the transmission cost is, the higher the cost is when data is transmitted from the server node to the receiving node; n ^x represents the normalized number of hops nodes for the server node x.

Thus, the maximum node number required by the server node to jump to the receiving node is queried to obtain the corresponding jump number of the server node, and the jump number is normalized to obtain the normalized jump number to be used as the sending cost of the server node, and the higher the sending cost is, the more difficult the server node is to send data to the receiving node.

In some embodiments, said calculating the communication priority of the server node from the reception cost and the transmission cost comprises:

inquiring the physical distance between the server node and the sending node to be used as a receiving distance, and calculating a receiving weight according to the receiving distance;

Inquiring the physical distance between the server node and the receiving node to be used as a transmission distance, and calculating a transmission weight according to the transmission distance;

and calculating the communication priority of the server node based on the receiving weight, the transmitting weight, the receiving cost and the transmitting cost.

In this way, the receiving weight is calculated by inquiring the physical distance between the server node and the sending node, and the sending weight is calculated by inquiring the physical distance between the server node and the receiving node, and the communication priority of the server node is further calculated based on the receiving weight, the sending weight, the receiving cost and the sending cost, so that data support is provided for subsequent path planning, and the accuracy of path planning can be improved.

In some embodiments, the method of calculating the communication priority satisfies the following relationship:

Wherein x represents the server node; w ₁ represents the reception weight; g (x) represents the reception cost; w ₁ represents the transmission weight; h (x) represents the transmission cost; f (x) represents a communication priority of the server node represented by x, the higher the value of the communication priority, the more should the server node be invoked to transmit data.

Therefore, the importance of the receiving cost and the sending cost is adjusted through the receiving weight and the sending weight, the importance of the receiving cost and the sending cost of the server node can be dynamically adjusted in the path planning process, the data can reach the receiving node quickly, and therefore the path planning efficiency is improved.

In some embodiments, said calculating a priority indicator for each communication path as a function of said communication priority comprises:

Randomly combining the server nodes to construct a path set, the path set comprising a plurality of communication paths, each communication path comprising a plurality of server nodes;

calculating the sum of all the communication priorities of the server nodes in each communication path as the communication priority of each communication path;

Counting the number of server nodes in the communication path, and taking the reciprocal of the number of the server nodes as the cost priority of the communication path, wherein the higher the cost priority is, the more the communication path is applied to transmit data;

Respectively carrying out normalization processing on the communication priority of the communication path and the cost priority to obtain a normalized communication priority and a normalized cost priority;

And calculating the sum of the normalized communication priority and the normalized cost priority of each communication path to serve as a priority index of the corresponding path.

In this way, a plurality of communication paths are obtained by randomly combining the server nodes, the number of the server nodes in the communication paths is counted to obtain the cost priority of the communication paths, normalization processing is carried out on the communication priority and the cost priority to obtain the normalized communication priority and the normalized cost priority respectively, finally, the priority index of the communication paths is obtained by calculating the sum of the normalized communication priority and the normalized cost priority, and data support is provided for the subsequent path screening step, so that the accuracy of path planning is improved.

In some embodiments, the screening target paths and alternative paths from the set of paths to complete path planning in accordance with the priority indicator comprises:

Taking the communication path with the highest priority index as a target path, and taking the rest communication paths as alternative paths;

Calculating an intersection of the alternative path and the target path, and calculating a suboptimal rate of the alternative path according to the intersection length and a priority index of the alternative path;

And when a certain server node in the target path fails, enabling the alternative paths in sequence according to the sequence from the high suboptimal rate to the low suboptimal rate.

In this way, the target paths are screened out from the path set through the priority index, the rest paths are used as alternative paths, the intersection of the alternative paths and the target paths is calculated, the suboptimal rate of each alternative path is calculated according to the intersection length and the priority index, when the target paths fail, the alternative paths can be started in sequence according to the sequence from the suboptimal rate to the descending, data guidance is provided for path planning, and the fault tolerance of data transmission can be improved.

