CN117033835A - Push information determining method and device - Google Patents
Push information determining method and device Download PDFInfo
- Publication number
- CN117033835A CN117033835A CN202210470283.0A CN202210470283A CN117033835A CN 117033835 A CN117033835 A CN 117033835A CN 202210470283 A CN202210470283 A CN 202210470283A CN 117033835 A CN117033835 A CN 117033835A
- Authority
- CN
- China
- Prior art keywords
- entity
- preference feature
- interest preference
- vector
- index tree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 239000013598 vector Substances 0.000 claims abstract description 388
- 230000003993 interaction Effects 0.000 claims abstract description 34
- 238000005192 partition Methods 0.000 claims description 65
- 238000013507 mapping Methods 0.000 claims description 23
- 238000010276 construction Methods 0.000 claims description 14
- 238000005070 sampling Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 5
- 238000003491 array Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9027—Trees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a push information determining method and a device, wherein the push information determining method comprises the following steps: acquiring historical entity resource interaction information of a plurality of entities; determining a plurality of first entity interest preference feature vectors based on the historical entity resource interaction information; constructing a target binary index tree based on the plurality of first entity interest preference feature vectors; searching in a target binary index tree based on the interest preference feature vector of the entity to be recommended to obtain a plurality of target entity interest preference feature vectors matched with the interest preference feature vector of the entity to be recommended; push information is determined based on the plurality of target entity interest preference feature vectors. The method and the device can improve the efficiency of determining the push information.
Description
Technical Field
The application mainly relates to the technical field of information push, in particular to a push information determining method and device.
Background
Information push is a new technology for reducing information overload by periodically transmitting information required by an entity on the internet through a certain technical standard or protocol. Push technology reduces the time for searching on a network by automatically transmitting information to an entity. It searches, filters, and pushes information to entities on a regular basis according to the interests of the entities, helping the entities to efficiently discover valuable information. However, the logistics scene is complex and changeable, the physical demands are quite different, different value-added service products are designed for different scenes, and the traditional information pushing mode has lower pushing efficiency due to larger data volume in the logistics scene.
That is, the efficiency of the push information determining method in the related art is low.
Disclosure of Invention
The application provides a push information determining method and device, and aims to solve the problem that the push information determining method in the prior art is low in efficiency.
In a first aspect, the present application provides a push information determining method, where the push information determining method includes:
acquiring historical entity resource interaction information of a plurality of entities;
determining a plurality of first entity interest preference feature vectors based on the historical entity resource interaction information, wherein the first entity interest preference vectors represent the probability of entity preference of various resources;
constructing a target binary index tree based on the plurality of first entity interest preference feature vectors;
searching in a target binary index tree based on the interest preference feature vector of the entity to be recommended to obtain a plurality of target entity interest preference feature vectors matched with the interest preference feature vector of the entity to be recommended;
push information is determined based on the plurality of target entity interest preference feature vectors.
Optionally, the constructing the target binary index tree based on the plurality of first entity interest preference feature vectors includes:
randomly sampling the interest preference feature vectors of the first entities to obtain interest preference feature vectors of the second entities;
Constructing a first binary index tree based on a plurality of second entity interest preference feature vectors;
mapping the plurality of first entity interest preference feature vectors to partition vector sets corresponding to all leaf nodes on the first binary index tree to obtain a second binary index tree;
the target binary index tree is determined based on a second binary index tree.
Optionally, the constructing a first binary index tree based on the plurality of second entity interest preference feature vectors includes:
acquiring a second mean value vector of the plurality of second entity interest preference feature vectors;
calculating a second average distance value of distances between the plurality of second entity interest preference feature vectors and the second average value vector;
determining a second average distance value of the plurality of second entity interest preference feature vectors as a root node;
bifurcating the root node into a left child node and a right child node, mapping a second entity interest preference feature vector with a distance value smaller than a second average distance value to a vector set corresponding to the left child node, and mapping a second entity interest preference feature vector with a distance value larger than the second average distance value to a vector set corresponding to the left child node;
And respectively taking the left child node and the right child node as root nodes to perform bifurcating to obtain vector sets corresponding to the nodes after bifurcating, wherein the vector quantity of the vector sets is smaller than a preset value, so as to obtain a first bifurcate index tree.
Optionally, the determining the target binary index tree based on the second binary index tree includes:
acquiring the vector quantity in the partition vector set corresponding to each leaf node on the second binary index tree;
bifurcating leaf nodes corresponding to the partition vector sets with the vector quantity larger than a preset value to obtain a second binary index tree after bifurcating;
when the number of vectors in the partition vector set corresponding to each leaf node in the second binary index tree after bifurcating is not larger than a preset value, determining the second binary index tree after bifurcating as a third binary index tree;
a target binary index tree is determined based on the third binary index tree.
Optionally, the determining the target binary index tree based on the third binary index tree includes:
mapping each first entity interest preference feature vector to two adjacent partition vector sets in the partition vector set in the third binary index tree to obtain a fourth binary index tree;
Calculating a fourth mean vector of each partition vector set in the fourth binary index tree;
calculating the distance value between each first entity interest preference feature vector and the fourth mean value vector in the partition vector set;
sorting each first entity interest preference feature vector in the partition vector set from large to small according to the distance value from the fourth mean vector in each partition vector set;
and removing the first entity interest preference feature vectors which are sequenced and positioned behind the preset value in each partition vector set in the fourth binary index tree to obtain a target binary index tree.
