CN112650862B - Method and device for constructing interest network, electronic equipment and computer storage medium - Google Patents
Method and device for constructing interest network, electronic equipment and computer storage medium Download PDFInfo
- Publication number
- CN112650862B CN112650862B CN202011456721.5A CN202011456721A CN112650862B CN 112650862 B CN112650862 B CN 112650862B CN 202011456721 A CN202011456721 A CN 202011456721A CN 112650862 B CN112650862 B CN 112650862B
- Authority
- CN
- China
- Prior art keywords
- node
- user interaction
- interaction information
- nodes
- interest network
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000003993 interaction Effects 0.000 claims abstract description 197
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000007704 transition Effects 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
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
- G06F16/435—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/9024—Graphs; Linked lists
-
- 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
- G06F16/906—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
The application provides a method and a device for constructing an interest network, electronic equipment and a computer storage medium, wherein the method comprises the following steps: acquiring a plurality of user interaction information, and analyzing the user interaction information to obtain an entity indicated by the user interaction information and a guest group flow between the entities indicated by the user interaction information; then, each entity indicated by the user interaction information is used as a node of the interest network, and the connection relationship between two nodes of the interest network is established by utilizing the guest group flow between the entities indicated by the user interaction information; finally, the weight of each node in the interest network is calculated, and the weight of the connection relationship between two nodes having the connection relationship in the interest network is calculated. And a final interest network is obtained, and the purpose of accurately recommending the entities possibly liked by the user to the user can be achieved by using the interest network.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method and an apparatus for constructing an interest network, an electronic device, and a computer storage medium.
Background
At present, personalized recommendation is performed on different users and entities such as commodities, shops, videos and the like which the users possibly like, and in the matching process, comprehensive and accurate interest depiction is required to be performed on the users.
In the personalized recommendation method, user preference is predicted according to historical browsing data or current browsing data of a user, entities such as commodities, shops and videos which are possibly interested in the user are predicted, and then recommendation is performed to the user through terminal equipment and the like.
However, this way of determining the recommending entity has the following problems: the browsing data of the user cannot directly reflect the real preference of the user, and has certain unilateral property.
Disclosure of Invention
In view of the foregoing, the present application provides a method, an apparatus, an electronic device, and a computer storage medium for constructing an interest network, which are used for accurately recommending entities that a user may like to the user.
In order to achieve the above purpose, the embodiment of the present application provides the following technical solutions:
the first aspect of the present application provides a method for constructing an interest network, including:
acquiring a plurality of pieces of user interaction information, wherein each piece of user interaction information is used for indicating that a user has interaction behavior on one entity in a target scene;
Analyzing the user interaction information to obtain an entity indicated by the user interaction information and a group flow between the entities indicated by the user interaction information, wherein the group flow is used for explaining that after a user has interaction behavior with one entity in the target scene, the user has interaction behavior with the other entity in the target scene;
each entity indicated by the user interaction information is used as a node of an interest network, and a connection relation between two nodes of the interest network is established by utilizing the guest group flow between the entities indicated by the user interaction information, wherein the connection relation between the two nodes of the interest network represents the guest group flow between the entities corresponding to the two nodes;
and calculating the weight of each node in the interest network, and calculating the weight of the connection relation between two nodes with the connection relation in the interest network.
Optionally, the calculating the weight of each node in the interest network includes:
respectively counting and indicating the user interaction information of the entity corresponding to each node in the interest network from the acquired plurality of user interaction information;
And calculating the weight of each node in the interest network by using the user interaction information of the entity corresponding to each node obtained through statistics.
Optionally, the calculating the weight of each node in the interest network by using the user interaction information of the entity corresponding to each node obtained through statistics includes:
aiming at each node in the interest network, classifying the user interaction information of the entity corresponding to each node according to the classification standard of the user interaction information to obtain the user interaction information under each class;
and calculating the weighted value of the quantity of the user interaction information of each node in the interest network under each category, and taking the sum of the weighted values of the quantity of the user interaction information of each node in the interest network under each category as the weight of each node in the interest network.
Optionally, the calculating the weight of the connection relationship between two nodes having the connection relationship in the interest network includes:
determining the connection direction of the two nodes with the connection relationship by using a target guest group flow, wherein the target guest group flow refers to: in the group flow between the entities indicated by the user interaction information, the group flow between the entities corresponding to the two nodes with the connection relationship is included;
And calculating the weight of the connection relation of the two nodes with the connection relation in the determined connection direction.
Optionally, the calculating the weight of the connection relationship between the two nodes with the connection relationship in the determined connection direction includes:
identifying an amount of traffic flowing in a direction from a first node to a second node from among traffic flowing between the first node and the second node, the first node referring to one of the two nodes having a connection relationship, the second node referring to the other of the two nodes having a connection relationship, the first node to the second node referring to the determined connection direction;
and taking the total quantity of the group flows from the first node to the second node, and the ratio of the total quantity of the group flows from the first node to the neighbor node as the weight in the direction from the first node to the second node, wherein the neighbor node refers to the node with a connection relation with the first node.
