Text pushing method and system

Abstract

The application provides a text pushing method and system, the method comprising: obtaining an aggregation result of a target object set; obtaining a high-similarity set corresponding to each similar subgraph in the aggregation result; and pushing the target text based on the text unit objects in the high-similarity set. The system executes the method. The application takes the text unit objects corresponding to each similar subgraph in the aggregation result of the target object set as a high-similarity set, and can push the target text to the same user in a short time, thereby ensuring the timeliness and accuracy of the text pushing.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a text push method and system. Background Technology

[0002] In large-scale collaborative translation processes, in a large translation project, the fragmented text is assigned to different users for translation based on the clustering results. However, this cannot guarantee that highly similar texts will be assigned to the same cluster, and therefore cannot guarantee that these highly similar texts will be accurately pushed to the same user for text translation in a short period of time. Summary of the Invention

[0003] The text push method and system provided by this invention are used to solve the above-mentioned problems in the prior art. By taking the text unit objects corresponding to each similar subgraph in the aggregation result of the target object set as a highly similar set, the target text can be pushed to the same user in a short time, ensuring the timeliness and accuracy of text push.

[0004] The present invention provides a text push method, comprising:

[0005] The aggregation result of the target object set is obtained. The target object set includes multiple text unit objects, each text unit object being a vector representation of a target object. The target object is obtained by segmenting the target text. The aggregation result is used to characterize the similarity of each target object in the target set.

[0006] Obtain the high similarity set corresponding to each similar subgraph in the aggregation result, wherein the high similarity set corresponding to the similar subgraph includes the text unit object corresponding to the similar subgraph;

[0007] The target text is pushed based on the text unit objects in the highly similar set.

[0008] According to a text push method provided by the present invention, the method for obtaining the aggregation result of the target object set includes:

[0009] Perform the aggregation process at least once until there are no elements left in the first target difference set;

[0010] The aggregation result is obtained based on all similar subgraphs obtained in at least one of the aggregation processes.

[0011] The aggregation process includes: obtaining similar subgraphs corresponding to the target undirected graph; updating the undirected graph based on the first target difference set and the second target difference set; updating the target undirected graph according to the updated undirected graph; the updated undirected graph serving as the undirected graph in the next aggregation process; the updated target undirected graph serving as the target undirected graph in the next aggregation process; the target undirected graph in the first aggregation process is obtained based on the undirected graph in the first aggregation process; the undirected graph in the first aggregation process is constructed based on the target object set.

[0012] The first target difference set is the difference between the first target set and the second target set. The first target set is determined by the set of all vertices in the similar subgraphs obtained in each aggregation process, and the second target set is determined by the set of all vertices in the target undirected graph in each aggregation process.

[0013] The second target difference set is the difference set between the third target set and the fourth target set. The third target set is determined based on the set of all edges in the similar subgraphs obtained in each aggregation process, and the fourth target set is determined based on the set of all edges in the target undirected graph in each aggregation process.

[0014] According to a text push method provided by the present invention, the method for obtaining the target undirected graph includes:

[0015] Based on each of the target objects, determine the vertices of the undirected graph;

[0016] Determine the edges of the undirected graph based on the relative distance between any two target objects;

[0017] Construct the undirected graph based on its vertices and edges;

[0018] Delete edges in the undirected graph that exceed a preset threshold, and delete isolated vertices in the undirected graph to obtain the target undirected graph.

[0019] According to a text push method provided by the present invention, obtaining the similar subgraph corresponding to the target undirected graph includes:

[0020] The set of the first edges with the smallest relative distance in the target undirected graph is taken as the fifth target set;

[0021] The set of target vertices constituting the first side is taken as the target vertex set;

[0022] Perform the first processing procedure at least once until there are no elements in the sixth target set or there is no second edge with the smallest relative distance in the third target difference set, and obtain the similar subgraph;

[0023] The first processing procedure includes: if the second edge exists in the third target difference set, and if a preset condition is met, then the second processing procedure is executed at least once until the preset condition is not met, and the second edge is deleted from the sixth target set to update the sixth target set until there are no elements in the sixth target set.