Optionally, the searching the preference feature vector of interest of the entity to be recommended based on the entity to be recommended in the target binary index tree to obtain a plurality of preference feature vectors of interest of the target entity matched with the preference feature vector of interest of the entity to be recommended includes:
acquiring an entity identifier of an entity to be recommended;
judging whether an interest preference feature vector of the entity to be recommended, which is matched with the entity identifier, exists in a cache database;
if the to-be-recommended entity interest preference feature vector matched with the entity identifier does not exist in the cache database, acquiring the to-be-recommended entity interest preference feature vector matched with the entity identifier from a storage database, and if the to-be-recommended entity interest preference feature vector matched with the entity identifier exists in the cache database, acquiring the to-be-recommended entity interest preference feature vector matched with the entity identifier from the cache database;
Searching in a target binary index tree based on the interest preference feature vector of the entity to be recommended to obtain a plurality of target entity interest preference feature vectors matched with the interest preference feature vector of the entity to be recommended.
Optionally, the determining a plurality of first entity interest preference feature vectors based on the historical entity resource interaction information includes:
constructing a first knowledge graph taking entities, hosts and resources as nodes based on the historical entity resource interaction information;
acquiring the occurrence probability of each node relation in the first knowledge graph;
removing node relations with occurrence probability lower than preset probability in the first knowledge graph to obtain a second knowledge graph;
and performing graph embedding on the second knowledge graph to obtain a plurality of first entity interest preference feature vectors.
In a second aspect, the present application provides a push information determining apparatus, including:
the acquisition unit is used for acquiring historical entity resource interaction information of a plurality of entities;
the first determining unit is used for determining a plurality of first entity interest preference feature vectors based on the historical entity resource interaction information, and the first entity interest preference vectors represent the probability of entity preference of various resources;
A construction unit, configured to construct a target binary index tree based on a plurality of first entity interest preference feature vectors;
the searching unit is used for searching in the target binary index tree based on the interest preference feature vector of the entity to be recommended to obtain a plurality of target entity interest preference feature vectors matched with the interest preference feature vector of the entity to be recommended;
and the second determining unit is used for determining pushing information based on the interest preference feature vectors of the plurality of target entities.
Optionally, the construction unit is configured to:
randomly sampling the interest preference feature vectors of the first entities to obtain interest preference feature vectors of the second entities;
constructing a first binary index tree based on a plurality of second entity interest preference feature vectors;
mapping the plurality of first entity interest preference feature vectors to partition vector sets corresponding to all leaf nodes on the first binary index tree to obtain a second binary index tree;
the target binary index tree is determined based on a second binary index tree.
Optionally, the construction unit is configured to:
acquiring a second mean value vector of the plurality of second entity interest preference feature vectors;
calculating a second average distance value of distances between the plurality of second entity interest preference feature vectors and the second average value vector;
Determining a second average distance value of the plurality of second entity interest preference feature vectors as a root node;
bifurcating the root node into a left child node and a right child node, mapping a second entity interest preference feature vector with a distance value smaller than a second average distance value to a vector set corresponding to the left child node, and mapping a second entity interest preference feature vector with a distance value larger than the second average distance value to a vector set corresponding to the left child node;
and respectively taking the left child node and the right child node as root nodes to perform bifurcating to obtain vector sets corresponding to the nodes after bifurcating, wherein the vector quantity of the vector sets is smaller than a preset value, so as to obtain a first bifurcate index tree.
Optionally, the construction unit is configured to:
acquiring the vector quantity in the partition vector set corresponding to each leaf node on the second binary index tree;
bifurcating leaf nodes corresponding to the partition vector sets with the vector quantity larger than a preset value to obtain a second binary index tree after bifurcating;
when the number of vectors in the partition vector set corresponding to each leaf node in the second binary index tree after bifurcating is not larger than a preset value, determining the second binary index tree after bifurcating as a third binary index tree;
A target binary index tree is determined based on the third binary index tree.
Optionally, the construction unit is configured to:
mapping each first entity interest preference feature vector to two adjacent partition vector sets in the partition vector set in the third binary index tree to obtain a fourth binary index tree;
calculating a fourth mean vector of each partition vector set in the fourth binary index tree;
calculating the distance value between each first entity interest preference feature vector and the fourth mean value vector in the partition vector set;
sorting each first entity interest preference feature vector in the partition vector set from large to small according to the distance value from the fourth mean vector in each partition vector set;
and removing the first entity interest preference feature vectors which are sequenced and positioned behind the preset value in each partition vector set in the fourth binary index tree to obtain a target binary index tree.
Optionally, the search unit is configured to:
acquiring an entity identifier of an entity to be recommended;
judging whether an interest preference feature vector of the entity to be recommended, which is matched with the entity identifier, exists in a cache database;
if the to-be-recommended entity interest preference feature vector matched with the entity identifier does not exist in the cache database, acquiring the to-be-recommended entity interest preference feature vector matched with the entity identifier from a storage database, and if the to-be-recommended entity interest preference feature vector matched with the entity identifier exists in the cache database, acquiring the to-be-recommended entity interest preference feature vector matched with the entity identifier from the cache database;
Searching in a target binary index tree based on the interest preference feature vector of the entity to be recommended to obtain a plurality of target entity interest preference feature vectors matched with the interest preference feature vector of the entity to be recommended.
Optionally, the acquiring unit is configured to:
constructing a first knowledge graph taking entities, hosts and resources as nodes based on the historical entity resource interaction information;
acquiring the occurrence probability of each node relation in the first knowledge graph;
removing node relations with occurrence probability lower than preset probability in the first knowledge graph to obtain a second knowledge graph;
and performing graph embedding on the second knowledge graph to obtain a plurality of first entity interest preference feature vectors.
In a third aspect, the present application provides a computer apparatus comprising:
one or more processors;
a memory; and
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the push information determining method of any of the first aspects.
In a fourth aspect, the present application provides a computer readable storage medium storing a plurality of instructions adapted to be loaded by a processor for performing the steps of the push information determining method of any one of the first aspects.