Optionally, the calculating the weight of the connection relationship between the two nodes with the connection relationship in the determined connection direction includes:
Identifying, in a traffic flow between a first node and a second node, an amount of traffic flow in a direction from the first node to the second node, the first node referring to one of the two nodes having a connection relationship, the second node referring to the other of the two nodes having a connection relationship, the first node to the second node referring to the determined connection direction;
classifying the identified quantity of the guest group flowing in the direction from the first node to the second node according to the classification standard of the guest group flowing to obtain the quantity of the guest group flowing under each category;
calculating a weighted value of the amount of the group flow under each category from each node to the second node;
taking the ratio of the sum of weighted values of the amounts of the group flows of the first node to the second node under each category to the sum of weighted values of the amounts of the group flows of the first node to the neighbor node under each category as the weight of the first node to the second node, wherein the neighbor node refers to the node with the connection relation with the first node.
A second aspect of the present application provides a device for constructing an interest network, including:
The system comprises an acquisition unit, a target scene and a display unit, wherein the acquisition unit is used for acquiring a plurality of user interaction information, and each user interaction information is used for indicating that a user has interaction behavior on one entity in the target scene;
the analysis unit is used for analyzing the user interaction information to obtain an entity indicated by the user interaction information and a group flow between the entities indicated by the user interaction information, wherein the group flow is used for explaining that after the user has interaction behavior with one entity in the target scene, the user has interaction behavior with the other entity in the target scene;
the establishing unit is used for taking each entity indicated by the user interaction information as one node of the interest network, and establishing a connection relationship between two nodes of the interest network by utilizing the guest group flow between the entities indicated by the user interaction information, wherein the connection relationship between the two nodes of the interest network represents the guest group flow between the entities corresponding to the two nodes;
a first calculation unit for calculating a weight of each node in the interest network;
and the second calculation unit is used for calculating the weight of the connection relation between the two nodes with the connection relation in the interest network.
Optionally, the first computing unit includes:
the statistics unit is used for respectively counting and indicating the user interaction information of the entity corresponding to each node in the interest network from the acquired plurality of user interaction information;
and the first calculating subunit is used for calculating the weight of each node in the interest network by using the user interaction information of the entity corresponding to each node obtained through statistics.
Optionally, the first computing subunit includes:
the first classification unit is used for classifying the user interaction information of the entity corresponding to each node according to the category classification standard of the user interaction information aiming at each node in the interest network to obtain the user interaction information under each category;
a node weight calculation unit, configured to calculate a weighted value of the amount of user interaction information under each category for each node in the interest network, and take a sum of weighted values of the amounts of user interaction information under each category for each node in the interest network as a weight for each node in the interest network.
Optionally, the second computing unit includes:
a determining unit, configured to determine a connection direction of the two nodes having a connection relationship by using a target group flow, where the target group flow refers to: in the group flow between the entities indicated by the user interaction information, the group flow between the entities corresponding to the two nodes with the connection relationship is included;
And the second calculating subunit is used for calculating the weight of the connection relation of the two nodes with the connection relation in the determined connection direction.
Optionally, the second computing subunit includes:
a first identifying unit configured to identify, from among a group flow between a first node that refers to one of the two nodes having a connection relationship and a second node that refers to the other of the two nodes having a connection relationship, an amount of the group flow in a direction from the first node to the second node, the first node to the second node referring to the determined connection direction;
and the calculation unit of the weight of the first connection relation is used for taking the total quantity of the group flow from the first node to the second node, the ratio of the total quantity of the group flow from the first node to the neighbor node as the weight of the first node to the second node, and the neighbor node refers to the node with the connection relation with the first node.
Optionally, the second computing subunit includes:
a second identifying unit configured to identify, in a group flow between a first node and a second node, an amount of the group flow in a direction from the first node to the second node, the first node referring to one of the two nodes having a connection relationship, the second node referring to the other of the two nodes having a connection relationship, the first node to the second node referring to the determined connection direction;
The second classification unit is used for classifying the identified quantity of the group flow in the direction from the first node to the second node according to the classification standard of the group flow to obtain the quantity of the group flow under each class;
a weight calculation unit for calculating a weight of the amount of group flow under each category from the each node to the second node;
and a calculation unit of the weight of the first connection relation is used for taking the duty ratio of the sum of the weighted values of the amount of the guest group flowing under each category from the first node to the second node and the weighted value of the sum of the weighted values from the first node to the neighbor node as the weight of the first node to the second node, wherein the neighbor node refers to the node with the connection relation with the first node.
A third aspect of the present application provides an electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of the first aspects of the present application.
A fourth aspect of the present application provides a computer readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a method according to any of the first aspects of the present application.