[0024] The third target difference set is the difference set between the fifth target set and the sixth target set in each of the first processing steps;

[0025] The preset conditions include: in each of the first processing steps, the non-target vertices constituting the second side are connected to at least a preset number of target vertices in the target vertex set;

[0026] The second processing procedure includes: adding a non-target vertex in the second edge as the target vertex to the target vertex set to update the target vertex set; adding a third edge to the latest fifth target set to update the fifth target set; and updating the sixth target set according to the updated target vertex set. The third edge is the edge connecting the non-target vertex and the target vertex in each second processing procedure. The updated fifth target set is used as the fifth target set in the next first processing procedure, and the updated sixth target set is used as the sixth target set in the next first processing procedure.

[0027] The sixth target set is determined based on the set of all edges in the target undirected graph that are connected to at least one target vertex in the target vertex set during each of the first processing steps.

[0028] According to a text push method provided by the present invention, obtaining the similar sub-graph includes:

[0029] If no element exists in the sixth target set, the similar subgraph is obtained based on the updated target vertex set and the updated fifth target set;

[0030] If the second edge does not exist in the third target difference set, the similarity subgraph is obtained based on the first edge and the target vertex corresponding to the first edge.

[0031] According to a text push method provided by the present invention, the method for obtaining the relative distance includes:

[0032] Obtain the distance between any two target objects and each centroid, where the centroid is obtained after an initial clustering of the target object set;

[0033] The relative distance is obtained based on the distance between any two target objects and each centroid.

[0034] According to a text push method provided by the present invention, obtaining the distance between any two target objects and each centroid includes:

[0035] The distance is determined based on the Euclidean distance, Manhattan distance, or cosine similarity between any two target objects and each centroid.

[0036] The present invention also provides a text push system, comprising: a first acquisition module, a second acquisition module, and a text push module;

[0037] The first acquisition module is used to obtain the aggregation result of the target object set, the target object set includes multiple text unit objects, the text unit objects are vector representations of the target objects, the target objects are obtained by segmenting the target text, and the aggregation result is used to characterize the similarity of each target object in the target set;

[0038] The second acquisition module is used to acquire the high similarity set corresponding to each similar subgraph in the aggregation result, wherein the high similarity set corresponding to the similar subgraph includes the text unit object corresponding to the similar subgraph;

[0039] The text push module is used to push the target text based on the text unit objects in the highly similar set.

[0040] The present invention also provides an electronic device, including a processor and a memory storing a computer program, wherein the processor executes the program to implement the text push method as described above.

[0041] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the text push method as described above.

[0042] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements any of the text push methods described above.

[0043] The text push method and system provided by this invention treats the text unit objects corresponding to each similar subgraph in the aggregation result of the target object set as a highly similar set, which can push the target text to the same user in a short time, ensuring the timeliness and accuracy of text push. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0045] Figure 1 This is a flowchart illustrating the text push method provided by the present invention;

[0046] Figure 2 This is a schematic diagram of the structure of the text push system provided by the present invention;

[0047] Figure 3 This is a schematic diagram of the physical structure of the electronic device provided by the present invention. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0049] Figure 1 This is a flowchart illustrating the text push method provided by the present invention, as shown below. Figure 1 As shown, the method includes:

[0050] Step 100: Obtain the aggregation result of the target object set, wherein the target object set includes multiple text unit objects, the text unit objects are vector representations of the target objects, the target objects are obtained by segmenting the target text, and the aggregation result is used to characterize the similarity of each target object in the target set;

[0051] Step 110: Obtain the high similarity set corresponding to each similar subgraph in the aggregation result. The high similarity set corresponding to the similar subgraph includes the text unit object corresponding to the similar subgraph.

[0052] Step 120: Push the target text based on the text unit objects in the highly similar set.

[0053] It should be noted that the above method can be implemented by computer equipment.

[0054] In this embodiment of the invention, the target object set can specifically be a set of target objects, where each element corresponds to a vector representation of a text unit object. The target object set contains vector representations of at least two target objects or at least two text object units. The text unit object can be obtained by segmenting the target text to be pushed, or more specifically, by segmenting the target text at a certain granularity, such as by segmenting the target text by sentences or paragraphs. All text unit objects are then represented as vectors to obtain the target objects, and the set of all target objects is considered the target object set. The vector representation of text unit objects typically employs two methods: unsupervised methods, using deep neural networks to obtain dense vectors representing a semantic expression; and supervised methods, acquiring independent features of the text to establish a sparse vector representation.

[0055] In this embodiment of the invention, the aggregation result may specifically be obtained after performing at least one aggregation process on the above-mentioned target object set. The aggregation result may specifically be the similarity of each target object in the target set, and may specifically include the similarity subgraphs obtained in each aggregation process.

[0056] In this embodiment of the invention, the text unit objects corresponding to each similar subgraph in the aggregation result are taken as a high similarity set, and the target text is pushed based on each text unit object in the high similarity set. The push of the target text can specifically be to push the target text to the same translator, or to process the target text uniformly, so as to ensure the consistency and uniformity of the translator's translation of the target text.

[0057] The text push method provided by this invention treats the text unit objects corresponding to each similar subgraph in the aggregation result of the target object set as a highly similar set, which can push the target text to the same user in a short time, ensuring the timeliness and accuracy of text push.

[0058] Furthermore, in one embodiment, the method for obtaining the aggregation result of the target object set includes:

[0059] Perform the aggregation process at least once until there are no elements left in the first target difference set;

[0060] The aggregation result is obtained based on all similar subgraphs obtained in at least one of the aggregation processes.

[0061] The aggregation process includes: obtaining similar subgraphs corresponding to the target undirected graph; updating the undirected graph based on the first target difference set and the second target difference set; updating the target undirected graph according to the updated undirected graph; the updated undirected graph serving as the undirected graph in the next aggregation process; the updated target undirected graph serving as the target undirected graph in the next aggregation process; the target undirected graph in the first aggregation process is obtained based on the undirected graph in the first aggregation process; the undirected graph in the first aggregation process is constructed based on the target object set.

[0062] The first target difference set is the difference between the first target set and the second target set. The first target set is determined by the set of all vertices in the similar subgraphs obtained in each aggregation process, and the second target set is determined by the set of all vertices in the target undirected graph in each aggregation process.

[0063] The second target difference set is the difference set between the third target set and the fourth target set. The third target set is determined based on the set of all edges in the similar subgraphs obtained in each aggregation process, and the fourth target set is determined based on the set of all edges in the target undirected graph in each aggregation process.

[0064] In this embodiment of the invention, the aggregation process can specifically involve obtaining similar subgraphs corresponding to the target undirected graph, updating the undirected graph based on the first target difference set and the second target difference set, and updating the target undirected graph based on the updated undirected graph. The updated undirected graph serves as the undirected graph in the next aggregation process, and the updated target undirected graph serves as the target undirected graph in the next aggregation process.

[0065] In this embodiment of the invention, the target undirected graph can be specifically obtained by preprocessing the undirected graph. The undirected graph in the first aggregation process can be specifically constructed based on each target object in the target object set. The undirected graph other than the first aggregation process can be specifically obtained by using the first target difference set as the vertices of the undirected graph and the second target difference set as the edges of the undirected graph.

[0066] In this embodiment of the invention, the absence of any element in the first target difference set can specifically mean that the first target difference set is an empty set. The first target difference set can specifically be the difference set obtained by subtracting the first target set from the second target set in each aggregation process. The first target set can specifically be the set composed of all vertices in the similar subgraph in each aggregation process. The similar subgraph can specifically be constructed from various target objects of the same class in the target undirected graph. The second target set can specifically be the set composed of all vertices in the target undirected graph in each aggregation process.

[0067] In this embodiment of the invention, the second target difference set can be specifically the difference set obtained by subtracting the third target set from the fourth target set in each aggregation process. The third target set can be specifically the set composed of all edges in the similar subgraphs in each aggregation process. The fourth target set can be specifically the set composed of all edges in the target undirected graph in each aggregation process.

[0068] In this embodiment of the invention, clustering divides a set of target objects into different classes according to a specific criterion (such as distance), maximizing the similarity of target objects within the same class and maximizing the differences between target objects in different classes. In other words, after clustering, target objects of the same class are grouped together as much as possible, while target objects of different classes are separated as much as possible. The specific class label is not considered during the partitioning process; the goal is simply to group similar target objects together.

[0069] In this embodiment of the invention, at least one aggregation process is performed until no element exists in the first target difference set, at which point the aggregation process is stopped.

[0070] In this embodiment of the invention, updating the target undirected graph based on the updated undirected graph can specifically involve preprocessing the updated undirected graph to obtain the updated target undirected graph.

[0071] In this embodiment of the invention, after no element exists in the first target difference set, all similar subgraphs obtained through the above aggregation process are used as the aggregation result of each target object in the target object set.

[0072] The text push method provided by this invention constructs an undirected graph of each target object and splits the undirected graph into similar subgraphs, which enables the aggregation of similar target objects, improves the accuracy of the aggregation results, and lays the foundation for ensuring the timeliness and accuracy of text push based on the aggregation results.

[0073] Furthermore, in one embodiment, the method for obtaining the target undirected graph may specifically include:

[0074] Based on each of the target objects, determine the vertices of the undirected graph;

[0075] Determine the edges of the undirected graph based on the relative distance between any two target objects;

[0076] Construct the undirected graph based on its vertices and edges;

[0077] Delete edges in the undirected graph that exceed a preset threshold, and delete isolated vertices in the undirected graph to obtain the target undirected graph.

[0078] In this embodiment of the invention, each target object is used as a vertex of an undirected graph, the relative distance is used as an edge of the undirected graph, and all edges with a relative distance greater than a preset threshold and isolated vertices are deleted from the undirected graph to obtain the target undirected graph.

[0079] In this embodiment of the invention, the isolated vertex can specifically be a vertex that falls outside the undirected graph after all edges with a relative distance greater than a preset threshold are deleted from the undirected graph.

[0080] Furthermore, in one embodiment, the method for obtaining the relative distance may specifically include:

[0081] Obtain the distance between any two target objects and each centroid, where the centroid is obtained after an initial clustering of the target object set;

[0082] The relative distance is obtained based on the distance between any two target objects and each centroid.

[0083] In this embodiment of the invention, the centroid can specifically refer to the k cluster centers obtained after an initial clustering of the target object set, with each cluster center corresponding to a centroid. This initial clustering can specifically employ a common clustering algorithm, such as K-means or DBSCAN.

[0084] In this embodiment of the invention, the relative distance can be specifically obtained by subtracting the absolute values ​​of the distances from each target object to each centroid in pairs, and then summing the absolute values ​​and averaging them.

[0085] Furthermore, in one embodiment, obtaining the distance between any two target objects and each centroid may specifically include:

[0086] The distance is determined based on the Euclidean distance, Manhattan distance, or cosine similarity between any two target objects and each centroid.

[0087] In this embodiment of the invention, the distance can be specifically the distance between vectors, and can be obtained by using the Euclidean distance, Manhattan distance, or cosine similarity between any two target objects and each centroid.

[0088] The text push method provided by this invention constructs an undirected graph based on a set of target objects, and processes the undirected graph to obtain a target undirected graph. This lays the foundation for obtaining corresponding similar subgraphs based on the target undirected graph, thereby grouping similar target objects together and improving the accuracy of clustering results.

[0089] Furthermore, in one embodiment, obtaining the similar subgraphs corresponding to the target undirected graph may specifically include:

[0090] The set of the first edges with the smallest relative distance in the target undirected graph is taken as the fifth target set;

[0091] The set of target vertices constituting the first side is taken as the target vertex set;

[0092] Perform the first processing procedure at least once until there are no elements in the sixth target set or there is no second edge with the smallest relative distance in the third target difference set, and obtain the similar subgraph;

[0093] The first processing procedure includes: if the second edge exists in the third target difference set, and if a preset condition is met, then the second processing procedure is executed at least once until the preset condition is not met, and the second edge is deleted from the sixth target set to update the sixth target set until there are no elements in the sixth target set.

[0094] The third target difference set is the difference set between the fifth target set and the sixth target set in each of the first processing steps;

[0095] The preset conditions include: in each of the first processing steps, the non-target vertices constituting the second side are connected to at least a preset number of target vertices in the target vertex set;

[0096] The second processing procedure includes: adding a non-target vertex in the second edge as the target vertex to the target vertex set to update the target vertex set; adding a third edge to the latest fifth target set to update the fifth target set; and updating the sixth target set according to the updated target vertex set. The third edge is the edge connecting the non-target vertex and the target vertex in each second processing procedure. The updated fifth target set is used as the fifth target set in the next first processing procedure, and the updated sixth target set is used as the sixth target set in the next first processing procedure.

[0097] The sixth target set is determined based on the set of all edges in the target undirected graph that are connected to at least one target vertex in the target vertex set during each of the first processing steps.

[0098] Further, in one embodiment, obtaining the similar subgraph includes:

[0099] If no element exists in the sixth target set, the similar subgraph is obtained based on the updated target vertex set and the updated fifth target set;

[0100] If the second edge does not exist in the third target difference set, the similarity subgraph is obtained based on the first edge and the target vertex corresponding to the first edge.

[0101] In this embodiment of the invention, the fifth target set can be specifically a set composed of the first edge, which can be specifically the edge with the smallest relative distance among all edges constituting the target undirected graph.

[0102] In this embodiment of the invention, a fifth target set is constructed based on the set composed of the first edges.

[0103] In this embodiment of the invention, the target vertex set is a set of target vertices connected to the first edge.

[0104] During the first aggregation process, there is only one first edge, and there are two target vertices connecting the first edge.

[0105] In this embodiment of the invention, the following first processing procedure is repeatedly executed until no element exists in the sixth target set or no second edge with the smallest relative distance exists in the third target difference set. At this point, the first processing procedure is stopped, and a similar subgraph is obtained for each iteration of the first processing procedure. The absence of any element in the sixth target set can specifically mean that the sixth target set is empty. The third target difference set can specifically be the difference set obtained by subtracting the fifth target set from the sixth target set in each iteration of the first processing procedure.

[0106] In this embodiment of the invention, the first processing step can specifically involve repeatedly executing the following second processing step when a second edge exists in the third target difference set, until a preset condition is not met, at which point the execution of the second processing step is stopped. The preset condition can specifically be that in each of the first processing steps, the non-target vertices constituting the second edge are connected to at least a preset number of target vertices in the target vertex set; more specifically, in each of the first processing steps, the non-target vertices constituting the second edge are connected to at least half of the target vertices in the target vertex set.

[0107] In this embodiment of the invention, the second processing step can specifically involve, under the condition that a preset condition is met, adding a non-target vertex from the second edge as a target vertex to the target vertex set to update the target vertex set, adding the third edge to the fifth target set to update the fifth target set, and updating the sixth target set based on the updated target vertex set; under the condition that the preset condition is not met, deleting the second edge from the sixth target set to update the sixth target set, and stopping the second processing step when there are no elements left in the sixth target set. The third edge can specifically be the edge connecting the non-target vertex and the target vertex in each second processing step. The updated fifth target set serves as the fifth target set in the next first processing step, and the updated sixth target set serves as the sixth target set in the next first processing step.

[0108] In this embodiment of the invention, the sixth target set can specifically be the set of all edges in the target undirected graph that are connected to at least one target vertex in the target vertex set during each first processing step.

[0109] In this embodiment of the invention, there are two conditions for stopping the first processing step: first, the sixth target set does not contain any element; second, the third target difference set does not contain a second edge.

[0110] In this embodiment of the invention, when the sixth target set does not contain any elements, the updated target vertex set is used as the vertices of the similar subgraph, and the updated fifth target set is used as the edges of the similar subgraph to construct the similar subgraph.

[0111] In this embodiment of the invention, if there is no second edge in the third target difference set, the first edge is used as the edge of the similar subgraph, and the target vertex corresponding to the first edge is used as the vertex of the similar subgraph to construct the similar subgraph.

[0112] For example, in step 1, the target text (e.g., a translation document) is segmented at a certain granularity to obtain n text unit objects corresponding to the target text;

[0113] Step 2: For n text unit objects, the text vector model is used to represent the n text unit objects as a vector expression to obtain n target objects. Among them, there are usually two types of vector expressions for text unit objects: one is the unsupervised method: obtaining a dense vector of its semantic expression through a deep neural network; the other is to obtain the independent features of the text through a supervised method and establish a sparse vector expression.

[0114] Step 3: For n text unit objects, establish a set S containing n target objects, where each target object in the set is a vector representation of each text unit object;

[0115] Step 4: Cluster the target object set S consisting of these n target objects to obtain k cluster centers, each cluster center corresponding to a centroid. This initial clustering can specifically use general clustering algorithms, such as K-means, DBSCAN, etc.

[0116] Step 5: Calculate pairwise distances between the n target objects:

[0117] Step 5.1: Calculate the distance from each target object in the target object set S to these k centroids. Specifically, this distance can be calculated using Euclidean distance, Manhattan distance, cosine similarity, or other distance calculation methods.

[0118] Step 5.2: Subtract the distances from each target object to the k centroids pairwise and take the absolute values. Sum these k absolute values ​​and take the average value as the relative distance between the two target objects.