The embodiment of the application also provides a path planning device based on artificial intelligence, which comprises:

a building unit, configured to build a server cluster, where the server cluster includes a plurality of server nodes, each server node is configured to transmit data, and one of the plurality of server nodes includes a sending node and a receiving node;

the first calculation unit is used for calculating the receiving cost of each server node, and the receiving cost is used for representing the difficulty of the server node in receiving the data sent by the sending node;

The second calculation unit is used for calculating the sending cost of each server node, and the sending cost is used for representing the difficulty of the server node to send data to the receiving node;

a third calculation unit, configured to calculate a communication priority of the server node according to the receiving cost and the sending cost, where the communication priority is used to characterize a degree to which the server node is preferentially invoked when transmitting data;

A combining unit configured to combine the server nodes to construct a path set, where the path set includes a plurality of communication paths, each communication path includes a plurality of server nodes, and calculate a priority index of each communication path according to the communication priority;

And the screening unit is used for screening the target path and the alternative path from the path set according to the priority index so as to complete path planning.

The embodiment of the application also provides electronic equipment, which comprises:

A memory storing computer readable instructions; and

And a processor executing computer readable instructions stored in the memory to implement the artificial intelligence based path planning method.

Embodiments of the present application also provide a computer-readable storage medium having stored therein computer-readable instructions that are executed by a processor in an electronic device to implement the artificial intelligence based path planning method.

Drawings

FIG. 1 is a flow chart of a preferred embodiment of an artificial intelligence based path planning method in accordance with the present application.

Fig. 2 is a functional block diagram of a preferred embodiment of an artificial intelligence based path planning apparatus in accordance with the present application.

Fig. 3 is a schematic structural diagram of an electronic device according to a preferred embodiment of the path planning method based on artificial intelligence according to the present application.

Fig. 4 is a schematic structural diagram of a server cluster according to the present application.

Fig. 5 is a schematic diagram of a maximum number of hops for a server node to jump to a receiving node using shell scripts in accordance with the present application.

Fig. 6 is a schematic diagram of the structure of an evaluation matrix according to the present application.

Detailed Description

The application will be described in detail below with reference to the drawings and the specific embodiments thereof in order to more clearly understand the objects, features and advantages of the application. It should be noted that, without conflict, embodiments of the present application and features in the embodiments may be combined with each other. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, the described embodiments are merely some, rather than all, embodiments of the present application.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.

The embodiment of the application provides a path planning method based on artificial intelligence, which can be applied to one or more electronic devices, wherein the electronic devices are devices capable of automatically performing numerical calculation and/or information processing according to preset or stored instructions, and the hardware comprises, but is not limited to, a microprocessor, an application specific integrated circuit (ApplicationSpecificIntegratedCircuit, ASIC), a programmable gate array (Field-ProgrammableGateArray, FPGA), a digital processor (DigitalSignalProcessor, DSP), an embedded device and the like.

The electronic device may be any electronic product that can interact with a user, such as a personal computer, tablet, smart phone, personal digital assistant (PersonalDigitalAssistant, PDA), gaming machine, interactive web television (IntemetProtocolTelevision, IPTV), smart wearable device, etc.

The electronic device may also include a network device and/or a user device. Wherein the network device includes, but is not limited to, a single network server, a server group of multiple network servers, or a cloud of a large number of hosts or network servers based on cloud computing (CloudComputing).

The network in which the electronic device is located includes, but is not limited to, the internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VirtualPrivateNetwork, VPN), and the like.

FIG. 1 is a flow chart of a preferred embodiment of the artificial intelligence based path planning method of the present application. The order of the steps in the flowchart may be changed and some steps may be omitted according to various needs.

S10, constructing a server cluster, wherein the server cluster comprises a plurality of server nodes, each server node is used for transmitting data, and the plurality of server nodes comprise a sending node and a receiving node.

In this optional embodiment, the server cluster is composed of a plurality of server nodes, and each server node is used for calculating and transmitting data, where the server nodes may be devices with a data transmission function, such as a computer or a router, and the server cluster may use a plurality of computers to perform parallel calculation so as to obtain a higher calculation speed, or use a plurality of computers to make a backup, so as to ensure that the server cluster can operate normally when any one of the server nodes in the cluster fails.

In this alternative embodiment, the communication mode between each server node is optical fiber communication, and the longer the length of the optical fiber, the longer the time required for transmitting data between two server nodes.

In this alternative embodiment, the server cluster includes a sending node and a receiving node, where the sending node is configured to send data to the receiving node, and the receiving node is configured to receive the data transmitted by the sending node.

In this alternative embodiment, the function of the plurality of server nodes is to transmit data sent by the sending node to the receiving node.

Exemplary, fig. 4 is a schematic structural diagram of a server cluster according to the present embodiment.

Therefore, the data is transmitted through the server cluster, so that the reliability of data transmission is ensured, and the timeliness of the data transmission can be improved.