As can be seen from the above solutions, in a method, an apparatus, an electronic device, and a computer storage medium for constructing an interest network provided in the present application, the construction method includes: obtaining a plurality of user interaction information, analyzing the user interaction information, and obtaining an entity indicated by the user interaction information and a guest group flow between the entities indicated by the user interaction information, wherein the guest group flow is used for explaining that after a user has interaction behavior with one entity in a target scene, the guest group flow has interaction behavior with the other entity in the target scene; then, each entity indicated by the user interaction information is used as one node of the interest network, and the connection relation between two nodes of the interest network is established by utilizing the guest group flow between the entities indicated by the user interaction information, wherein the connection relation between the two nodes of the interest network represents the guest group flow between the entities corresponding to the two nodes; finally, the weight of each node in the interest network is calculated, and the weight of the connection relationship between two nodes having the connection relationship in the interest network is calculated. And a final interest network is obtained, and the purpose of accurately recommending the entities possibly liked by the user to the user can be achieved by using the interest network.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a specific flowchart of a method for constructing an interest network according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a network of interest according to another embodiment of the present application;
FIG. 3 is a specific flowchart of a method for constructing an interest network according to an embodiment of the present application;
FIG. 4 is a specific flowchart of a method for constructing an interest network according to an embodiment of the present application;
FIG. 5 is a specific flowchart of a method for constructing an interest network according to an embodiment of the present application;
FIG. 6 is a specific flowchart of a method for constructing an interest network according to an embodiment of the present application;
FIG. 7 is a specific flowchart of a method for constructing an interest network according to an embodiment of the present application;
FIG. 8 is a schematic diagram of a device for constructing a network of interest according to an embodiment of the present disclosure;
Fig. 9 is a schematic diagram of an electronic device for implementing a method for constructing an interest network according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present invention 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 invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that the terms "first," "second," and the like in this application are used merely to distinguish between different devices, modules, or units and are not intended to limit the order or interdependence of functions performed by such devices, modules, or units, but the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but also other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The embodiment of the application provides a method for constructing an interest network, as shown in fig. 1, specifically including the following steps:
s101, acquiring a plurality of user interaction information.
Each piece of user interaction information is used for indicating that a user has interaction behavior on one entity in a target scene. An entity may be understood as a material presented to a user, for example: stores in electronic commerce, commodities in stores, videos in streaming media, content in news and the like. The interaction behavior is a user behavior generated by a user on an entity, and can be, but is not limited to, collection, browsing, praying, purchasing, clicking, and the like. The user interaction information may include: entity identification of the entity of the user interaction and interaction behavior identification of the user, wherein the interaction behavior identification is used for explaining the type of the interaction behavior of the user.
It should be noted that, the user interaction information may be offline interaction information or online interaction information, which is not limited herein. The manner of acquiring the user interaction information may be real-time statistics of the user interaction information, or may be acquiring historical data of the user interaction information, or may simultaneously acquire the historical data of the user interaction information and real-time statistics of the user interaction information, which is not limited herein.
S102, analyzing the user interaction information to obtain the entity indicated by the user interaction information and the group flow between the entities indicated by the user interaction information.
The group flow is used for explaining that after a user has interaction with one entity u in the target scene, the user has interaction with another entity v in the target scene, and is defined as traffic (u→v).
For example: after the user has interaction with the commodity A in the store, the user has interaction with commodities such as the commodity B, the commodity C and the like; or after the user has interaction with store A in the electronic commerce, the user has interaction with stores B, C and the like in the electronic commerce.
S103, each entity indicated by the user interaction information is used as one node of the interest network, and the connection relationship between two nodes of the interest network is established by using the group flow between the entities indicated by the user interaction information.
The connection relation between two nodes of the interest network represents the group flow between the entities corresponding to the two nodes.
Referring to fig. 2, a schematic diagram of an interest network is shown, wherein numerals in circles represent labels of entities corresponding to nodes in the interest network, and links between circles represent a group flow between two entities.
It should be noted that the group flows in the interest network have an asymmetry, and that the interest network is a directed network. For example: each node in the interest network represents a store, and the number of users who travel to store 8 after the interaction occurs in store 1 is not necessarily equal to the number of users who travel to store 1 after the interaction occurs in store 8.
S104, calculating the weight of each node in the interest network and calculating the weight of the connection relation between two nodes with the connection relation in the interest network.
The weight of the node is used for indicating the importance degree of the node in the whole interest network; the physical meaning of the weight of the connection relationship between two nodes with the connection relationship is to count the transition probability of the group flow in the interest network.
Specifically, according to the obtained user interaction information, the weight of each node in the current interest network is calculated, and the weight of the connection relationship between two nodes with the connection relationship in the interest network is calculated. After the weight of each node in the current interest network is calculated, and the weight of the connection relation between all the two nodes with the connection relation in the interest network is calculated, the establishment of the interest network is completed.
It should be noted that, the weight of each node in the interest network may be obtained not only by calculation through obtaining the obtained user interaction information, but also according to various ranking settings of each node in the current interest network, and may be, but not limited to, the current popularity ranking, sales ranking, and the like. For example: the node with the first current popularity rank is given a weight of 1.0, the node with the second current popularity rank is given a weight of 0.8, the node with the third current popularity rank is given a weight of 0.7, etc.