The application provides a push information determining method and a device, wherein the push information determining method comprises the following steps: acquiring historical entity resource interaction information of a plurality of entities; determining a plurality of first entity interest preference feature vectors based on the historical entity resource interaction information; constructing a target binary index tree based on the plurality of first entity interest preference feature vectors; searching in a target binary index tree based on the interest preference feature vector of the entity to be recommended to obtain a plurality of target entity interest preference feature vectors matched with the interest preference feature vector of the entity to be recommended; push information is determined based on the plurality of target entity interest preference feature vectors. Under the condition that the efficiency of the pushing information determining method is low in the prior art, the pushing information determining method is creatively provided, first entity interest preference feature vectors of all entities are determined according to historical shopping behavior information of a large number of entities, then the first entity interest preference feature vectors are built into target binary index trees, when a new entity to be recommended needs to be recommended for resource recommendation, the target binary index trees are directly used for searching a plurality of target entity interest preference feature vectors matched with the entity to be recommended interest preference feature vectors, information related to the entity to be recommended can be quickly searched in the large number of information, and pushing information determination is carried out according to the target entity interest preference feature vectors, so that the pushing information determining efficiency can be improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic view of a scenario of a push information determining system according to an embodiment of the present application;
FIG. 2 is a flow chart of an embodiment of a method for determining push information in an embodiment of the present application;
fig. 3 is a schematic diagram of a first knowledge graph in a push information determining method according to an embodiment of the present application;
fig. 4 is a schematic diagram of a network structure embedded in the graph in the push information determining method according to an embodiment of the present application;
fig. 5 is a schematic diagram of a target binary index tree in a method for determining push information according to an embodiment of the present application;
FIG. 6 is a schematic structural diagram of an embodiment of a push information determining apparatus provided in an embodiment of the present application;
FIG. 7 is a schematic diagram of an embodiment of a computer device provided in an embodiment of the application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.
In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate orientations or positional relationships based on the drawings are merely for convenience in describing the present application and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present application. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more features. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the present application, the term "exemplary" is used to mean "serving as an example, instance, or illustration. Any embodiment described as "exemplary" in this disclosure is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the application. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present application may be practiced without these specific details. In other instances, well-known structures and processes have not been described in detail so as not to obscure the description of the application with unnecessary detail. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
The embodiment of the application provides a push information determining method and device, which are respectively described in detail below.
Referring to fig. 1, fig. 1 is a schematic view of a scenario of a push information determining system according to an embodiment of the present application, where the push information determining system may include a computer device 100, and a push information determining apparatus is integrated in the computer device 100.
In the embodiment of the present application, the computer device 100 may be an independent server, or may be a server network or a server cluster formed by servers, for example, the computer device 100 described in the embodiment of the present application includes, but is not limited to, a computer, a network host, a single network server, a plurality of network server sets, or a cloud server formed by a plurality of servers. Wherein the Cloud server is composed of a large number of computers or web servers based on Cloud Computing (Cloud Computing).
In the embodiment of the present application, the computer device 100 may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device 100 may be a desktop, a portable computer, a network server, a palm computer (Personal Digital Assistant, PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, an embedded device, etc., and the embodiment is not limited to the type of the computer device 100.
It will be appreciated by those skilled in the art that the application environment shown in fig. 1 is only one application scenario of the present application, and is not limited to the application scenario of the present application, and other application environments may further include more or fewer computer devices than those shown in fig. 1, for example, only 1 computer device is shown in fig. 1, and it will be appreciated that the push information determining system may further include one or more other computer devices capable of processing data, which is not limited herein.
In addition, as shown in fig. 1, the push information determining system may further include a memory 200 for storing data.
It should be noted that, the schematic view of the scenario of the push information determining system shown in fig. 1 is only an example, and the push information determining system and the scenario described in the embodiments of the present application are for more clearly describing the technical solution of the embodiments of the present application, and do not constitute a limitation on the technical solution provided by the embodiments of the present application, and as one of ordinary skill in the art can know, along with the evolution of the push information determining system and the appearance of a new service scenario, the technical solution provided by the embodiments of the present application is equally applicable to similar technical problems.
Firstly, in the embodiment of the application, a push information determining method is provided, and the push information determining method includes: acquiring historical entity resource interaction information of a plurality of entities; determining a plurality of first entity interest preference feature vectors based on the historical entity resource interaction information; constructing a target binary index tree based on the plurality of first entity interest preference feature vectors; searching in a target binary index tree based on the interest preference feature vector of the entity to be recommended to obtain a plurality of target entity interest preference feature vectors matched with the interest preference feature vector of the entity to be recommended; push information is determined based on the plurality of target entity interest preference feature vectors.
As shown in fig. 2, fig. 2 is a flowchart of an embodiment of a push information determining method according to an embodiment of the present application, where the push information determining method includes steps S201 to S205 as follows:
s201, acquiring historical entity resource interaction information of a plurality of entities.
The historical entity resource interaction information includes that the entity purchased a resource when receiving a posting. For example, entity u1 purchases resource i1 when hosting mailpiece c 1. Specifically, the historical entity resource interaction information of the plurality of entities is the historical entity resource interaction information of the plurality of entities in a preset period, and the preset period can be one month, two months and the like of history according to specific settings. It should be noted that, the history entity resource interaction information is obtained in a legal and reasonable manner, and personal information is encrypted during data processing.
S202, determining a plurality of first entity interest preference feature vectors based on historical entity resource interaction information.
In a specific embodiment, determining a plurality of first entity interest preference feature vectors based on historical entity resource interaction information may include:
(1) And constructing a first knowledge graph taking the entity, the consignment and the resource as nodes based on the historical entity resource interaction information.
As shown in fig. 3, in the first knowledge graph of fig. 3, users represent Entities, cargos represent brackets, items represent resources, and enties represent attributes of the resources. r represents the node relation among the nodes, r1 represents a mailpiece, and r3 represents a purchase. For example, entity u1 purchases resource i1 when hosting mailpiece c 1. In the first knowledge graph, the node relation between the entity u1 and the supporting object c1 is a supporting object r1, and the node relation between the supporting object c1 and the resource i1 is an additional purchase r3.
(2) And obtaining the occurrence probability of each node relation in the first knowledge graph.
(3) And removing the node relation with the occurrence probability lower than the preset probability in the first knowledge graph to obtain a second knowledge graph.
Because of the existence of the multi-hop relation, the number of the higher-order relations is increased sharply and the contribution to different resources is very unbalanced, the node relation with the occurrence probability lower than the preset probability in the first knowledge graph is removed, the second knowledge graph is obtained, the node relation with the low weight value in the first knowledge graph can be cut off, and the second knowledge graph with smaller data quantity is obtained. And the subsequent calculation efficiency is improved.
(4) And performing graph embedding on the second knowledge graph to obtain a plurality of first entity interest preference feature vectors.
The purpose of graph embedding is to map each node in a given graph into a low-dimensional vector representation (or node embedding in general) that typically retains some of the critical information of the node in the original graph. Nodes in the graph can be viewed from two domains: 1) An original graph domain in which nodes are connected by edges (or graph structures); 2) An embedded domain, wherein each node is represented as a continuous vector.
As shown in fig. 4, fig. 4 is a schematic diagram of the network architecture of the embedding of fig. 4. In a specific embodiment, the second knowledge-graph input graph is embedded into a network to obtain a plurality of first entity interest preference feature vectors. The graph embedded network may be a GCN, SDNE, or the like.
S203, constructing a target binary index tree based on the plurality of first entity interest preference feature vectors.
As shown in fig. 5, fig. 5 is a binary index tree. Binary index trees, also called number state arrays, have an array in their memory structure, but a tree in their logical structure. It is contemplated that when stacking, we use array inventory, but it is logically a complete binary tree. Node 5 is the root node, nodes 2 and 8 are the left and right children of node 5, respectively, and nodes 1, 3 and 7 are leaf nodes. Leaf nodes are generally referred to as leaf nodes. The leaf nodes of the index refer to the data blocks forming the bottommost layer of the B-tree index, wherein the sorted index column values and rowid of the record where the column values are located are stored, and the index column values are arranged in an ascending order by default. Leaf nodes are concepts among discrete mathematics. Nodes without child nodes (i.e., degree 0) in a tree are called leaf nodes, and are called "leaves" for short. Leaves refer to nodes with a degree of 0, also known as end nodes.
In a particular embodiment, a first mean vector of a plurality of first entity interest preference feature vectors is obtained. The first mean vector is an average value of the plurality of first entity interest preference feature vectors, and of course, the first mean vector may also be a cluster center obtained by clustering the plurality of first entity interest preference feature vectors. Calculating a first average distance value of distances between the plurality of first entity interest preference feature vectors and the first mean vector; the distance between vectors may be Manhattan distance, chebyshev distance, mahalanobis distance, etc. Determining a first average distance value of the plurality of second entity interest preference feature vectors as a root node; bifurcating the root node into a left child node and a right child node, mapping a first entity interest preference feature vector with a distance value smaller than a first average distance value to a vector set corresponding to the left child node, and mapping a first entity interest preference feature vector with a distance value larger than the first average distance value to a vector set corresponding to the right child node; and respectively taking the left child node and the right child node as root nodes to perform bifurcating to obtain vector sets corresponding to the bifurcated nodes, wherein the vector quantity of the vector sets is smaller than a preset value, so as to obtain a target binary index tree. The preset value K may be set according to a specific situation.
If the target binary index tree is directly constructed by using the plurality of first entity interest preference feature vectors, the data size is too large, and the construction speed of the target binary index tree is slow, in order to improve the construction speed, in another specific embodiment, constructing the target binary index tree based on the plurality of first entity interest preference feature vectors includes:
(1) And randomly sampling the interest preference feature vectors of the first entities to obtain interest preference feature vectors of the second entities.
The number of second entity interest preference feature vectors is lower than the number of first entity interest preference feature vectors. The sampling proportion of random sampling can be 0.1, 0.2, etc., and can be set according to specific situations.
(2) A first binary index tree is constructed based on the plurality of second entity interest preference feature vectors.
In a particular embodiment, a second mean vector of a plurality of second entity interest preference feature vectors is obtained. The second mean vector is an average value of the plurality of second entity interest preference feature vectors, and of course, the second mean vector may also be a cluster center obtained by clustering the plurality of second entity interest preference feature vectors. Calculating a second average distance value of distances between the plurality of second entity interest preference feature vectors and the second average value vector; the distance between vectors may be Manhattan distance, chebyshev distance, mahalanobis distance, etc. Determining a second average distance value of the plurality of second entity interest preference feature vectors as a root node; bifurcating the root node into a left child node and a right child node, mapping a second entity interest preference feature vector with a distance value smaller than a second average distance value to a vector set corresponding to the left child node, and mapping a second entity interest preference feature vector with a distance value larger than the second average distance value to a vector set corresponding to the right child node; and respectively taking the left child node and the right child node as root nodes to perform bifurcating to obtain vector sets corresponding to the nodes after bifurcating, wherein the vector quantity of the vector sets is smaller than a preset value, so as to obtain a first bifurcate index tree. The preset value K may be set according to a specific situation.
(3) Mapping the plurality of first entity interest preference feature vectors to partition vector sets corresponding to all leaf nodes on the first binary index tree to obtain a second binary index tree.
In a specific embodiment, distance values of the first entity interest preference feature vectors and third mean vectors of the partition vector sets corresponding to the leaf nodes on the first binary index tree are calculated respectively, and the first entity interest preference feature vectors are mapped to the partition vector sets corresponding to the third mean vectors with the highest distance values.