S11, calculating the receiving cost of each server node, wherein the receiving cost is used for representing the difficulty of the server node to receive the data sent by the sending node.

In an alternative embodiment, calculating the cost of receipt for each server node includes:

In this alternative embodiment, the physical distance refers to the total length of the communication optical fiber between two server nodes, and the further the physical distance is, the longer the time for the server node to receive data is, so the physical distance between the server node and the sending node can be queried to calculate the first receiving cost of the server node, and in this scheme, the physical distance between the server node and the target node can be recorded as Dis.

In this optional embodiment, the physical distance may be normalized by using a maximizing algorithm to obtain a normalized physical distance as a first receiving cost, where the first receiving cost may be recorded as C1, and a calculation manner of the first receiving cost C1 satisfies the following relational expression:

Wherein, C1 represents the first reception cost, and Dis ^max represents the maximum value in the normalized physical distance; the DIS represents the normalized physical distance.

For example, when the optical fiber distance between the server node a and the target node is 10 km and the maximum value of the physical distance is 100 km, the first receiving cost of the server node B is calculated in the following manner:

The reception cost of the server node a takes a value of 0.1.

In this alternative embodiment, the hardware information of the server node may be queried to calculate the performance index of the server node, and the inverse of the performance index is taken as the second receiving cost. The hardware information at least comprises the core number and frequency of a central processing unit of the server node, the cache frequency and the disk writing speed, wherein the higher the core number and the frequency of the central processing unit, the faster the data processing speed of the server node is, the higher the cache frequency is, the faster the data processing speed of the server node is, and the higher the disk writing speed is, the faster the data receiving speed of the server node is.

In this optional embodiment, the core number and the frequency, the cache frequency, and the disk writing speed of the central processing unit may be normalized according to a maximization algorithm to obtain normalized hardware information, where the core number of the central processing unit is taken as an example, and the maximization algorithm satisfies the following relational expression:

Wherein Xn ⁱ represents the core number of the central processing unit normalized by the ith server node; x ⁱ represents the number of cores of the central processing unit of the ith server; x ^max represents the maximum number of central processing unit cores for all server nodes.

For example, when the number of cores of the central processing unit of the 1 st server node is 4 and the maximum number of cores of the central processing unit is 32, the calculation manner of the core number of the central processing unit normalized by the 1 st server node is:

the normalized core number of the central processing unit of the 1 st server node is 0.125.

In this optional embodiment, the sum of the normalized hardware information may be calculated to serve as a performance index of the server node, and the inverse of the performance index is taken as a second receiving cost of the server node, where the faster the server receives and processes data, the smaller the second receiving cost of the server node, in this scheme, the second receiving cost may be denoted as C2, and the calculating manner of the second receiving cost C2 satisfies the following relational expression:

wherein C2 represents the second reception cost, a higher value of the C2 indicating that the server node is more difficult to receive data from the transmitting node; xn represents the core number of the normalized central processing unit; yn represents the frequency of the normalized central processing unit; zn represents the normalized cache frequency; wn represents the normalized disk write speed.

For example, if the core number of the normalized central processing unit of a certain server node is 0.125, the core frequency of the normalized central processing unit is 0.5, the normalized cache frequency is 0.8, and the normalized disk writing speed is 1, the calculation manner of the second receiving cost of the server node is:

The second reception cost of the server node is 0.41.

In this alternative embodiment, the receiving cost of each server node may be calculated based on the first receiving cost and the second receiving cost, where the higher the receiving cost is, the more difficult the server node receives data from the sending node, and in this scheme, the receiving cost may be recorded as g (x), where x represents the server node x, and the receiving cost g (x) is calculated by:

Wherein x represents the server node; g (x) represents the receiving cost of the server node represented by x, wherein the higher the receiving cost is, the higher the cost is when the server node receives data from the transmitting node; c1 ^x represents a first reception cost of the server node x; c2 ^x represents a second reception cost of the server node x; e represents a natural constant.

For example, when the first receiving cost of the server node x is 10 and the second receiving cost is 0.41, the receiving cost of the server node is calculated in the following manner:

The value of the reception cost of the server node is 0.964. In this way, the first receiving cost of the server node is calculated by inquiring the physical distance between the server node and the target node, and the second receiving cost of each server node is calculated by inquiring the hardware information of each server node, so that the receiving cost of the server node is calculated according to the first receiving cost and the second receiving cost, and data support is provided for the follow-up calculation of the priority of the server node and the planning of the communication path, thereby improving the rationality of the communication path planning.

S12, calculating the sending cost of each server node, wherein the sending cost is used for representing the difficulty of sending data to the receiving node by the server node.

In an alternative embodiment, said calculating the transmission cost of each server node includes:

inquiring the maximum node number of the server node to the receiving node as the jump node number, wherein the higher the jump node number is, the more difficult the receiving node receives the data sent by the server node;

normalizing the jump node number to obtain a normalized jump node number;

And inputting the normalized jump node number into a preset mapping model to obtain a mapping result and serve as the sending cost of the server node, wherein the higher the sending cost is, the harder the receiving node receives the data sent by the server node.

In this alternative embodiment, the maximum number of nodes that the server node jumps to the receiving node may be queried according to a preset program to serve as the number of jump nodes, where the higher the number of jump nodes, the higher the sending cost of the server node.

The preset program may be a shell script, and the shell script may be in the form of a "tracert node ip", where tracert is a built-in function of the sehll script, and the function of tracert is to query the number of hops required for the server node to jump to the target node, and node ip represents the ip address of the receiving node, and fig. 5 is a schematic diagram of querying the maximum number of hops for the server node to jump to the receiving node by using the shell script.

In this alternative embodiment, the number of hops may be normalized to obtain a normalized number of hops, and, for example, when the number of hops of a certain server node is 90 and the number of maximum hops is 100, the calculation manner of the number of normalized hops of the server is:

in this optional embodiment, the number of normalized jump nodes may be input into a preset mapping model to obtain a mapping result and be used as a transmission cost of the server node, where in this scheme, the transmission cost may be noted as h (x), where x represents a certain server node, and a calculation manner of the transmission cost h (x) satisfies the following relational expression:

For example, when the number of the normalized jump nodes is 0.9, the transmission cost h (x) of the server node x is calculated in the following manner:

the transmission cost of the server node takes a value of 0.978.

And S13, calculating the communication priority of the server node according to the receiving cost and the sending cost, wherein the communication priority is used for representing the degree of priority calling of the server node when the server node transmits data.

In an alternative embodiment, calculating the communication priority of the server node from the reception cost and the transmission cost includes:

In this optional embodiment, the physical distance between the server node and the sending node may be queried to obtain a receiving distance, and the receiving distance may be normalized according to the maximizing algorithm to obtain a normalized receiving distance, where in this scheme, the normalized receiving distance is recorded as Dis1, and further, a receiving weight w ₁ may be calculated according to the normalized receiving distance, where a calculating manner of the receiving weight is:

w₁＝1+Dis1

Wherein w ₁ represents a receiving weight, which is used for adjusting importance of a receiving cost in a path selection process, and the higher the value of the receiving weight is, the higher the influence degree of the receiving cost on the communication priority of the server node is; dis1 represents the normalized receiving distance.

For example, when the normalized receiving distance between the server node and the transmitting node is 0.1, the receiving weight of the server node is calculated in the following manner:

w₁＝1+0.1＝1.1

the value of the receiving weight of the server node is 1.1.

In this optional embodiment, the physical distance between the server node and the receiving node may be queried as a transmission distance, and normalization processing is performed on the transmission distance according to the maximizing algorithm to obtain a normalized transmission distance, where the normalized transmission distance is recorded as Dis2, and the transmission weight w ₂ may be further calculated according to the normalized transmission distance, where the calculation method of the transmission weight satisfies the following relational expression:

w₂＝1+Dis2

Wherein w ₂ represents a transmission weight, which is used for adjusting the importance of the transmission cost in the path selection process, and the higher the value of the transmission weight is, the higher the influence degree of the transmission cost on the communication priority of the server node is; the Dis2 represents the normalized transmission distance.

For example, when Dis2 is 0.5, the transmission weight of the server node is calculated in the following manner:

w₂＝1+0.5＝1.5

The transmission weight of the server node takes a value of 1.5.

In this alternative embodiment, the communication priority of the server node may be calculated based on the weight, the receiving cost and the sending cost, where a specific calculation manner of the communication priority satisfies the following relation:

Wherein x represents the server node; f (x) represents the communication priority of the server node represented by x; w ₁ represents the reception weight; g (x) represents the reception cost; w ₁ represents the transmission weight; h (x) represents the transmission cost.

For example, when a certain server node has a receiving weight of 11, a receiving cost of 0.964, a transmitting weight of 11, and a transmitting cost of 0.978, the communication priority corresponding to the server node is calculated by:

the corresponding communication priority of the server has a value of 2.67.

In another alternative embodiment, the communication priority of the server node may be calculated according to an a ^* algorithm, where the a ^* algorithm is a direct search method in a static road network that is more efficient in solving the shortest path. In this alternative embodiment, the reciprocal of the receiving cost may be used as a cost value in the a ^* algorithm, and the reciprocal of the sending cost may be used as a heuristic value in the a ^* algorithm, and the communication priority of the server node may be further calculated according to the cost value and the heuristic value, where the calculation manner of the communication priority satisfies the following relation:

wherein x represents the server node; f (x) represents a communication priority of the server node x; g (x) represents the cost of reception of the server node x; h (x) represents the transmission cost of the server node x.

For example, when the cost of receiving the server node x is 0.964 and the cost of sending the server node x is 0.978, the communication priority f (x) of the server node x is calculated in the following manner:

the communication priority of the server node x has a value of 2.05.

S14, combining the server nodes to construct a path set, wherein the path set comprises a plurality of communication paths, each communication path comprises a plurality of server nodes, and calculating a priority index of each communication path according to the communication priority;

In an alternative embodiment, said calculating the priority index of each communication path according to the communication priority comprises:

The sum of the communication priorities of all the server nodes in each communication path is calculated as the communication priority of each communication path.

In this alternative embodiment, the server nodes may be randomly combined to construct a path set, where the path set includes a plurality of communication paths, and each communication path includes a plurality of server nodes, and the function of the paths is to transmit data sent by the sending node to the receiving node through the server nodes.

In this alternative embodiment, the sum of the communication priorities of all the server nodes in the communication path may be calculated as the communication priority of the communication path, and the inverse of the number of server nodes in the communication path may be taken as the cost priority, where the higher the cost priority, the more should be selected as the target path.

In this alternative embodiment, the communication priority and the cost priority may be normalized according to a preset normalization algorithm to obtain a normalized communication priority and cost priority, where the preset normalization algorithm may be a maximization algorithm, and the maximum minimization algorithm satisfies the following relation:

Wherein T represents the normalized communication priority or normalized cost priority; i represents the class of priority and the value of i is { communication, path }; x represents the communication priority or cost priority of a certain path; Representing the maximum in communication priority or the maximum in cost priority.

For example, when the communication priority of a certain path has a value of 10 and the maximum value of the communication priorities is 100, the normalized communication priority corresponding to the path is calculated by:

The normalized communication priority corresponding to the path has a value of 0.1.

In this alternative embodiment, the sum of the normalized communication priority and the normalized cost priority of each path may be used as the priority index corresponding to each path, and the greater the priority index, the more the path should be used as the preferred communication scheme.

In this optional embodiment, the priority index is calculated in the following manner:

T＝T^{Communication system}+T^Path

Wherein T represents the priority index, the greater the priority index, the more the path should be treated as a preferred communication scheme; t ^{Communication system} represents a normalized communication priority index corresponding to the path; t ^Path represents the normalized cost priority index for that path.

For example, when the normalized communication priority corresponding to a certain path is 0.1 and the normalized cost priority corresponding to the certain path is 0.1, the calculation manner of the priority index corresponding to the path is:

T＝0.1+0.1＝0.2

The priority index corresponding to the path is 0.2.

And S15, screening target paths and alternative paths from the path set according to the priority index to complete path planning.

In an alternative embodiment, the screening the target path and the alternative path from the path set according to the priority index includes:

calculating the intersection of the alternative path and the target path, and calculating the suboptimal rate of the alternative path according to the intersection length and the priority index of the communication path;

In an alternative embodiment, the communication path with the highest priority index may be taken as the target path, and the rest of the communication paths may be taken as the alternative paths.

In another alternative embodiment, a dynamic programming algorithm may be utilized to screen the target path from the set of paths. In this alternative embodiment, the specific implementation steps of the dynamic programming algorithm are as follows:

a1: marking each server node by using a natural number starting from 1, wherein, for example, if the server cluster comprises 4 server nodes, the marks of the server nodes are respectively 1,2,3 and 4, and a marking sequence is constructed according to the order of the marks of the server nodes from small to large, and for example, if the marks of the server nodes are respectively 1,2,3 and 4, the marking sequence is [1,2,3 and 4];

a2: constructing an evaluation matrix according to the communication priority of the marking sequence and the server node, wherein the row names of the evaluation matrix from top to bottom are each element in the marking sequence, the column names of the evaluation matrix from left to right are each element in the marking sequence, the value of each element in the evaluation matrix is the server node corresponding to the name of the column in which the element is located, and if the column name of one element in the evaluation matrix is 2, the value of the element is the communication priority corresponding to the server node marked as 2;

A3: traversing the elements of each column in the row from the first row of the evaluation matrix in the order from left to right, taking the column with the maximum value in the elements of the row as a corresponding target node of the row, and setting the values of all the elements in the column with the maximum value as minus infinity;

a4: and sequentially arranging target nodes corresponding to each row in the evaluation matrix according to the sequence from top to bottom to obtain the target path.

In this alternative embodiment, a schematic structure of the evaluation matrix is shown in fig. 6.

In an alternative embodiment, the intersection of the alternate path with the target path may be calculated and the suboptimal rate of the alternate path may be calculated based on the intersection length and the priority indicator of the communication path.

In this alternative embodiment, the target path may be noted as P ^R, and the target path P ^R may be characterized as a set, i.e., theWhere n represents the number of server nodes in the target path,/>Representing a first server node in the target path.

In this alternative embodiment, the intersection of each of the remaining paths with the set may be determined according to a preset program, where the preset program may be a Python program, and may be in a form of "print (len (P ^R.intersection(P^e))"), where P ^R represents the target path, P ^e represents the e candidate path, intersection represents a function of the Python language that finds the intersection, and the result output by the Python program is the length of the intersection, where the longer the length of the intersection indicates that the more nodes in the remaining paths share nodes with the target path, and the higher the probability of failure of the alternative path with the longer intersection if a problem occurs in the target path.

In this optional embodiment, the length of the intersection may be normalized according to the maximizing algorithm to obtain a normalized intersection length, where the maximizing method is calculated in the following manner:

Wherein L ^k represents the normalized intersection length of the kth alternative path; k represents an index of the alternative path; l ^max represents the maximum value of the length of the intersection.

For example, when the intersection length of the 1 st alternative path and the target path is 10 and the maximum value of the intersection length is 100, the normalized intersection length of the first alternative path is calculated by:

the normalized intersection length of the 1 st alternative path is 0.1.

In this optional embodiment, the suboptimal rate of the alternative path may be calculated according to the intersection length and the priority index, where the calculating method of the suboptimal rate is:

Wherein S ^k represents a suboptimal rate of a kth alternative path, and a higher suboptimal rate indicates that the alternative path should be selected for communication when the target path fails; l ^k represents the normalized intersection length of the kth alternative path with the target path; t ^k represents the priority index of the kth alternative path.

For example, when the normalized intersection length of the 1 st alternative path is 0.1 and the corresponding priority index is 1, the suboptimal rate of the 1 st alternative path is calculated in the following manner:

The value of the suboptimal rate of the 1 st alternative path is 11.

In this optional embodiment, when a certain server node in the target path fails, the alternative paths may be sequentially started to perform data transmission according to the order of the suboptimal rate from high to low.

Fig. 2 is a functional block diagram of a preferred embodiment of an artificial intelligence based path planning apparatus according to an embodiment of the present application. The artificial intelligence based path planning apparatus 11 includes a construction unit 110, a first calculation unit 111, a second calculation unit 112, a third calculation unit 113, a combination unit 114, and a screening unit 115. The module/unit referred to in the present application refers to a series of computer program segments capable of being executed by the processor 13 and of performing a fixed function, which are stored in the memory 12. In the present embodiment, the functions of the respective modules/units will be described in detail in the following embodiments.

In an alternative embodiment, the building unit 110 is configured to build a server cluster, where the server cluster includes a plurality of server nodes, each server node is configured to transmit data, and one of the plurality of server nodes includes a sending node and a receiving node.

In an alternative embodiment, the first calculating unit 111 is configured to calculate a receiving cost of each server node, where the receiving cost is used to characterize a difficulty of the server node to receive the data sent by the sending node.

The reception cost of the server node a takes a value of 0.1.

The second reception cost of the server node is 0.41.

The value of the reception cost of the server node is 0.964.

In an alternative embodiment, the second calculating unit 112 is configured to calculate a transmission cost of each server node, where the transmission cost is used to characterize a difficulty of the server node transmitting data to the receiving node.

normalizing the jump node number to obtain a normalized jump node number;

the transmission cost of the server node takes a value of 0.978.

In an alternative embodiment, the third calculating unit 113 is configured to calculate a communication priority of the server node according to the receiving cost and the sending cost, where the communication priority is used to characterize a degree to which the server node is preferentially invoked when transmitting data.

w₁＝1+Dis1

w₁＝1+0.1＝1.1

the value of the receiving weight of the server node is 1.1.

w₂＝1+Dis2

w₂＝1+0.5＝1.5

The transmission weight of the server node takes a value of 1.5.

the corresponding communication priority of the server has a value of 2.67.

the communication priority of the server node x has a value of 2.05.

In an alternative embodiment, the combining unit 114 is configured to combine the server nodes to construct a path set, where the path set includes a plurality of communication paths, each communication path includes a plurality of server nodes, and calculate the priority index of each communication path according to the communication priority.

T＝T^{Communication system}+T^Path

T＝0.1+0.1＝0.2

The priority index corresponding to the path is 0.2.

In an alternative embodiment, the screening unit 115 is configured to screen the target path and the alternative path from the path set according to the priority index to complete path planning.

the normalized intersection length of the 1 st alternative path is 0.1.

The value of the suboptimal rate of the 1 st alternative path is 11.

Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device 1 comprises a memory 12 and a processor 13. The memory 12 is used to store computer readable instructions and the processor 13 is used to execute the computer readable instructions stored in the memory to implement the artificial intelligence based path planning method of any of the embodiments described above.

In an alternative embodiment, the electronic device 1 further comprises a bus, a computer program stored in the memory 12 and executable on the processor 13, such as an artificial intelligence based path planning program.

Fig. 3 shows only the electronic device 1 with the components 12-13, it being understood by a person skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or a different arrangement of components.

In connection with fig. 1, the memory 12 in the electronic device 1 stores a plurality of computer readable instructions to implement an artificial intelligence based path planning method, the processor 13 being executable to implement:

Specifically, the specific implementation method of the above instructions by the processor 13 may refer to the description of the relevant steps in the corresponding embodiment of fig. 1, which is not repeated herein.

It will be appreciated by those skilled in the art that the schematic diagram is merely an example of the electronic device 1 and does not constitute a limitation of the electronic device 1, the electronic device 1 may be a bus type structure, a star type structure, the electronic device 1 may further comprise more or less other hardware or software than illustrated, or a different arrangement of components, e.g. the electronic device 1 may further comprise an input-output device, a network access device, etc.

It should be noted that the electronic device 1 is only used as an example, and other electronic products that may be present in the present application or may be present in the future are also included in the scope of the present application by way of reference.

The memory 12 includes at least one type of readable storage medium, which may be non-volatile or volatile. The readable storage medium includes flash memory, a removable hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 12 may in some embodiments be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. The memory 12 may in other embodiments also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (SMARTMEDIACARD, SMC), a secure digital (SecureDigital, SD) card, a flash memory card (FLASHCARD) or the like provided on the electronic device 1. Further, the memory 12 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 12 may be used not only for storing application software installed in the electronic device 1 and various types of data, such as codes of path planning programs based on artificial intelligence, etc., but also for temporarily storing data that has been output or is to be output.

The processor 13 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (CentralProcessingunit, CPU), microprocessors, digital processing chips, graphics processors, various control chips, and the like. The processor 13 is a control core (ControlUnit) of the electronic device 1, connects the various components of the entire electronic device 1 using various interfaces and lines, executes programs or modules stored in the memory 12 (e.g., performs an artificial intelligence based path planning program, etc.), and invokes data stored in the memory 12 to perform various functions of the electronic device 1 and process data.

The processor 13 executes an operating system of the electronic device 1 and various types of applications installed. The processor 13 executes the application program to implement the steps of the various embodiments of the artificial intelligence based path planning method described above, such as the steps shown in fig. 1.

Illustratively, the computer program may be partitioned into one or more modules/units that are stored in the memory 12 and executed by the processor 13 to complete the present application. The one or more modules/units may be a series of computer readable instruction segments capable of performing the specified functions, which instruction segments describe the execution of the computer program in the electronic device 1. For example, the computer program may be divided into a construction unit 110, a first calculation unit 111, a second calculation unit 112, a third calculation unit 113, a combination unit 114, a screening unit 115.

The integrated units implemented in the form of software functional modules described above may be stored in a computer readable storage medium. The software functional modules are stored in a storage medium and include instructions for causing a computer device (which may be a personal computer, a computer device, or a network device, etc.) or a processor (processor) to perform portions of the artificial intelligence-based path planning method according to various embodiments of the application.

The integrated modules/units of the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as a stand alone product. Based on this understanding, the present application may also be implemented by a computer program for instructing a relevant hardware device to implement all or part of the procedures of the above-mentioned embodiment method, where the computer program may be stored in a computer readable storage medium and the computer program may be executed by a processor to implement the steps of each of the above-mentioned method embodiments.

Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a Read-only memory (ROM), a random access memory, other memory, and the like.

Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created from the use of blockchain nodes, and the like.

The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The blockchain (Blockchain), essentially a de-centralized database, is a string of data blocks that are generated in association using cryptographic methods, each of which contains information from a batch of network transactions for verifying the validity (anti-counterfeit) of its information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.

The bus may be a peripheral component interconnect standard (PeripheralComponentInterconnect, PCI) bus, or an extended industry standard architecture (ExtendedIndustryStandardArchitecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. For ease of illustration, only one arrow is shown in FIG. 3, but only one bus or one type of bus is not shown. The bus is arranged to enable a connection communication between the memory 12 and the at least one processor 13 etc.

Although not shown, the electronic device 1 may further comprise a power source (such as a battery) for powering the various components, which may preferably be logically connected to the at least one processor 13 via a power management means, whereby the functions of charge management, discharge management, and power consumption management are achieved by the power management means. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which are not described herein.

Further, the electronic device 1 may also comprise a network interface, optionally comprising a wired interface and/or a wireless interface (e.g. WI-FI interface, bluetooth interface, etc.), typically used for establishing a communication connection between the electronic device 1 and other electronic devices.

The electronic device 1 may optionally further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (organic light-emitting diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.

The embodiment of the application also provides a computer readable storage medium (not shown), wherein computer readable instructions are stored in the computer readable storage medium, and the computer readable instructions are executed by a processor in an electronic device to implement the path planning method based on artificial intelligence according to any one of the embodiments.

It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.

In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.

The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional module in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.

Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. Several of the elements or devices described in the specification may be embodied by one and the same item of software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.

Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present application and not for limiting the same, and although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present application without departing from the spirit and scope of the technical solution of the present application.

Claims

1. A path planning method based on artificial intelligence, the method comprising:

Calculating a transmission cost of each server node, comprising: inquiring the maximum node number of the server node to jump to the receiving node to be used as the jumping node number; normalizing the jump node number to obtain a normalized jump node number; inputting the normalized number of jump nodes into a custom mapping model to obtain a mapping result and taking the mapping result as the sending cost of the server node, wherein the higher the sending cost is, the harder the receiving node receives the data sent by the server node, and the custom mapping model satisfies the following relation: Wherein x represents the server node; h (x) represents a transmission cost of the server node represented by x, and the higher the transmission cost is, the higher the cost is when data is transmitted from the server node to the receiving node; n ^x represents the normalized number of hops nodes of the server node x; e represents a natural constant; the sending cost is used for representing the difficulty of the server node to send data to the receiving node;

2. The artificial intelligence based path planning method of claim 1 wherein said calculating a cost of receipt for each server node comprises:

3. The artificial intelligence based path planning method of claim 1 wherein said calculating a communication priority of the server node as a function of the reception cost and the transmission cost comprises:

4. The artificial intelligence based path planning method of claim 3 wherein the communication priority calculation method satisfies the following relationship:

Wherein x represents the server node; w ₁ represents the reception weight; g (x) represents the cost of reception of the server node x; w ₁ represents the transmission weight; h (x) represents the transmission cost of the server node x; f (x) represents the communication priority of the server node x, the higher the value of the communication priority, the more should the server node be invoked to transmit data.

5. The artificial intelligence based path planning method of claim 4 wherein said calculating a priority indicator for each communication path based on the communication priority comprises:

6. The artificial intelligence based path planning method of claim 1 wherein the screening target paths and alternative paths from the path set according to the priority index to complete path planning comprises:

7. An artificial intelligence based path planning apparatus, the apparatus comprising means for implementing the method of any one of claims 1 to 6, the apparatus comprising:

8. An electronic device, the electronic device comprising:

A memory storing computer readable instructions; and

A processor executing computer readable instructions stored in the memory to implement the artificial intelligence based path planning method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized by: the computer readable storage medium has stored therein computer readable instructions that are executed by a processor in an electronic device to implement the artificial intelligence based path planning method of any one of claims 1 to 6.