According to the method for constructing the interest network, the plurality of user interaction information is obtained, and the user interaction information is analyzed, so that the entity indicated by the user interaction information and the guest group flow between the entities indicated by the user interaction information are obtained, wherein the guest group flow is used for explaining that after the user has interaction with one entity in a target scene, the guest group flow has interaction with the other entity in the target scene; then, each entity indicated by the user interaction information is used as one node of the interest network, and the connection relation between two nodes of the interest network is established by utilizing the guest group flow between the entities indicated by the user interaction information, wherein the connection relation between the two nodes of the interest network represents the guest group flow between the entities corresponding to the two nodes; finally, the weight of each node in the interest network is calculated, and the weight of the connection relationship between two nodes having the connection relationship in the interest network is calculated. And a final interest network is obtained, and the purpose of accurately recommending the entities possibly liked by the user to the user can be achieved by using the interest network.
Optionally, in another embodiment of the present application, an implementation of calculating the weight of each node in the interest network in step S104, as shown in fig. 3, includes:
s301, respectively counting the number of the user interaction information of the entity corresponding to each node in the interest network from the acquired plurality of user interaction information.
Specifically, the number of user interaction information indicating the entity corresponding to each node in the interest network may be counted according to the entity identifier in the user interaction information.
For example: referring to fig. 2, from the acquired multiple pieces of user interaction information, interaction information of the entity corresponding to each node in fig. 2 is obtained through statistics, for example: the node 1 obtains 13 pieces of user interaction information, the node 8 obtains 7 pieces of user interaction information, and the like.
S302, calculating the weight of each node in the interest network by using the user interaction information of the entity corresponding to each node obtained through statistics.
The weight may be assigned to each node according to the percentage of the number of user interaction information obtained by each node to the number of user interaction information obtained by all nodes.
For example: the quantity of the user interaction information acquired by the node 1 accounts for 10% of the quantity of the user interaction information acquired by all the nodes, and then a weight of 0.1 is distributed for the node 1; the number of the obtained user interaction information obtained by the node 2 accounts for 20% of the number of the obtained user interaction information obtained by all the nodes, and then the weight of 0.2 is distributed for the node 1.
If the type of the interaction behavior of the user on the entity is not unique, the following embodiment may be used to calculate the weight of each node in the interest network. In another embodiment of the present application, an implementation of step S302, as shown in fig. 4, includes:
s401, aiming at each node in the interest network, classifying the user interaction information of the entity corresponding to each aimed node according to the classification standard of the user interaction information to obtain the user interaction information under each category.
The classification criteria of the user interaction information may be, but are not limited to, classification according to praise, collection, browsing, etc., which is not limited herein.
Specifically, the number of the user interaction information of each entity is counted according to the entity identification in the user interaction information, and then the user interaction information of each entity is classified by utilizing the interaction behavior identification in the user interaction information, so that the number of the user interaction information with small categories indicated by the interaction behavior identification is obtained.
For example: classifying each piece of user interaction information obtained from the node 1 in the interest network in fig. 2 according to the interaction behavior identifier in the user interaction information, for example: praise 3 times, collect 1 time, browse 11 times, etc.
S402, calculating a weighted value of the quantity of the user interaction information of each node in the interest network under each category, and taking the sum of the weighted values of the quantity of the user interaction information of each node in the interest network under each category as the weight of each node in the interest network.
The weighting values of the user interaction information of different categories may be the same or different, for example: the weight of one praise is 0.5, the weight of one collection is 0.8, the weight of one browse is 0.1, etc.
Taking the example that the weight value of one praise is 0.5, the weight value of one collection is 0.8 and the weight value of one browse is 0.1, when the node 1 obtains praise 3 times, collects 1 time and browses 11 times, the weight of the node is as follows: 0.1×11+0.5×3+0.8×1=3.4.
Optionally, in another embodiment of the present application, an implementation of calculating the weight of the connection relationship between two nodes having the connection relationship in the interest network in step S104, as shown in fig. 5, includes:
s501, determining the connection direction of two nodes with a connection relationship by using the target group flow.
Wherein, the target group of guests flows refers to: in the group flow between the entities indicated by the user interaction information, the group flow between the entities corresponding to the two nodes with the connection relationship is included.
Specifically, the user interaction information includes an entity identifier and a user behavior identifier, and may also include a timestamp of the user interaction behavior on the entity, so that each piece of user interaction information can be used to identify which entity the user generates the interaction behavior on and the occurrence time of the user interaction on the entity. And analyzing the obtained user interaction information by analyzing, and analyzing the user interaction information belonging to the same user. Aiming at the user behavior information of each user, according to the time stamp in the user interaction information, the sequence of the entities of which the user generates the interaction behavior is obtained, and the two entities before and after the user generates the interaction behavior have guest group flow. The front entity and the rear entity of the interactive behavior of the user respectively correspond to one node of the interest network, the two nodes have a connection relationship, and the sequence from the former entity to the latter entity is the connection direction between the two nodes with the connection relationship.
S502, calculating the weight of the connection relation of the two nodes with the connection relation in the determined connection direction.
Specifically, the weight of the connection relation in the determined connection direction is calculated according to the guest group flow between the entities corresponding to the two nodes with the connection relation.