(4) A target binary index tree is determined based on the second binary index tree.
In a specific embodiment, determining the target binary index tree based on the second binary index tree includes: the second binary index tree is determined to be the target binary index tree. The construction efficiency can be improved by constructing a basic first binary index tree by using a small amount of second entity interest preference feature vectors and then mapping a large amount of first entity interest preference feature vectors to leaf nodes of the first binary index tree.
To improve the accuracy of the target binary index tree, in another specific embodiment, determining the target binary index tree based on the second binary index tree includes:
(1) And obtaining the vector quantity in the partition vector set corresponding to each leaf node on the second binary index tree.
(2) And bifurcating the leaf nodes corresponding to the partition vector sets with the vector quantity larger than the preset value to obtain a second binary index tree after bifurcating.
The number of vectors in the partition vector set is larger than a preset value K, which indicates that the partition data volume is too large, and the constructed second binary index tree is unbalanced and needs to be bifurcated again.
(3) And when the number of vectors in the partition vector set corresponding to each leaf node in the second binary index tree after bifurcating is not larger than a preset value, determining the second binary index tree after bifurcating as a third binary index tree.
And when the number of vectors in the partition vector set corresponding to each leaf node in the second binary index tree after bifurcating is not greater than a preset value K, indicating that the second binary index tree is already bifurcated to an equilibrium state, and determining the second binary index tree after bifurcating as a third binary index tree.
When the partitioned vector sets with the vector quantity larger than the preset value K exist in the second binary index tree after bifurcating, the second binary index tree is indicated not to be bifurcate to an equilibrium state, and the leaf nodes corresponding to the partitioned vector sets with the vector quantity larger than the preset value K are bifurcate again.
(4) A target binary index tree is determined based on the third binary index tree.
In a specific embodiment, determining the target binary index tree based on the third binary index tree includes: the third binary index tree is determined to be the target binary index tree.
In another specific embodiment, to further improve accuracy of the target binary index tree, ensuring that the set of vectors corresponding to the same leaf node includes the most similar vector, determining the target binary index tree based on the third binary index tree includes:
(1) And mapping each first entity interest preference feature vector to two adjacent partition vector sets in the partition vector set in the third binary index tree to obtain a fourth binary index tree.
All first entity interest preference feature vectors are mapped into the partition where the first entity interest preference feature vectors are located and the adjacent partitions according to the inter-vector distance, namely each vector is mapped into three partitions.
(2) A fourth mean vector for each set of partition vectors in a fourth binary index tree is calculated.
(3) And calculating the distance value between each first entity interest preference feature vector and the fourth mean vector in the partition vector set.
(4) And ordering each first entity interest preference feature vector in the partition vector set from large to small according to the distance value from the fourth mean vector in each partition vector set.
(5) And removing the first entity interest preference feature vectors which are sequenced and positioned behind the preset value in each partition vector set in the fourth binary index tree to obtain a target binary index tree.
Namely, each partition vector set in the fourth binary index tree sorts and rejects the first entity interest preference feature vectors positioned behind the preset value K, and each partition vector set only keeps the first entity interest preference feature vectors of the preset value K.
S204, searching in a target binary index tree based on the interest preference feature vector of the entity to be recommended, and obtaining a plurality of target entity interest preference feature vectors matched with the interest preference feature vector of the entity to be recommended.
In a specific embodiment, searching in a target binary index tree based on interest preference feature vectors of entities to be recommended of the entities to be recommended to obtain a plurality of target entity interest preference feature vectors matched with the interest preference feature vectors of the entities to be recommended, including:
(1) And acquiring the entity identification of the entity to be recommended.
The entity identification may be an entity handset number, a login account, etc.
(2) And judging whether the to-be-recommended entity interest preference feature vector matched with the entity identifier exists in the cache database.
Specifically, the cache database is a Redis cache. Redis is a type of in-memory cache database. And reading the interest preference feature vector of the entity to be recommended, which is matched with the entity identifier, from the cache database, so that the speed of acquiring the interest preference feature vector of the entity to be recommended can be improved.
(3) If the preference feature vector of the to-be-recommended entity interest matched with the entity identifier does not exist in the cache database, the preference feature vector of the to-be-recommended entity interest matched with the entity identifier is obtained from the storage database, and if the preference feature vector of the to-be-recommended entity interest matched with the entity identifier exists in the cache database, the preference feature vector of the to-be-recommended entity interest matched with the entity identifier is obtained from the cache database.
Wherein the storage database is Hbase. The amount of data stored in the database is greater than the amount of data stored in the cache database. The data reading speed of the storage database is smaller than the data reading speed of the cache database.
(4) Searching in a target binary index tree based on the interest preference feature vector of the entity to be recommended to obtain a plurality of target entity interest preference feature vectors matched with the interest preference feature vector of the entity to be recommended.
In a specific embodiment, searching is performed in a target binary index tree based on interest preference feature vectors of entities to be recommended of the entities to be recommended, so as to obtain a plurality of target entity interest preference feature vectors matched with the interest preference feature vectors of the entities to be recommended. Specifically, whether the distance value between the interest preference feature vector of the entity to be recommended and the mean value vector corresponding to the root node is smaller than a first average distance value is judged, if yes, searching is conducted on the left child node corresponding to the root node, and if not, searching is conducted on the right child node corresponding to the root node. After the left child node or the right child node is determined, searching again by taking the left child node or the right child node as a root node, and determining a plurality of first entity interest preference feature vectors corresponding to the leaf nodes as a plurality of target entity interest preference feature vectors matched with the entity interest preference feature vectors to be recommended when the leaf nodes of the target binary index tree are searched.
S205, pushing information is determined based on the interest preference feature vectors of the target entities.