[0119] Step 6: Denote the set S consisting of all target objects as the vertex set of the undirected graph G as V, and the set consisting of the relative distances between any two target objects as the edge set of the undirected graph G as E, thus obtaining the undirected graph G = (V, E).

[0120] Step 7: In the undirected graph G, delete all edges whose relative distance is greater than a preset threshold, and then delete isolated vertices to obtain the target undirected graph G_sim = (V_sim, E_sim), where V_sim is the set of all vertices of the target undirected graph G_sim, and E_sim is the set of all edges of the target undirected graph G_sim.

[0121] Step 8, construct the cluster set:

[0122] Step 8.1: Take the first edge with the smallest relative distance in E_sim, add the first edge to set E1, and add the vertex corresponding to the first edge to set V1;

[0123] Step 8.2: Find the set of all edges connecting vertices in V1 from the target undirected graph G_sim, denoted as E_tp;

[0124] Step 8.3: Calculate the difference between set E_tp and set E1, i.e. (E_tp–E1), and find the second edge with the smallest relative distance in the set of edges (E_tp–E1);

[0125] Step 8.3.1, if the second side exists:

[0126] Step 8.3.1.1: If the other vertex corresponding to the second edge (i.e., a vertex not in set V1) is connected to more than half of the vertices in set V1, then add the vertex not in set V1 to V1, and add the third edge connecting the vertex not in set V1 to all vertices in set V1 to set E1, then go to step 8.2.

[0127] Step 8.3.1.2, otherwise, remove the second edge from the set E_tp;

[0128] Step 8.3.1.3: If there are no elements in set E_tp, then set V1 is completed and proceed to step 9; otherwise, proceed to step 8.3.

[0129] Step 8.3.2: If the second side does not exist, then set V1 is completed, proceed to step 9;

[0130] Step 9: The similar subgraph G1 = (V1, E1) is the first maximum similar subgraph of the obtained target undirected graph, and its vertex set V1 is the set of target objects of the same class.

[0131] Step 10: If there are no elements in the difference set (V_sim–V1) between set V_sim and set V1, the algorithm ends; otherwise, (V_sim–V1, E_sim–E1) is used as a new undirected graph G, and the process proceeds to step 7.

[0132] Step 11: The text unit object corresponding to each maximum similarity subgraph is a high similarity set. Pushing text unit objects belonging to the same high similarity set to the same translator, or processing these texts uniformly, can ensure the consistency and uniformity of text translation for this set.

[0133] The text push method provided by this invention can group target objects of the same type together by splitting the preprocessed undirected graph into similar subgraphs, thereby avoiding the problem of clustering results deviating and improving the accuracy of clustering results.

[0134] The text push system provided by the present invention is described below. The text push system described below can be referred to in correspondence with the text push method described above.

[0135] Figure 2 This is a schematic diagram of the text push system provided by the present invention, as shown below. Figure 2 As shown, it includes:

[0136] The first acquisition module 200, the second acquisition module 210, and the text push module 220;

[0137] The first acquisition module 200 is used to obtain the aggregation result of the target object set, the target object set includes multiple text unit objects, the text unit objects are vector representations of the target objects, the target objects are obtained by segmenting the target text, and the aggregation result is used to characterize the similarity of each target object in the target set;

[0138] The second acquisition module 210 is used to acquire the high similarity set corresponding to each similar subgraph in the aggregation result, wherein the high similarity set corresponding to the similar subgraph includes the text unit object corresponding to the similar subgraph;

[0139] The text push module 220 is used to push the target text based on the text unit objects in the highly similar set.

[0140] The text push system provided by this invention treats the text unit objects corresponding to each similar subgraph in the aggregation result of the target object set as a highly similar set, which enables the target text to be pushed to the same user in a short time, ensuring the timeliness and accuracy of text push.

[0141] Figure 3 This is a schematic diagram of the physical structure of an electronic device provided by the present invention, such as... Figure 3 As shown, the electronic device may include a processor 310, a communication interface 311, a memory 312, and a bus 313, wherein the processor 310, the communication interface 311, and the memory 312 communicate with each other via the bus 313. The processor 310 can call logical instructions in the memory 312 to execute the following methods:

[0142] The aggregation result of the target object set is obtained. The target object set includes multiple text unit objects, each text unit object being a vector representation of a target object. The target object is obtained by segmenting the target text. The aggregation result is used to characterize the similarity of each target object in the target set.

[0143] Obtain the high similarity set corresponding to each similar subgraph in the aggregation result, wherein the high similarity set corresponding to the similar subgraph includes the text unit object corresponding to the similar subgraph;

[0144] The target text is pushed based on the text unit objects in the highly similar set.

[0145] Furthermore, the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, and can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer power supply (which may be a personal computer, server, or network power supply, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0146] Furthermore, this invention discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by a computer, the computer can execute the text push method provided in the above-described method embodiments, for example including:

[0147] The aggregation result of the target object set is obtained. The target object set includes multiple text unit objects, each text unit object being a vector representation of a target object. The target object is obtained by segmenting the target text. The aggregation result is used to characterize the similarity of each target object in the target set.

[0148] Obtain the high similarity set corresponding to each similar subgraph in the aggregation result, wherein the high similarity set corresponding to the similar subgraph includes the text unit object corresponding to the similar subgraph;

[0149] The target text is pushed based on the text unit objects in the highly similar set.

[0150] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the text push methods provided in the above embodiments, including, for example:

[0151] The aggregation result of the target object set is obtained. The target object set includes multiple text unit objects, each text unit object being a vector representation of a target object. The target object is obtained by segmenting the target text. The aggregation result is used to characterize the similarity of each target object in the target set.

[0152] Obtain the high similarity set corresponding to each similar subgraph in the aggregation result, wherein the high similarity set corresponding to the similar subgraph includes the text unit object corresponding to the similar subgraph;

[0153] The target text is pushed based on the text unit objects in the highly similar set.

[0154] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0155] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer power supply (which may be a personal computer, server, or network power supply, etc.) to execute the methods described in various embodiments or some parts of the embodiments.

[0156] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention 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; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A text push method, characterized in that, include: The aggregation result of the target object set is obtained. The target object set includes multiple target objects. The target object is a vector representation of a text unit object. The text unit object is obtained by segmenting the target text. The aggregation result is used to characterize the similarity of each target object in the target set. Obtain the high similarity set corresponding to each similar subgraph in the aggregation result, wherein the high similarity set corresponding to the similar subgraph includes the text unit object corresponding to the similar subgraph; The target text is pushed based on the text unit objects in the highly similar set; The methods for obtaining the aggregation result of the target object set include: Perform the aggregation process at least once until there are no elements left in the first target difference set; The aggregation result is obtained based on all similar subgraphs obtained in at least one of the aggregation processes. The aggregation process is used to obtain similar subgraphs corresponding to the target undirected graph. The first target difference set is the difference set between the first target set and the second target set. The first target set is determined based on the set of all vertices in the similar subgraphs obtained in each aggregation process. The second target set is determined based on the set of all vertices in the target undirected graph in each aggregation process. The step of obtaining the similar subgraphs corresponding to the target undirected graph includes: The set of the first edges with the smallest relative distance in the target undirected graph is taken as the fifth target set; The set of target vertices constituting the first side is taken as the target vertex set; Perform the first processing procedure at least once until there are no elements in the sixth target set or there is no second edge with the smallest relative distance in the third target difference set, and obtain the similar subgraph; The first processing procedure includes: if the second edge exists in the third target difference set, and if a preset condition is met, then the second processing procedure is executed at least once until the preset condition is not met, and the second edge is deleted from the sixth target set to update the sixth target set until there are no elements in the sixth target set. The third target difference set is the difference set between the fifth target set and the sixth target set in each of the first processing steps; The preset conditions include: in each of the first processing steps, the non-target vertices constituting the second side are connected to at least a preset number of target vertices in the target vertex set; The second processing procedure includes: adding a non-target vertex in the second edge as the target vertex to the target vertex set to update the target vertex set; adding a third edge to the latest fifth target set to update the fifth target set; and updating the sixth target set according to the updated target vertex set. The third edge is the edge connecting the non-target vertex and the target vertex in each second processing procedure. The updated fifth target set is used as the fifth target set in the next first processing procedure, and the updated sixth target set is used as the sixth target set in the next first processing procedure.

2. The text push method according to claim 1, characterized in that, The aggregation process includes: obtaining similar subgraphs corresponding to the target undirected graph; updating the undirected graph based on the first target difference set and the second target difference set; updating the target undirected graph according to the updated undirected graph; the updated undirected graph is used as the undirected graph in the next aggregation process; the updated target undirected graph is used as the target undirected graph in the next aggregation process; the target undirected graph in the first aggregation process is obtained based on the undirected graph in the first aggregation process; the undirected graph in the first aggregation process is constructed based on the target object set. The second target difference set is the difference set between the third target set and the fourth target set. The third target set is determined based on the set of all edges in the similar subgraphs obtained in each aggregation process, and the fourth target set is determined based on the set of all edges in the target undirected graph in each aggregation process.

3. The text push method according to claim 2, characterized in that, The methods for obtaining the target undirected graph include: Based on each of the target objects, determine the vertices of the undirected graph; Determine the edges of the undirected graph based on the relative distance between any two target objects; Construct the undirected graph based on its vertices and edges; Delete edges in the undirected graph that exceed a preset threshold, and delete isolated vertices in the undirected graph to obtain the target undirected graph.

4. The text push method according to claim 1, characterized in that, The step of obtaining the similar subgraph includes: If no element exists in the sixth target set, the similar subgraph is obtained based on the updated target vertex set and the updated fifth target set; If the second edge does not exist in the third target difference set, the similarity subgraph is obtained based on the first edge and the target vertex corresponding to the first edge.

5. The text push method according to claim 3, characterized in that, The method for obtaining the relative distance includes: Obtain the distance between any two target objects and each centroid, where the centroid is obtained after an initial clustering of the target object set; The relative distance is obtained based on the distance between any two target objects and each centroid.

6. The text push method according to claim 5, characterized in that, The step of obtaining the distance between any two target objects and each centroid includes: The distance is determined based on the Euclidean distance, Manhattan distance, or cosine similarity between any two target objects and each centroid.

7. A text push system, characterized in that, include: The module consists of a first acquisition module, a second acquisition module, and a text push module. The first acquisition module is used to obtain the aggregation result of the target object set, the target object set includes multiple text unit objects, the text unit objects are vector representations of the target objects, the target objects are obtained by segmenting the target text, and the aggregation result is used to characterize the similarity of each target object in the target set; The second acquisition module is used to acquire the high similarity set corresponding to each similar subgraph in the aggregation result, wherein the high similarity set corresponding to the similar subgraph includes the text unit object corresponding to the similar subgraph; The text push module is used to push the target text based on the text unit objects in the highly similar set; The methods for obtaining the aggregation result of the target object set include: Perform the aggregation process at least once until there are no elements left in the first target difference set; The aggregation result is obtained based on all similar subgraphs obtained in at least one of the aggregation processes. The aggregation process is used to obtain similar subgraphs corresponding to the target undirected graph. The first target difference set is the difference set between the first target set and the second target set. The first target set is determined based on the set of all vertices in the similar subgraphs obtained in each aggregation process. The second target set is determined based on the set of all vertices in the target undirected graph in each aggregation process. The step of obtaining the similar subgraphs corresponding to the target undirected graph includes: The set of the first edges with the smallest relative distance in the target undirected graph is taken as the fifth target set; The set of target vertices constituting the first side is taken as the target vertex set; Perform the first processing procedure at least once until there are no elements in the sixth target set or there is no second edge with the smallest relative distance in the third target difference set, and obtain the similar subgraph; The first processing procedure includes: if the second edge exists in the third target difference set, and if a preset condition is met, then the second processing procedure is executed at least once until the preset condition is not met, and the second edge is deleted from the sixth target set to update the sixth target set until there are no elements in the sixth target set. The third target difference set is the difference set between the fifth target set and the sixth target set in each of the first processing steps; The preset conditions include: in each of the first processing steps, the non-target vertices constituting the second side are connected to at least a preset number of target vertices in the target vertex set; The second processing procedure includes: adding a non-target vertex in the second edge as the target vertex to the target vertex set to update the target vertex set; adding a third edge to the latest fifth target set to update the fifth target set; and updating the sixth target set according to the updated target vertex set. The third edge is the edge connecting the non-target vertex and the target vertex in each second processing procedure. The updated fifth target set is used as the fifth target set in the next first processing procedure, and the updated sixth target set is used as the sixth target set in the next first processing procedure.

8. An electronic device comprising a processor and a memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the text push method according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the text push method as described in any one of claims 1 to 6.

Images