Optionally, in another embodiment of the present application, an implementation of step S502, as shown in fig. 6, includes:
s601, identifying the amount of the group flow in the direction from the first node to the second node from the group flow between the first node and the second node.
Wherein the first node refers to one of two nodes having a connection relationship, the second node refers to the other of the two nodes having a connection relationship, and the first node to the second node refer to the determined connection direction.
S602, taking the total quantity of the group flow from the first node to the second node and the ratio of the total quantity of the group flow from the first node to the neighbor node as the weight in the direction from the first node to the second node.
Wherein, the neighbor node refers to a node having a connection relationship with the first node.
Let u denote the first node, v denote the second node, traffic (u→v) denote the amount of traffic flowing from the first node to the second node, nb (u) denote the set of all neighbor nodes connected to the first node, t denote the weights in the neighbor nodes, and p (u→v) denote the weights in the direction from the first node to the second node. Then, the weight in the direction from the first node to the second node is calculated by:
If the type of the amount of the group flow is not unique, two nodes with connection relations are calculated, and when the weight of the connection relation in the determined connection direction is determined, the following manner provided by the embodiment can be selected. In another embodiment of the present application, an implementation of step S502, as shown in fig. 7, includes:
s701, identifying an amount of traffic flowing in a direction from the first node to the second node in traffic flowing between the first node and the second node.
Wherein the first node refers to one of two nodes having a connection relationship, the second node refers to the other of the two nodes having a connection relationship, and the first node to the second node refer to the determined connection direction.
S702, classifying the identified quantity of the group flow in the direction from the first node to the second node according to the classification standard of the group flow to obtain the quantity of the group flow under each category.
The classification criteria of the group flow may be according to the amount of group flow with purchasing behavior, the amount of group flow with collecting behavior, and the like.
For example: the amount of the group flow with purchasing behavior in the group flow in the direction from the first node to the second node is 3 times, the amount of the group flow with collecting behavior is 18 times, and the like.
S703, calculating a weighted value of the amount of the group flow from each node to the second node under each category.
The weighting values of the group flows of different categories may be the same or different, for example: the weight value of the group flow with purchasing behavior from the first node to the second node is 0.3, the weight value of the group flow with collecting behavior is 0.1, and the like.
Taking the example that the weighted value of the first node to the second node for the group flow with purchasing behavior is 0.3 and the weighted value of the first node to the second node for the group flow with collecting behavior is 0.1, when the amount of the group flow with purchasing behavior in the direction from the first node to the second node is 3 times and the amount of the group flow with collecting behavior is 18 times, the weighted value of the first node to the second node for the group flow with purchasing behavior is: 0.3×3=0.9; the weighted value of the amount of group flow in the collectable behavior from the first node to the second node is: 0.1×18=1.8.
S704, taking the ratio of the sum of weighted values of the amounts of the group flows under each category from the first node to the second node, as the weight in the direction from the first node to the second node.
Wherein, the neighbor node refers to a node having a connection relationship with the first node.
Taking the example that the weighted value of the group flow with purchasing behavior from the first node to the second node is 0.3 and the weighted value of the group flow with collecting behavior from the first node to the second node is 0.1, when the amount of the group flow with purchasing behavior in the group flow with purchasing behavior from the first node to the second node is 3 times and the amount of the group flow with collecting behavior is 18 times, the sum of the weighted values of the amounts of the group flows from the first node to the second node under each category is: 0.1×18+0.3×3=2.7.
Also, a first node is denoted by x, a second node is denoted by y,traffic i (x→y) represents the amount of group flow under i categories from the first node to the second node; a, a i A weight value representing the class i; traffic ic h (x→t) represents the amount of group flow under i categories representing the first node to t node; b i A weight value representing the class i; a, a i ＝b i The method comprises the steps of carrying out a first treatment on the surface of the traffic (x→y) represents a summary of the amount of traffic flow of all classes weighted in the first node to the second node, nb (x) represents a set of all neighbor nodes connected to the first node, t represents a neighbor node, p (x→y) represents a weight in the direction of the first node to the second node, wherein traffic (x→y) = Σ i a i *traffic i (x→y)；traffic(x→t)＝∑ i b i *traffic i (x→t); then, the weight in the direction from the first node to the second node is calculated by:
another embodiment of the present application provides a device for constructing an interest network, as shown in fig. 8, specifically including:
an obtaining unit 801, configured to obtain a plurality of user interaction information.
Each piece of user interaction information is used for indicating that a user has interaction behavior on one entity in a target scene.
The parsing unit 802 is configured to parse the user interaction information to obtain an entity indicated by the user interaction information and a group stream between the entities indicated by the user interaction information.
The group flow is used for explaining that after the user has interaction with one entity in the target scene, the user has interaction with the other entity in the target scene.
The establishing unit 803 is configured to use each entity indicated by the user interaction information as one node of the interest network, and establish a connection relationship between two nodes of the interest network by using a group flow between entities indicated by the user interaction information.
The connection relation between two nodes of the interest network represents the group flow between the entities corresponding to the two nodes.
A first calculating unit 804, configured to calculate a weight of each node in the interest network.