In a specific embodiment, a plurality of interest preference feature vectors of the target entity are input into a preset ordering model to obtain a plurality of resources, and the plurality of resources are pushed to the entity as push information. Specifically, resource information of a plurality of resources is sent to a browser of an entity. The method comprises the steps that a preset sorting model is obtained through training according to a preset training set, the preset training set comprises a plurality of training samples, the training samples comprise a plurality of first entity interest preference feature vectors and corresponding sample labels, and the sample labels are resources corresponding to a plurality of first historical entity product features. The preset ranking model may be lightGBM.
In order to better implement the push information determining method in the embodiment of the present application, on the basis of the push information determining method, the embodiment of the present application further provides a push information determining apparatus, as shown in fig. 6, where the push information determining apparatus 300 includes:
an obtaining unit 301, configured to obtain historical entity resource interaction information of a plurality of entities;
a first determining unit 302, configured to determine a plurality of first entity interest preference feature vectors based on the historical entity resource interaction information;
A construction unit 303, configured to construct a target binary index tree based on a plurality of first entity interest preference feature vectors;
the searching unit 304 is configured to search in the target binary index tree based on the preference feature vector of the to-be-recommended entity interest of the to-be-recommended entity, to obtain a plurality of preference feature vectors of the target entity interest that are matched with the preference feature vector of the to-be-recommended entity interest;
the second determining unit 305 is configured to determine push information based on the multiple target entity interest preference feature vectors.
Optionally, the construction unit 303 is configured to:
randomly sampling the interest preference feature vectors of the first entities to obtain interest preference feature vectors of the second entities;
constructing a first binary index tree based on a plurality of second entity interest preference feature vectors;
mapping the plurality of first entity interest preference feature vectors into partition vector sets corresponding to all leaf nodes on the first binary index tree to obtain a second binary index tree;
a target binary index tree is determined based on the second binary index tree.
Optionally, the construction unit 303 is configured to:
acquiring a second mean value vector of the plurality of second entity interest preference feature vectors;
calculating a second average distance value of distances between the plurality of second entity interest preference feature vectors and the second average value vector;
Determining a second average distance value of the plurality of second entity interest preference feature vectors as a root node;
bifurcating the root node into a left child node and a right child node, mapping a second entity interest preference feature vector with a distance value smaller than a second average distance value to a vector set corresponding to the left child node, and mapping a second entity interest preference feature vector with a distance value larger than the second average distance value to a vector set corresponding to the left child node;
and respectively taking the left child node and the right child node as root nodes to perform bifurcating to obtain vector sets corresponding to the nodes after bifurcating, wherein the vector quantity of the vector sets is smaller than a preset value, so as to obtain a first bifurcate index tree.
Optionally, the construction unit 303 is configured to:
acquiring the vector quantity in the partition vector set corresponding to each leaf node on the second binary index tree;
bifurcating leaf nodes corresponding to the partition vector sets with the vector quantity larger than a preset value to obtain a second binary index tree after bifurcating;
when the number of vectors in the partition vector set corresponding to each leaf node in the second binary index tree after bifurcating is not larger than a preset value, determining the second binary index tree after bifurcating as a third binary index tree;
A target binary index tree is determined based on the third binary index tree.
Optionally, the construction unit 303 is configured to:
mapping each first entity interest preference feature vector to two adjacent partition vector sets in the partition vector set in the third binary index tree to obtain a fourth binary index tree;
calculating a fourth mean vector of each partition vector set in the fourth binary index tree;
calculating the distance value between each first entity interest preference feature vector and the fourth mean value vector in the partition vector set;
sorting each first entity interest preference feature vector in the partition vector set from large to small according to the distance value from the fourth mean vector in each partition vector set;
and removing the first entity interest preference feature vectors which are sequenced and positioned behind the preset value in each partition vector set in the fourth binary index tree to obtain a target binary index tree.
Optionally, the searching unit 304 is configured to:
acquiring an entity identifier of an entity to be recommended;
judging whether an entity interest preference feature vector to be recommended, which is matched with the entity identifier, exists in the cache database;
if the to-be-recommended entity interest preference feature vector matched with the entity identifier does not exist in the cache database, acquiring the to-be-recommended entity interest preference feature vector matched with the entity identifier from the storage database, and if the to-be-recommended entity interest preference feature vector matched with the entity identifier exists in the cache database, acquiring the to-be-recommended entity interest preference feature vector matched with the entity identifier from the cache database;
Searching in a target binary index tree based on the interest preference feature vector of the entity to be recommended to obtain a plurality of target entity interest preference feature vectors matched with the interest preference feature vector of the entity to be recommended.
Optionally, the obtaining unit 301 is configured to:
constructing a first knowledge graph taking entities, hosts and resources as nodes based on historical entity resource interaction information;
acquiring the occurrence probability of each node relation in the first knowledge graph;
removing node relations with occurrence probability lower than preset probability in the first knowledge graph to obtain a second knowledge graph;
and performing graph embedding on the second knowledge graph to obtain a plurality of first entity interest preference feature vectors.
The embodiment of the application also provides a computer device, which integrates any of the pushing information determining devices provided by the embodiment of the application, and the computer device comprises:
one or more processors;
a memory; and
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to perform the steps in the push information determination method in any of the push information determination method embodiments described above.
As shown in fig. 7, a schematic structural diagram of a computer device according to an embodiment of the present application is shown, specifically:
the computer device may include one or more processors 401 of a processing core, memory 402 of one or more computer readable storage media, a power supply 403, and an input unit 404, among other components. It will be appreciated by those skilled in the art that the computer device structure shown in the figures is not limiting of the computer device and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components. Wherein:
the processor 401 is a control center of the computer device, connects various parts of the entire computer device using various interfaces and lines, and performs various functions of the computer device and processes data by running or executing software programs and/or modules stored in the memory 402, and calling data stored in the memory 402, thereby performing overall monitoring of the computer device. Optionally, processor 401 may include one or more processing cores; the processor 401 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, and preferably, the processor 401 may integrate an application processor, which primarily handles operating systems, user interfaces, application programs, and the like, with a modem processor, which primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 401.
The memory 402 may be used to store software programs and modules, and the processor 401 executes various functional applications and data processing by executing the software programs and modules stored in the memory 402. The memory 402 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the computer device, etc. In addition, memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.
The computer device further comprises a power supply 403 for supplying power to the various components, preferably the power supply 403 may be logically connected to the processor 401 by a power management system, so that functions of charge, discharge, and power consumption management may be performed by the power management system. The power supply 403 may also include one or more of any of a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.
The computer device may also include an input unit 404, which input unit 404 may be used to receive input numeric or character information and to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.
Although not shown, the computer device may further include a display unit or the like, which is not described herein. In particular, in this embodiment, the processor 401 in the computer device loads executable files corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and the processor 401 executes the application programs stored in the memory 402, so as to implement various functions as follows:
acquiring historical entity resource interaction information of a plurality of entities; determining a plurality of first entity interest preference feature vectors based on the historical entity resource interaction information; constructing a target binary index tree based on the plurality of first entity interest preference feature vectors; searching in a target binary index tree based on the interest preference feature vector of the entity to be recommended to obtain a plurality of target entity interest preference feature vectors matched with the interest preference feature vector of the entity to be recommended; push information is determined based on the plurality of target entity interest preference feature vectors.
Those of ordinary skill in the art will appreciate that all or a portion of the steps of the various methods of the above embodiments may be performed by instructions, or by instructions controlling associated hardware, which may be stored in a computer-readable storage medium and loaded and executed by a processor.
To this end, an embodiment of the present application provides a computer-readable storage medium, which may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like. The method for determining the push information comprises the steps of storing a computer program, wherein the computer program is loaded by a processor to execute any step in the method for determining the push information. For example, the loading of the computer program by the processor may perform the steps of:
acquiring historical entity resource interaction information of a plurality of entities; determining a plurality of first entity interest preference feature vectors based on the historical entity resource interaction information; constructing a target binary index tree based on the plurality of first entity interest preference feature vectors; searching in a target binary index tree based on the interest preference feature vector of the entity to be recommended to obtain a plurality of target entity interest preference feature vectors matched with the interest preference feature vector of the entity to be recommended; push information is determined based on the plurality of target entity interest preference feature vectors.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and the portions of one embodiment that are not described in detail in the foregoing embodiments may be referred to in the foregoing detailed description of other embodiments, which are not described herein again.
In the implementation, each unit or structure may be implemented as an independent entity, or may be implemented as the same entity or several entities in any combination, and the implementation of each unit or structure may be referred to the foregoing method embodiments and will not be repeated herein.
The specific implementation of each operation above may be referred to the previous embodiments, and will not be described herein.
The foregoing describes in detail a method and apparatus for determining push information provided by the embodiments of the present application, and specific examples are applied to illustrate the principles and embodiments of the present application, where the foregoing description of the embodiments is only for helping to understand the method and core idea of the present application; meanwhile, as those skilled in the art will vary in the specific embodiments and application scope according to the ideas of the present application, the present description should not be construed as limiting the present application in summary.
Claims (10)
1. The push information determining method is characterized by comprising the following steps:
Acquiring historical entity resource interaction information of a plurality of entities;
determining a plurality of first entity interest preference feature vectors based on the historical entity resource interaction information, wherein the first entity interest preference vectors represent the probability of entity preference of various resources;
constructing a target binary index tree based on the plurality of first entity interest preference feature vectors;
searching in a target binary index tree based on the interest preference feature vector of the entity to be recommended to obtain a plurality of target entity interest preference feature vectors matched with the interest preference feature vector of the entity to be recommended;
push information is determined based on the plurality of target entity interest preference feature vectors.
2. The push information determining method of claim 1, wherein the constructing a target binary index tree based on the plurality of first entity interest preference feature vectors comprises:
randomly sampling the interest preference feature vectors of the first entities to obtain interest preference feature vectors of the second entities;
constructing a first binary index tree based on a plurality of second entity interest preference feature vectors;
mapping the plurality of first entity interest preference feature vectors to partition vector sets corresponding to all leaf nodes on the first binary index tree to obtain a second binary index tree;
The target binary index tree is determined based on a second binary index tree.
3. The push information determining method of claim 2, wherein the constructing a first binary index tree based on the plurality of second entity interest preference feature vectors comprises:
acquiring a second mean value vector of the plurality of second entity interest preference feature vectors;
calculating a second average distance value of distances between the plurality of second entity interest preference feature vectors and the second average value vector;
determining a second average distance value of the plurality of second entity interest preference feature vectors as a root node;
bifurcating the root node into a left child node and a right child node, mapping a second entity interest preference feature vector with a distance value smaller than a second average distance value to a vector set corresponding to the left child node, and mapping a second entity interest preference feature vector with a distance value larger than the second average distance value to a vector set corresponding to the right child node;
and respectively taking the left child node and the right child node as root nodes to perform bifurcating to obtain vector sets corresponding to the nodes after bifurcating, wherein the vector quantity of the vector sets is smaller than a preset value, so as to obtain a first bifurcate index tree.
4. The push information determination method of claim 2, wherein the determining the target binary index tree based on the second binary index tree comprises:
acquiring the vector quantity in the partition vector set corresponding to each leaf node on the second binary index tree;
bifurcating leaf nodes corresponding to the partition vector sets with the vector quantity larger than a preset value to obtain a second binary index tree after bifurcating;
when the number of vectors in the partition vector set corresponding to each leaf node in the second binary index tree after bifurcating is not larger than a preset value, determining the second binary index tree after bifurcating as a third binary index tree;
a target binary index tree is determined based on the third binary index tree.
5. The push information determining method of claim 4, wherein the determining a target binary index tree based on the third binary index tree comprises:
mapping each first entity interest preference feature vector to two adjacent partition vector sets in the partition vector set in the third binary index tree to obtain a fourth binary index tree;
calculating a fourth mean vector of each partition vector set in the fourth binary index tree;
Calculating the distance value between each first entity interest preference feature vector and the fourth mean value vector in the partition vector set;
sorting each first entity interest preference feature vector in the partition vector set from large to small according to the distance value from the fourth mean vector in each partition vector set;
and removing the first entity interest preference feature vectors which are sequenced and positioned behind the preset value in each partition vector set in the fourth binary index tree to obtain a target binary index tree.
6. The push information determining method according to claim 1, wherein the searching the target binary index tree based on the preference feature vector of interest of the entity to be recommended to obtain a plurality of preference feature vectors of interest of the target entity matching the preference feature vector of interest of the entity to be recommended includes:
acquiring an entity identifier of an entity to be recommended;
judging whether an interest preference feature vector of the entity to be recommended, which is matched with the entity identifier, exists in a cache database;
if the to-be-recommended entity interest preference feature vector matched with the entity identifier does not exist in the cache database, acquiring the to-be-recommended entity interest preference feature vector matched with the entity identifier from a storage database, and if the to-be-recommended entity interest preference feature vector matched with the entity identifier exists in the cache database, acquiring the to-be-recommended entity interest preference feature vector matched with the entity identifier from the cache database;
Searching in a target binary index tree based on the interest preference feature vector of the entity to be recommended to obtain a plurality of target entity interest preference feature vectors matched with the interest preference feature vector of the entity to be recommended.
7. The push information determining method of claim 1, wherein the determining a plurality of first entity interest preference feature vectors based on the historical entity resource interaction information comprises:
constructing a first knowledge graph taking entities, hosts and resources as nodes based on the historical entity resource interaction information;
acquiring the occurrence probability of each node relation in the first knowledge graph;
removing node relations with occurrence probability lower than preset probability in the first knowledge graph to obtain a second knowledge graph;
and performing graph embedding on the second knowledge graph to obtain a plurality of first entity interest preference feature vectors.
8. A push information determining device, characterized in that the push information determining device comprises:
the acquisition unit is used for acquiring historical entity resource interaction information of a plurality of entities;
the first determining unit is used for determining a plurality of first entity interest preference feature vectors based on the historical entity resource interaction information, and the first entity interest preference vectors represent the probability of entity preference of various resources;
A construction unit, configured to construct a target binary index tree based on a plurality of first entity interest preference feature vectors;
the searching unit is used for searching in the target binary index tree based on the interest preference feature vector of the entity to be recommended to obtain a plurality of target entity interest preference feature vectors matched with the interest preference feature vector of the entity to be recommended;
and the second determining unit is used for determining pushing information based on the interest preference feature vectors of the plurality of target entities.
9. A computer device, the computer device comprising:
one or more processors;
a memory; and
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the push information determining method of any of claims 1 to 7.
10. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program is loaded by a processor to perform the steps in the push information determining method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210470283.0A CN117033835A (en) | 2022-04-28 | 2022-04-28 | Push information determining method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210470283.0A CN117033835A (en) | 2022-04-28 | 2022-04-28 | Push information determining method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117033835A true CN117033835A (en) | 2023-11-10 |
Family
ID=88641718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210470283.0A Pending CN117033835A (en) | 2022-04-28 | 2022-04-28 | Push information determining method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117033835A (en) |
-
2022
- 2022-04-28 CN CN202210470283.0A patent/CN117033835A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106484875B (en) | MOLAP-based data processing method and device | |
| WO2018041168A1 (en) | Information pushing method, storage medium and server | |
| US7711735B2 (en) | User segment suggestion for online advertising | |
| CA3059929C (en) | Text searching method, apparatus, and non-transitory computer-readable storage medium | |
| CN107895038B (en) | Link prediction relation recommendation method and device | |
| CN112115227B (en) | Data query method and device, electronic equipment and storage medium | |
| CN106844407B (en) | Tag network generation method and system based on data set correlation | |
| CN108021708B (en) | Content recommendation method and device and computer readable storage medium | |
| CN110322318B (en) | Client grouping method, device and computer storage medium | |
| CN111651641B (en) | Graph query method, device and storage medium | |
| CN112434188A (en) | Data integration method and device for heterogeneous database and storage medium | |
| CN109460398A (en) | Complementing method, device and the electronic equipment of time series data | |
| CN115905630A (en) | Graph database query method, device, equipment and storage medium | |
| CN111582967A (en) | Content search method, device, equipment and storage medium | |
| CN111737461B (en) | Text processing method and device, electronic equipment and computer readable storage medium | |
| CN110503117A (en) | The method and apparatus of data clusters | |
| CN110851708B (en) | Negative sample extraction method, device, computer equipment and storage medium | |
| CN109961163A (en) | Gender prediction's method, apparatus, storage medium and electronic equipment | |
| CN113761311A (en) | Information retrieval method, device, server and readable storage medium | |
| CN117033835A (en) | Push information determining method and device | |
| CN108596412A (en) | Cross-cutting methods of marking and Marking apparatus based on user's similarity | |
| CN108388652B (en) | Method and device for sending song list identification | |
| CN113761305B (en) | Method and device for generating label hierarchical structure | |
| CN112561412B (en) | Method, device, server and storage medium for determining target object identifier | |
| CN113327154A (en) | E-commerce user message pushing method and system based on big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |