Method for determining information propagation paths in swarm intelligence scenario, and related device
By determining node similarity and link importance in swarm intelligence scenarios and using indirect communication to spread information, the problem of high cost of direct point-to-point communication is solved, achieving low-cost and efficient information dissemination.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- SHENZHEN HAIXING HARBOR DEVELOPMENT CO LTD
- Filing Date
- 2024-12-30
- Publication Date
- 2026-07-02
AI Technical Summary
In swarm intelligence scenarios, when information is disseminated using point-to-point direct communication, a large amount of communication resources are required, resulting in high communication costs.
By obtaining the node similarity and link importance in the target network, the information propagation path is determined, and information is propagated using indirect communication methods.
It reduces communication costs in the information dissemination process and improves the efficiency of information dissemination.
Smart Images
Figure CN2024143884_02072026_PF_FP_ABST
Abstract
Description
Methods and related equipment for determining information propagation paths in swarm intelligence scenarios Technical Field
[0001] This application relates to the field of network science and technology, and in particular to a method and related equipment for determining information propagation paths in a swarm intelligence scenario. Background Technology
[0002] In swarm intelligence scenarios, for networks composed of individuals as nodes, information needs to be propagated between these individuals (i.e., each node). Furthermore, swarm intelligence scenarios may contain individuals of different categories, requiring information to be disseminated from one category to another.
[0003] In related technologies, point-to-point direct communication is typically used for nodes in a network within a swarm intelligence scenario. For example, if a node wants to propagate information to multiple target nodes, it needs to communicate directly with each target node individually, requiring that the originating node and each target node be able to communicate directly. The problem with these technologies is that point-to-point direct communication requires significant communication resources, which is detrimental to reducing communication costs during information propagation.
[0004] Therefore, the relevant technologies still need to be improved and developed. Summary of the Invention
[0005] The main purpose of this application is to provide a method and related equipment for determining information propagation paths in swarm intelligence scenarios. It aims to solve the technical problem in related technologies that the use of point-to-point direct communication for information propagation between nodes in a network in swarm intelligence scenarios requires a large amount of communication resources, which is not conducive to reducing communication costs in the information propagation process.
[0006] To achieve the above objectives, the first aspect of this application provides a method for determining information propagation paths in a swarm intelligence scenario, wherein the method includes:
[0007] Obtain the target network, wherein the target network includes multiple nodes and multiple links for connecting the nodes, and the nodes include first-type nodes and second-type nodes;
[0008] Determine the node similarity corresponding to each of the above nodes, wherein the node similarity corresponding to a node is used to characterize the degree of similarity between the above node and all the above first type of nodes;
[0009] Determine the importance of each of the above links;
[0010] For each node in the target network, the importance of information propagation between the node and its neighboring nodes is determined based on the node similarity and the link importance between the node and its neighboring nodes.
[0011] Based on the aforementioned information propagation importance, the information propagation path from the first type of node to all the second type of node is determined.
[0012] Optionally, the first type of node mentioned above is an expert node, and the second type of node mentioned above is a non-expert node.
[0013] Optionally, determining the node similarity corresponding to each of the above nodes includes:
[0014] For each node, calculate the basic similarity between the above-mentioned node and each first-class node;
[0015] Based on the sum of the basic similarities between the above nodes and each of the first type of nodes, the node similarity corresponding to the above nodes is determined.
[0016] Optionally, for each node, the basic similarity between the node and each node of the first type is calculated, including:
[0017] For each node in the target network described above, perform the following operations:
[0018] Obtain the walk volume corresponding to the above nodes through random walk;
[0019] Calculate the cosine similarity between the flow rate corresponding to the above nodes and the flow rate corresponding to each first-class node, and use it as the basic similarity between the above nodes and each first-class node.
[0020] Optionally, determining the link importance corresponding to each of the above links includes:
[0021] Calculate the Kemeny constant value corresponding to the target network mentioned above;
[0022] For each link, the link is removed from the target network to obtain the candidate network corresponding to the link. The Kemeny constant value corresponding to the candidate network is calculated. Based on the Kemeny constant value corresponding to the target network and the Kemeny constant value corresponding to the candidate network, the link importance corresponding to the link is determined.
[0023] Optionally, for each node in the target network, the importance of information propagation between the node and its neighboring nodes is determined based on the node similarity and the link importance between the node and its neighboring nodes, including:
[0024] For each node in the target network, calculate the logarithm of the node similarity corresponding to the node, and multiply the logarithm by the link importance between the node and its neighboring nodes to obtain the information propagation importance between the node and its neighboring nodes.
[0025] Optionally, the target network is a connected network, and the determination of the information propagation path from the first type of node to all the second type of node based on the information propagation importance includes:
[0026] The information propagation path is initialized based on the first type of nodes mentioned above;
[0027] Take the first type of node mentioned above as the starting node;
[0028] One of the second-type nodes in the target network that is not included in the above information propagation path is taken as the termination node;
[0029] Select the neighboring node with the highest information propagation importance between itself and the above-mentioned starting node and add it to the above-mentioned information propagation path, and take the selected neighboring node as the starting node.
[0030] Return to the above steps of selecting the neighboring node with the highest information propagation importance between the above starting node and adding it to the above information propagation path, and using the selected neighboring node as the starting node, until the above ending node is added to the above information propagation path;
[0031] Return to the steps described above, starting with the first type of node, until all the second type of nodes have been added to the information propagation path.
[0032] A second aspect of this application provides a system for determining information propagation paths in a swarm intelligence scenario, wherein the system comprises:
[0033] A network acquisition module is used to acquire a target network, wherein the target network includes multiple nodes and multiple links for connecting the nodes, and the nodes include first-type nodes and second-type nodes;
[0034] The node similarity determination module is used to determine the node similarity corresponding to each of the above nodes, wherein the node similarity corresponding to a node is used to characterize the degree of similarity between the above node and all the above first type of nodes;
[0035] The link importance determination module is used to determine the link importance corresponding to each of the above links;
[0036] The information propagation importance determination module is used to determine the information propagation importance between each node and its neighboring nodes for each node in the target network, based on the node similarity corresponding to the node and the link importance between the node and its neighboring nodes.
[0037] The information propagation path determination module is used to determine the information propagation path from the first type of node to all the second type of node based on the information propagation importance mentioned above.
[0038] A third aspect of this application provides a smart terminal, which includes a memory, a processor, and a swarm intelligence scenario information propagation path determination program stored in the memory and executable on the processor. When the swarm intelligence scenario information propagation path determination program is executed by the processor, it implements any of the steps of the swarm intelligence scenario information propagation path determination method.
[0039] A fourth aspect of this application provides a computer-readable storage medium storing a program for determining information propagation paths in a swarm intelligence scenario. When executed by a processor, the program implements the steps of any one of the methods for determining information propagation paths in a swarm intelligence scenario.
[0040] As can be seen from the above, the method in this application includes: obtaining a target network, wherein the target network includes multiple nodes and multiple links for connecting the nodes, and the nodes include first-type nodes and second-type nodes; determining the node similarity corresponding to each of the nodes, wherein the node similarity corresponding to a node is used to characterize the degree of similarity between the node and all the first-type nodes; determining the link importance corresponding to each of the links; for each node in the target network, determining the information propagation importance between the node and each of its neighboring nodes based on the node similarity corresponding to the node and the link importance between the node and its neighboring nodes; and determining the information propagation path from the first-type nodes to all the second-type nodes based on the information propagation importance.
[0041] Compared to existing technologies, this application's solution, when propagating information within the target network (specifically, from a first-type node to a second-type node), does not employ direct point-to-point communication. Instead, it first determines the node similarity and link importance of corresponding nodes in real-time within the target network, and then determines the information propagation importance between a node and its neighboring nodes. Based on this information propagation importance, it determines the information propagation path from a first-type node to a second-type node in the target network. This allows for the determination of the optimal propagation path, upon which a first-type node can propagate information to a second-type node. The specific communication method can be direct communication or indirect communication through other nodes. Thus, it does not require direct communication between any two nodes in the target network. It eliminates the need for each first-type node to communicate directly with every second-type node, reducing the required communication resources and communication costs during information propagation. Attached Figure Description
[0042] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0043] Figure 1 is a flowchart illustrating a method for determining information propagation paths in a swarm intelligence scenario provided in an embodiment of this application;
[0044] Figure 2 is a schematic flowchart of a method for determining information propagation paths in a swarm intelligence scenario provided in an embodiment of this application.
[0045] Figure 3 is a schematic diagram of the components of an information propagation path determination system in a swarm intelligence scenario provided in an embodiment of this application.
[0046] Figure 4 is a block diagram illustrating the internal structure of a smart terminal according to an embodiment of this application. Detailed Implementation
[0047] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of this application with unnecessary detail.
[0048] Many specific details are set forth in the following description in order to provide a full understanding of this application. However, this application may also be implemented in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this application. Therefore, this application is not limited to the specific embodiments disclosed below.
[0049] In swarm intelligence scenarios, networks composed of individuals as nodes require information propagation between these individuals (i.e., nodes). Furthermore, swarm intelligence scenarios may involve individuals of different categories, necessitating the dissemination of information from one category to another. For example, information from expert nodes with higher knowledge levels needs to be propagated to non-expert nodes with lower knowledge levels, thereby better utilizing expert information. In some applications, better utilization of expert information can enhance the overall level of collective intelligence, thereby improving the effectiveness of subsequent decision-making.
[0050] Therefore, it is necessary to consider how to disseminate information from individual experts to other individuals. That is, to achieve information dissemination between nodes in a target network (such as a social network). In related technologies, for nodes in a network within a swarm intelligence scenario, point-to-point direct communication is typically used. For example, if a node wants to disseminate information to multiple target nodes, it needs to communicate directly with each target node individually, requiring the originating node to be able to communicate directly with each target node. The problem with these technologies is that point-to-point direct communication requires significant communication resources, which is detrimental to reducing communication costs during information dissemination.
[0051] Social learning can significantly enhance the speed and impact of information dissemination. However, in real-world scenarios, it is costly for individuals to communicate with all their social partners. This is because it's possible to propagate messages through multiple optimal paths without reaching every individual. Therefore, in the context of collective intelligence with social learning, finding the optimal dissemination path from experts to non-experts can enable the rapid, effective, and low-cost dissemination of expert information within the group.
[0052] To address at least one of the aforementioned technical problems, this application provides a method for determining information propagation paths in a swarm intelligence scenario. Specifically, the method involves: acquiring a target network, which includes multiple nodes and multiple links connecting these nodes; determining the node similarity of each node, where the node similarity represents the degree of similarity between the node and all the first-type nodes; determining the link importance of each link; for each node in the target network, determining the information propagation importance between the node and its neighboring nodes based on the node similarity and the link importance of the links between the node and its neighboring nodes; and determining the information propagation path from the first-type nodes to all the second-type nodes based on the information propagation importance.
[0053] Compared to existing technologies, this application's solution, when propagating information within the target network (specifically, from a first-type node to a second-type node), does not employ direct point-to-point communication. Instead, it first determines the node similarity and link importance of corresponding nodes in real-time within the target network, and then determines the information propagation importance between a node and its neighboring nodes. Based on this information propagation importance, it determines the information propagation path from a first-type node to a second-type node in the target network. This allows for the determination of the optimal propagation path, upon which a first-type node can propagate information to a second-type node. The specific communication method can be direct communication or indirect communication through other nodes. Thus, it does not require direct communication between any two nodes in the target network. It eliminates the need for each first-type node to communicate directly with every second-type node, reducing the required communication resources and communication costs during information propagation.
[0054] As shown in Figure 1, this application embodiment provides a method for determining information propagation paths in a swarm intelligence scenario. Specifically, the method includes the following steps:
[0055] Step S100: Obtain the target network, wherein the target network includes multiple nodes and multiple links for connecting the nodes, and the nodes include first-type nodes and second-type nodes.
[0056] The target network described above is a social network. Each node in the target network can be an individual within the social network, specifically, it could be a user device, an intelligent robot, or other types of individuals, without specific limitations. The links described above are used to establish communication connections between nodes, and the specific communication method can be wired or wireless communication, without specific limitations. The links described above can be considered as edges connecting nodes in the target network. It should be noted that, in this embodiment, it is not required that there be a link connecting any two nodes.
[0057] In this embodiment, the nodes in the target network can be of different categories. For example, they can include first-type nodes and second-type nodes. The specific category classification criteria can be determined and adjusted according to actual needs. It should be noted that the target network can include one or more first-type nodes, or it can include one or more second-type nodes. In this embodiment, we will take one first-type node and multiple second-type nodes as an example to specifically illustrate the process, in order to determine the optimal information propagation path from the first-type node to all second-type nodes.
[0058] In one application scenario, when multiple first-type nodes exist, the optimal information propagation path from each required first-type node to all second-type nodes can be determined separately. It should be noted that the information propagation paths corresponding to different first-type nodes can be the same or different; if the paths are the same, it means that all first-type nodes are on the same path.
[0059] In this embodiment, the first type of nodes are expert nodes, and the second type of nodes are non-expert nodes. The knowledge level (or intelligence level) of the expert nodes is higher than that of the non-expert nodes. Specifically, the expert nodes possess sufficient professional knowledge of the evaluation task and can make more accurate assessments. The non-expert individuals possess little or no professional knowledge of the evaluation task, and their assessments are not very accurate. In this embodiment, by determining the optimal path from expert nodes to all other non-expert nodes, information can be efficiently propagated from expert nodes to non-expert nodes during the social learning process.
[0060] In one application scenario, the aforementioned expert nodes and non-expert nodes are individuals with social learning capabilities. These individuals can be mapped to a social network (i.e., the target network), where the edges (i.e., links used to connect nodes) represent direct social connections between nodes.
[0061] Step S200: Determine the node similarity corresponding to each of the above nodes, wherein the node similarity corresponding to a node is used to characterize the degree of similarity between the above node and all the above first type of nodes.
[0062] In this embodiment of the application, for each node in the target network, the node similarity is calculated and determined to characterize its similarity with the expert node. The higher the similarity with the expert node, the better the dissemination efficiency and effect of the node in the information dissemination process, and the more it should be selected.
[0063] Specifically, determining the node similarity corresponding to each of the aforementioned nodes includes:
[0064] For each node, calculate the basic similarity between the above-mentioned node and each first-class node;
[0065] Based on the sum of the basic similarities between the above nodes and each of the first type of nodes, the node similarity corresponding to the above nodes is determined.
[0066] Specifically, for each node, the basic similarity between that node and each node of the first type is calculated, including:
[0067] For each node in the target network described above, perform the following operations:
[0068] Obtain the walk volume corresponding to the above nodes through random walk;
[0069] Calculate the cosine similarity between the flow rate corresponding to the above nodes and the flow rate corresponding to each first-class node, and use it as the basic similarity between the above nodes and each first-class node.
[0070] Specifically, in this embodiment of the application, the constructed social network G is used as the target network, which includes n nodes. The node set is denoted as NodeSet. Two subsets are obtained by dividing the nodes in the node set into two types: expert node set ESet and non-expert node set NESet. The target network also has an edge set EdgeSet, which stores all links (i.e. edges) corresponding to the target network.
[0071] For the target network with n nodes, the number of random walk steps per node is set to m (the value of m can be set and adjusted according to actual needs). Then, a random walk is performed on each node to obtain n m-dimensional walk vectors, where the elements of the vectors are the nodes visited during the random walk. The similarity between the vectors is calculated based on cosine similarity. For example, for two given m-dimensional walk vectors A and B, the cosine similarity between them is calculated based on the following formula (1):
[0072] For each node i∈NodeSet, we can calculate the cosine similarity C between its vector and that of the expert node j∈ESet. ij The total node similarity corresponding to node i is C.i =∑ j∈ESet C ij .
[0073] Step S300: Determine the importance of each of the above links.
[0074] The link importance mentioned above is used to characterize the significance of each link in the information propagation process. Link importance can be determined based on pre-set weight values or in real-time according to the actual network conditions.
[0075] In this embodiment of the application, determining the link importance corresponding to each of the above-mentioned links includes:
[0076] Calculate the Kemeny constant value corresponding to the target network mentioned above;
[0077] For each link, the link is removed from the target network to obtain the candidate network corresponding to the link. The Kemeny constant value corresponding to the candidate network is calculated. Based on the Kemeny constant value corresponding to the target network and the Kemeny constant value corresponding to the candidate network, the link importance corresponding to the link is determined.
[0078] Specifically, the Kemeny constant value can be calculated by combining graph theory and Markov chains. It should be noted that the embodiments in this application use an undirected network, and the degree of each node is at least 2 to ensure that the process of removing edges still conforms to the Markov process.
[0079] Consider discrete-time, finite-state, and homogeneous Markov chains, where the Markov chain is a discrete-time stochastic process x. k , k∈n, and is characterized by the following equation, as shown in formula (2):
[0080] Where n represents the number of states in the Markov process, specifically the number of nodes in the target network in this embodiment. p(E|F) represents the probability that event E occurs when event F occurs. A Markov chain with n states is completely described by an n×n transition probability matrix P, whose elements P ij State S i Just one step to transition to state S j The probability of . P is a row random nonnegative matrix, because the elements in each row are probabilities and their sum is 1.
[0081] Let P denote the transition probability matrix of a finite irreducible Markov chain, and let there exist conditions satisfying Pu = u and π. T P = π T The steady-state probability vector π and the all-1 vector u, from state S i to state Sj Average first pass time m ij This indicates that when the starting point is S i When reaching target S j If the expected number of steps is given, then the Kemeny constant can be expressed by the following formula (3):
[0082] Further calculations in, It represents the link importance corresponding to the link connecting nodes i and j. K is the Kemeny constant value corresponding to the candidate network after removing the link. ori This is the Kemeny constant value of the target network when the link is not removed.
[0083] Step S400: For each node in the target network, determine the importance of information propagation between the node and its neighboring nodes based on the node similarity and the link importance between the node and its neighboring nodes.
[0084] Specifically, for each node in the target network, based on the node similarity and the link importance between the node and its neighboring nodes, the importance of information propagation between the node and its neighboring nodes is determined, including:
[0085] For each node in the target network, calculate the logarithm of the node similarity corresponding to the node, and multiply the logarithm by the link importance between the node and its neighboring nodes to obtain the information propagation importance between the node and its neighboring nodes.
[0086] In this embodiment of the application, for any node, such as node i, the importance of information propagation between it and its neighboring node j is calculated based on the following formula (4):
[0087] The larger the value of L, the more important the points connected by the selected edge are. It should be noted that the logarithm in formula (4) is base 2. In actual use, it can be adjusted according to actual needs, and no specific limitation is made here.
[0088] Step S500: Determine the information propagation path from the first type of node to all the second type of node based on the information propagation importance mentioned above.
[0089] Specifically, the target network mentioned above is a connected network, and the information propagation path from the first type of node to all the second type of nodes is determined based on the importance of information propagation, including:
[0090] The information propagation path is initialized based on the first type of nodes mentioned above;
[0091] Take the first type of node mentioned above as the starting node;
[0092] One of the second-type nodes in the target network that is not included in the above information propagation path is taken as the termination node;
[0093] Select the neighboring node with the highest information propagation importance between itself and the above-mentioned starting node and add it to the above-mentioned information propagation path, and take the selected neighboring node as the starting node.
[0094] Return to the above steps of selecting the neighboring node with the highest information propagation importance between the above starting node and adding it to the above information propagation path, and using the selected neighboring node as the starting node, until the above ending node is added to the above information propagation path;
[0095] Return to the steps described above, starting with the first type of node, until all the second type of nodes have been added to the information propagation path.
[0096] In one application scenario, the optimal propagation path from expert node i to non-expert node j is selected as follows:
[0097] ① Obtain the NeighborSet of node i. For m∈NeighborSet, select the node m with the largest corresponding L value. If j=m, end the path selection and obtain the optimal path.<i,j> Otherwise, go to step ②;
[0098] ② Select the neighbor set NeighborSet of m. For t∈NeighborSet, select the node t that has the largest corresponding L value. If j=t, then end the path selection and obtain the optimal path.<i,t,j> Otherwise, continue with step ②.
[0099] Finally, multiple optimal paths from expert node i to all non-expert nodes j can be obtained, in the form of:<i,...t,...j> .
[0100] It should be noted that in the embodiments of this application, i and j in node i and node j only represent the corresponding node identifiers, and whether node i and node j are expert nodes or non-expert nodes depends on the specific description.
[0101] Figure 2 is a schematic flowchart illustrating the information propagation path determination method in a swarm intelligence scenario provided by an embodiment of this application. As shown in Figure 2, in this embodiment, the target network is obtained, node similarity is determined based on random walks, link importance is determined using the Kemeny constant, information propagation importance is determined based on node similarity and link importance, and finally, the information propagation path is determined based on the information propagation importance. In this way, the optimal propagation path can be found directly between experts and non-experts, and information can be propagated to other non-expert nodes without needing to propagate through all social connections. This saves information propagation resources and improves information propagation efficiency.
[0102] As can be seen from the above, the method for determining information propagation paths in a swarm intelligence scenario provided in this application embodiment involves: acquiring a target network, wherein the target network includes multiple nodes and multiple links for connecting the nodes, and the nodes include first-type nodes and second-type nodes; determining the node similarity corresponding to each node, wherein the node similarity corresponding to a node is used to characterize the degree of similarity between the node and all the first-type nodes; determining the link importance corresponding to each link; for each node in the target network, determining the information propagation importance between the node and each of its neighboring nodes based on the node similarity corresponding to the node and the link importance between the node and its neighboring nodes; and determining the information propagation path from the first-type nodes to all the second-type nodes based on the information propagation importance.
[0103] Compared to existing technologies, this application's solution, when propagating information within the target network (specifically, from a first-type node to a second-type node), does not employ direct point-to-point communication. Instead, it first determines the node similarity and link importance of corresponding nodes in real-time within the target network, and then determines the information propagation importance between a node and its neighboring nodes. Based on this information propagation importance, it determines the information propagation path from a first-type node to a second-type node in the target network. This allows for the determination of the optimal propagation path, upon which a first-type node can propagate information to a second-type node. The specific communication method can be direct communication or indirect communication through other nodes. Thus, it does not require direct communication between any two nodes in the target network. It eliminates the need for each first-type node to communicate directly with every second-type node, reducing the required communication resources and communication costs during information propagation.
[0104] As shown in Figure 3, corresponding to the information propagation path determination method in the above-mentioned swarm intelligence scenario, this application embodiment also provides an information propagation path determination system in the swarm intelligence scenario, the above-mentioned information propagation path determination system in the swarm intelligence scenario includes:
[0105] The network acquisition module 310 is used to acquire a target network, wherein the target network includes multiple nodes and multiple links for connecting the nodes, and the nodes include first-type nodes and second-type nodes.
[0106] The node similarity determination module 320 is used to determine the node similarity corresponding to each of the above nodes, wherein the node similarity corresponding to a node is used to characterize the degree of similarity between the above node and all the above first type of nodes;
[0107] The link importance determination module 330 is used to determine the link importance corresponding to each of the above links;
[0108] The information propagation importance determination module 340 is used to determine the information propagation importance between the above-mentioned node and each of its neighboring nodes for each node in the target network, based on the node similarity corresponding to the above-mentioned node and the link importance of the links between the above-mentioned node and its neighboring nodes.
[0109] The information propagation path determination module 350 is used to determine the information propagation path from the first type of node to all the second type of node based on the information propagation importance mentioned above.
[0110] Thus, when propagating information within the target network (specifically, from the first type of node to the second type of node), a direct point-to-point communication method is not used. Instead, the similarity between nodes and the importance of links are determined in real-time for each node in the target network. This allows for the real-time determination of the information propagation importance between a node and its neighboring nodes. Based on this importance, the optimal propagation path from the first type of node to the second type of node in the target network is determined. This allows the first type of node to propagate information to the second type of node, and the communication method can be direct communication or indirect communication through other nodes. Therefore, direct communication between any two nodes in the target network is not required. The elimination of the need for each first type of node to communicate directly with every second type of node reduces the required communication resources and lowers the communication costs during information propagation.
[0111] It should be noted that the specific structure and implementation of the information propagation path determination system and its various modules or units in the above-mentioned swarm intelligence scenario can be referred to the corresponding descriptions in the above method embodiments, and will not be repeated here.
[0112] It should be noted that the division of the various modules in the information propagation path determination system in the above-mentioned swarm intelligence scenario is not unique and is not intended as a specific limitation.
[0113] Based on the above embodiments, this application also provides a smart terminal, the principle block diagram of which is shown in Figure 4. The smart terminal includes a processor, a memory, a network interface, and a display screen connected via a system bus. The processor of the smart terminal provides computing and control capabilities. The memory of the smart terminal includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and an information propagation path determination program for swarm intelligence scenarios. The internal memory provides an environment for the operation of the operating system and the information propagation path determination program for swarm intelligence scenarios stored in the non-volatile storage medium. The network interface of the smart terminal is used to communicate with external terminals via a network connection. When the information propagation path determination program for swarm intelligence scenarios is executed by the processor, it implements the steps of any of the above-described information propagation path determination methods for swarm intelligence scenarios. The display screen of the smart terminal can be a liquid crystal display screen or an electronic ink display screen.
[0114] Those skilled in the art will understand that the principle block diagram shown in Figure 4 is merely a block diagram of a portion of the structure related to the solution of this application, and does not constitute a limitation on the smart terminal to which the solution of this application is applied. A specific smart terminal may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0115] In one embodiment, a smart terminal is provided, the smart terminal including a memory, a processor, and an information propagation path determination program for a swarm intelligence scenario stored in the memory and executable on the processor. When the information propagation path determination program for a swarm intelligence scenario is executed by the processor, it implements the steps of any of the information propagation path determination methods for a swarm intelligence scenario provided in the embodiments of this application.
[0116] This application also provides a computer-readable storage medium storing a program for determining information propagation paths in a swarm intelligence scenario. When executed by a processor, the program implements the steps of any of the methods for determining information propagation paths in a swarm intelligence scenario provided in this application.
[0117] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.
[0118] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the above device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above device can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0119] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0120] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0121] In the embodiments provided in this application, it should be understood that the disclosed systems / terminal devices and methods can be implemented in other ways. For example, the system / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units described above is merely a logical functional division, and in actual implementation, it can be divided in other ways. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.
[0122] If the integrated modules / units described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, and software distribution media, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.
[0123] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions are not in essence a departure from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.
Claims
1. A method for determining information propagation paths in a swarm intelligence scenario, characterized in that, The method includes: Obtain a target network, wherein the target network includes multiple nodes and multiple links for connecting the nodes, and the nodes include first-type nodes and second-type nodes; Determine the node similarity corresponding to each of the nodes, wherein the node similarity corresponding to a node is used to characterize the degree of similarity between the node and all the nodes of the first type; Determine the link importance corresponding to each of the aforementioned links; For each node in the target network, the importance of information propagation between the node and its neighboring nodes is determined based on the node similarity and the link importance between the node and its neighboring nodes. The information propagation path from the first type of node to all second type of nodes is determined based on the importance of the information propagation.
2. The method for determining information propagation paths in a swarm intelligence scenario according to claim 1, characterized in that, The first type of node is an expert node, and the second type of node is a non-expert node.
3. The method for determining information propagation paths in a swarm intelligence scenario according to claim 1, characterized in that, Determining the node similarity corresponding to each of the nodes includes: For each node, calculate the basic similarity between the node and each first-class node; The node similarity corresponding to the node is determined based on the sum of the basic similarities between the node and each of the first type of nodes.
4. The method for determining information propagation paths in a swarm intelligence scenario according to claim 3, characterized in that, The step of calculating the basic similarity between each node and each node of the first type includes: For each node in the target network, perform the following operations: The walk volume corresponding to the node is obtained by random walk; Calculate the cosine similarity between the flow rate corresponding to the node and the flow rate corresponding to each first-class node, and use it as the basic similarity between the node and each first-class node.
5. The method for determining information propagation paths in a swarm intelligence scenario according to claim 1, characterized in that, Determining the link importance corresponding to each of the links includes: Calculate the Kemeny constant value corresponding to the target network; For each link, the link is removed from the target network to obtain the candidate network corresponding to the link. The Kemeny constant value corresponding to the candidate network is calculated. Based on the Kemeny constant value corresponding to the target network and the Kemeny constant value corresponding to the candidate network, the link importance corresponding to the link is determined.
6. The method for determining information propagation paths in a swarm intelligence scenario according to claim 1, characterized in that, For each node in the target network, determining the information propagation importance between the node and its neighboring nodes based on the node similarity and the link importance between the node and its neighboring nodes includes: For each node in the target network, calculate the logarithm of the node similarity corresponding to the node, and multiply the logarithm by the link importance between the node and its neighboring nodes to obtain the information propagation importance between the node and its neighboring nodes.
7. The method for determining information propagation paths in a swarm intelligence scenario according to any one of claims 1 to 6, characterized in that, The target network is a connected network, and determining the information propagation path from the first type of node to all second type of nodes based on the information propagation importance includes: The information propagation path is initialized based on the first type of node; Take the first type of node as the starting node; A second-type node in the target network that is not included in the information propagation path is designated as a termination node; Select the neighboring node with the highest information propagation importance between itself and the starting node and add it to the information propagation path, and use the selected neighboring node as the starting node; Return to the step of selecting the neighboring node with the highest information propagation importance between the starting node and the starting node, add it to the information propagation path, and use the selected neighboring node as the starting node, until the ending node is added to the information propagation path; Return to the step of using the first type of node as the starting node, until all the second type of nodes have been added to the information propagation path.
8. A system for determining information propagation paths in a swarm intelligence scenario, characterized in that, The system includes: A network acquisition module is used to acquire a target network, wherein the target network includes multiple nodes and multiple links for connecting the nodes, and the nodes include first-type nodes and second-type nodes; A node similarity determination module is used to determine the node similarity corresponding to each of the nodes, wherein the node similarity corresponding to a node is used to characterize the degree of similarity between the node and all the first type of nodes; The link importance determination module is used to determine the link importance corresponding to each of the links; The information propagation importance determination module is used to determine the information propagation importance between a node and its neighboring nodes for each node in the target network, based on the node similarity corresponding to the node and the link importance of the links between the node and its neighboring nodes. The information propagation path determination module is used to determine the information propagation path from the first type of node to all second type of nodes based on the importance of information propagation.
9. A smart terminal, characterized in that, The smart terminal includes a memory, a processor, and a swarm intelligence scenario information propagation path determination program stored in the memory and executable on the processor. When the processor executes the swarm intelligence scenario information propagation path determination program, it implements the steps of the swarm intelligence scenario information propagation path determination method as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program for determining information propagation paths in a swarm intelligence scenario. When the program is executed by a processor, it implements the steps of the method for determining information propagation paths in a swarm intelligence scenario as described in any one of claims 1 to 7.