A second calculation unit 805 for calculating a weight of a connection relationship between two nodes having a connection relationship in the interest network.
The specific working process of the unit disclosed in the foregoing embodiments of the present application may refer to the content of the corresponding method embodiment, as shown in fig. 1, which is not repeated herein.
Optionally, in another embodiment of the present application, an implementation of the first computing unit 804 includes:
and the statistics unit is used for respectively counting the user interaction information of the entity corresponding to each node in the interest network from the acquired plurality of user interaction information.
And the first calculating subunit is used for calculating the weight of each node in the interest network by using the user interaction information of the entity corresponding to each node obtained through statistics.
The specific working process of the unit disclosed in the foregoing embodiments of the present application may refer to the content of the corresponding method embodiment, as shown in fig. 3, which is not described herein again.
Optionally, in another embodiment of the present application, an implementation of the first computing subunit includes:
the first classification unit is used for classifying the user interaction information of the entity corresponding to each node according to the category classification standard of the user interaction information aiming at each node in the interest network to obtain the user interaction information under each category.
And a node weight calculation unit for calculating a weighted value of the amount of user interaction information under each category for each node in the interest network, and taking the sum of weighted values of the amounts of user interaction information under each category for each node in the interest network as the weight of each node in the interest network.
The specific working process of the unit disclosed in the foregoing embodiments of the present application may refer to the content of the corresponding method embodiment, as shown in fig. 4, which is not described herein again.
Optionally, in another embodiment of the present application, an implementation of the second computing unit 805 includes:
and the determining unit is used for determining the connection direction of the two nodes with the connection relationship by utilizing the target group flow.
Wherein, the target group of guests flows refers to: in the group flow between the entities indicated by the user interaction information, the group flow between the entities corresponding to the two nodes with the connection relationship is included.
And the second calculating subunit is used for calculating the weight of the connection relation of the two nodes with the connection relation in the determined connection direction.
The specific working process of the unit disclosed in the foregoing embodiments of the present application may refer to the content of the corresponding method embodiment, as shown in fig. 5, which is not described herein again.
Optionally, in another embodiment of the present application, an implementation of the second computing subunit includes:
and the first identification unit is used for identifying the quantity of the group flow in the direction from the first node to the second node from the group flow between the first node and the second node.
Wherein the first node refers to one of two nodes having a connection relationship, the second node refers to the other of the two nodes having a connection relationship, and the first node to the second node refer to the determined connection direction.
And the calculation unit of the weight of the first connection relation is used for taking the total quantity of the group flow from the first node to the second node, the ratio of the total quantity of the group flow from the first node to the neighbor node as the weight in the direction from the first node to the second node.
Wherein, the neighbor node refers to a node having a connection relationship with the first node.
The specific working process of the unit disclosed in the foregoing embodiments of the present application may refer to the content of the corresponding method embodiment, as shown in fig. 6, which is not described herein again.
Optionally, in another embodiment of the present application, an implementation of the second computing subunit includes:
and the second identification unit is used for identifying the quantity of the group flow in the direction from the first node to the second node in the group flow between the first node and the second node.
Wherein the first node refers to one of two nodes having a connection relationship, the second node refers to the other of the two nodes having a connection relationship, and the first node to the second node refer to the determined connection direction.
And the second classification unit is used for classifying the identified quantity of the group flow in the direction from the first node to the second node according to the classification standard of the group flow to obtain the quantity of the group flow under each class.
And the weighted value calculation unit is used for calculating weighted values of the quantity of the group flow from each node to the second node under each category.
And the calculation unit of the weight of the first connection relation is used for taking the duty ratio of the sum of weighted values of the quantity of the guest group flow under each category from the first node to the second node as the weight of the first node to the second node.
Wherein, the neighbor node refers to a node having a connection relationship with the first node.
The specific working process of the unit disclosed in the foregoing embodiments of the present application may refer to the content of the corresponding method embodiment, as shown in fig. 7, which is not described herein again.
As can be seen from the above solution, in the device for constructing an interest network provided by the present application, the acquiring unit 801 acquires a plurality of pieces of user interaction information, the analyzing unit 802 analyzes the user interaction information, so as to obtain an entity indicated by the user interaction information, and a guest group flow between the entities indicated by the user interaction information, where the guest group flow is used for explaining that after a user has an interaction with one entity in a target scene, the guest group flow has an interaction with another entity in the target scene; then, the establishing unit 803 uses each entity indicated by the user interaction information as one node of the interest network, and establishes a connection relationship between two nodes of the interest network by using the guest group flow between the entities indicated by the user interaction information, wherein the connection relationship between the two nodes of the interest network represents the guest group flow between the entities corresponding to the two nodes; finally, the first calculation unit 804 calculates the weight of each node in the interest network, and the second calculation unit 805 calculates the weight of the connection relationship between two nodes having the connection relationship in the interest network. And a final interest network is obtained, and the purpose of accurately recommending the entities possibly liked by the user to the user can be achieved by using the interest network.
Another embodiment of the present application provides an electronic device, as shown in fig. 9, including:
one or more processors 901.
A storage 902, on which one or more programs are stored.
The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method as in any of the embodiments above.
Another embodiment of the present application provides a computer readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a method according to any of the above embodiments.
In the above embodiments of the disclosure, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus and method embodiments described above are merely illustrative, for example, flow diagrams and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in various embodiments of the present disclosure may be integrated together to form a single portion, or each module may exist alone, or two or more modules may be integrated to form a single portion. The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present disclosure may be embodied in essence or a part contributing to the prior art or a part of the technical solution, or in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a live device, or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present disclosure. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Those skilled in the art can make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for constructing an interest network, comprising:
acquiring a plurality of pieces of user interaction information, wherein each piece of user interaction information is used for indicating that a user has interaction behavior on one entity in a target scene;
analyzing the user interaction information to obtain an entity indicated by the user interaction information and a group flow between the entities indicated by the user interaction information, wherein the group flow is used for explaining that after a user has interaction behavior with one entity in the target scene, the user has interaction behavior with the other entity in the target scene;
each entity indicated by the user interaction information is used as a node of an interest network, and a connection relation between two nodes of the interest network is established by utilizing the guest group flow between the entities indicated by the user interaction information, wherein the connection relation between the two nodes of the interest network represents the guest group flow between the entities corresponding to the two nodes;
and calculating the weight of each node in the interest network, and calculating the weight of the connection relation between two nodes with the connection relation in the interest network.
2. The method of claim 1, wherein said calculating the weight of each node in the network of interest comprises:
respectively counting and indicating the user interaction information of the entity corresponding to each node in the interest network from the acquired plurality of user interaction information;
and calculating the weight of each node in the interest network by using the user interaction information of the entity corresponding to each node obtained through statistics.
3. The method according to claim 2, wherein calculating the weight of each node in the interest network using the statistically obtained user interaction information of the entity corresponding to each node comprises:
aiming at each node in the interest network, classifying the user interaction information of the entity corresponding to each node according to the classification standard of the user interaction information to obtain the user interaction information under each class;
and calculating the weighted value of the quantity of the user interaction information of each node in the interest network under each category, and taking the sum of the weighted values of the quantity of the user interaction information of each node in the interest network under each category as the weight of each node in the interest network.
4. The method according to claim 1, wherein the calculating the weight of the connection relationship between two nodes having the connection relationship in the interest network includes:
determining the connection direction of the two nodes with the connection relationship by using a target guest group flow, wherein the target guest group flow refers to: in the group flow between the entities indicated by the user interaction information, the group flow between the entities corresponding to the two nodes with the connection relationship is included;
and calculating the weight of the connection relation of the two nodes with the connection relation in the determined connection direction.
5. The construction method according to claim 4, wherein the calculating the weight of the connection relationship of the two nodes having the connection relationship in the determined connection direction includes:
identifying an amount of traffic flowing in a direction from a first node to a second node from among traffic flowing between the first node and the second node, the first node referring to one of the two nodes having a connection relationship, the second node referring to the other of the two nodes having a connection relationship, the first node to the second node referring to the determined connection direction;
And taking the total quantity of the group flows from the first node to the second node, and the ratio of the total quantity of the group flows from the first node to the neighbor node as the weight in the direction from the first node to the second node, wherein the neighbor node refers to the node with a connection relation with the first node.
6. The construction method according to claim 4, wherein the calculating the weight of the connection relationship of the two nodes having the connection relationship in the determined connection direction includes:
identifying, in a traffic flow between a first node and a second node, an amount of traffic flow in a direction from the first node to the second node, the first node referring to one of the two nodes having a connection relationship, the second node referring to the other of the two nodes having a connection relationship, the first node to the second node referring to the determined connection direction;
classifying the identified quantity of the guest group flowing in the direction from the first node to the second node according to the classification standard of the guest group flowing to obtain the quantity of the guest group flowing under each category;
calculating a weighted value of the amount of the group flow under each category from each node to the second node;
Taking the ratio of the sum of weighted values of the amounts of the group flows of the first node to the second node under each category to the sum of weighted values of the amounts of the group flows of the first node to the neighbor node under each category as the weight of the first node to the second node, wherein the neighbor node refers to the node with the connection relation with the first node.
7. A network of interest building apparatus, comprising:
the system comprises an acquisition unit, a target scene and a display unit, wherein the acquisition unit is used for acquiring a plurality of user interaction information, and each user interaction information is used for indicating that a user has interaction behavior on one entity in the target scene;
the analysis unit is used for analyzing the user interaction information to obtain an entity indicated by the user interaction information and a group flow between the entities indicated by the user interaction information, wherein the group flow is used for explaining that after the user has interaction behavior with one entity in the target scene, the user has interaction behavior with the other entity in the target scene;
the establishing unit is used for taking each entity indicated by the user interaction information as one node of the interest network, and establishing a connection relationship between two nodes of the interest network by utilizing the guest group flow between the entities indicated by the user interaction information, wherein the connection relationship between the two nodes of the interest network represents the guest group flow between the entities corresponding to the two nodes;
A first calculation unit for calculating a weight of each node in the interest network;
and the second calculation unit is used for calculating the weight of the connection relation between the two nodes with the connection relation in the interest network.
8. The building apparatus of claim 7, wherein the first computing unit comprises:
the statistics unit is used for respectively counting and indicating the user interaction information of the entity corresponding to each node in the interest network from the acquired plurality of user interaction information;
and the first calculating subunit is used for calculating the weight of each node in the interest network by using the user interaction information of the entity corresponding to each node obtained through statistics.
9. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-6.
10. A computer readable medium, characterized in that a computer program is stored thereon, wherein the computer program, when executed by a processor, implements the method according to any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011456721.5A CN112650862B (en) | 2020-12-10 | 2020-12-10 | Method and device for constructing interest network, electronic equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011456721.5A CN112650862B (en) | 2020-12-10 | 2020-12-10 | Method and device for constructing interest network, electronic equipment and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112650862A CN112650862A (en) | 2021-04-13 |
| CN112650862B true CN112650862B (en) | 2024-02-02 |
Family
ID=75353771
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011456721.5A Active CN112650862B (en) | 2020-12-10 | 2020-12-10 | Method and device for constructing interest network, electronic equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112650862B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113641919B (en) * | 2021-10-12 | 2022-03-25 | 北京达佳互联信息技术有限公司 | Data processing method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105117422A (en) * | 2015-07-30 | 2015-12-02 | 中国传媒大学 | Intelligent social network recommender system |
| CN105453119A (en) * | 2013-03-04 | 2016-03-30 | 阿普雷西有限公司 | System and method for dynamic client relationship management (CRM) |
| CN110413897A (en) * | 2019-06-14 | 2019-11-05 | 腾讯科技（深圳）有限公司 | Users' Interests Mining method, apparatus, storage medium and computer equipment |
| CN111523982A (en) * | 2020-04-30 | 2020-08-11 | 北京三快在线科技有限公司 | Commodity information recommendation method, commodity information recommendation device, server and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7424543B2 (en) * | 1999-09-08 | 2008-09-09 | Rice Iii James L | System and method of permissive data flow and application transfer |
-
2020
- 2020-12-10 CN CN202011456721.5A patent/CN112650862B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105453119A (en) * | 2013-03-04 | 2016-03-30 | 阿普雷西有限公司 | System and method for dynamic client relationship management (CRM) |
| CN105117422A (en) * | 2015-07-30 | 2015-12-02 | 中国传媒大学 | Intelligent social network recommender system |
| CN110413897A (en) * | 2019-06-14 | 2019-11-05 | 腾讯科技（深圳）有限公司 | Users' Interests Mining method, apparatus, storage medium and computer equipment |
| CN111523982A (en) * | 2020-04-30 | 2020-08-11 | 北京三快在线科技有限公司 | Commodity information recommendation method, commodity information recommendation device, server and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112650862A (en) | 2021-04-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107483982B (en) | Anchor recommendation method and device | |
| US9569499B2 (en) | Method and apparatus for recommending content on the internet by evaluating users having similar preference tendencies | |
| CN112131480B (en) | Personalized commodity recommendation method and system based on multilayer heterogeneous attribute network representation learning | |
| US9015128B2 (en) | Method and system for measuring social influence and receptivity of users | |
| CN106202534A (en) | A kind of content recommendation method based on community users behavior and system | |
| CN108280670A (en) | Seed crowd method of diffusion, device and information jettison system | |
| CN109165847B (en) | Item recommendation method, device and equipment based on recommendation system | |
| CN105589905A (en) | User interest data analysis and collection system and method | |
| CN102495864A (en) | Collaborative filtering recommending method and system based on grading | |
| CN101482884A (en) | Cooperation recommending system based on user predilection grade distribution | |
| CN108429776B (en) | Network object pushing method, device, client, interaction equipment and system | |
| CN107896153B (en) | Traffic package recommendation method and device based on mobile user internet surfing behavior | |
| CN105335518A (en) | Method and device for generating user preference information | |
| CN110188268A (en) | A kind of personalized recommendation method based on label and temporal information | |
| CN112650862B (en) | Method and device for constructing interest network, electronic equipment and computer storage medium | |
| CN116862592B (en) | Automatic push method for SOP private marketing information based on user behavior | |
| CN104657457A (en) | Data processing method for video evaluation of users, video recommendation method and devices | |
| CN112288554A (en) | Commodity recommendation method and device, storage medium and electronic device | |
| CN111340380A (en) | Client resource allocation method, device and storage medium | |
| CN114245185A (en) | Video recommendation method, model training method, device, electronic equipment and medium | |
| CN112560105A (en) | Joint modeling method and device for protecting multi-party data privacy | |
| US20230316106A1 (en) | Method and apparatus for training content recommendation model, device, and storage medium | |
| CN109062945B (en) | Information recommendation method, device and system for social network | |
| CN104199843A (en) | Service sorting and recommending method and system based on social network interactive data | |
| CN116127184A (en) | Product recommendation method and device, nonvolatile storage medium and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |