WO2021139513A1

WO2021139513A1 - Method and apparatus for processing interaction sequence data

Info

Publication number: WO2021139513A1
Application number: PCT/CN2020/137922
Authority: WO
Inventors: 常晓夫; 文剑烽; 刘旭钦; 宋乐
Original assignee: 支付宝(杭州)信息技术有限公司
Priority date: 2020-01-09
Filing date: 2020-12-21
Publication date: 2021-07-15
Also published as: CN111258469B; CN111258469A

Abstract

Provided are a method and apparatus for processing interaction data. In the method, firstly, a dynamic interaction graph constructed according to an interaction event set is obtained, wherein any node i points, by means of connection edges, to M associated nodes corresponding to N associated events in which an object represented by the node i participated the last time, the object is allowed to simultaneously participate in multiple associated events, and the node is allowed to be connected to more than two associated nodes. Then, in the dynamic interaction graph, a target sub-graph corresponding to a target node is determined. The target sub-graph comprises nodes within a predetermined range which are reached via connection edges, starting from the target node. Therefore, on the basis of node features of the nodes included in the target sub-graph and a pointing relationship of the connection edges between the nodes, a feature vector corresponding to the target node can be determined for service processing.

Description

Method and device for processing interactive sequence data

Technical field

One or more embodiments of this specification relate to the field of machine learning, and more particularly to methods and devices for processing interactive sequence data using machine learning.

Background technique

In many scenarios, user interaction events need to be analyzed and processed. Interaction events are one of the basic elements of Internet events. For example, the click behavior of a user when browsing a page can be regarded as an interaction event between the user and the page content block, and the purchase behavior in e-commerce can be regarded as the interaction between the user and the product Interaction events between users, communication between users through social platforms, and transfer behavior between accounts are interaction events between users. A series of user interaction events contain the user's fine-grained habits and preferences, as well as the characteristics of interactive objects, which are important source of features for machine learning models. Therefore, in many scenarios, it is desirable to characterize and model interactive participants based on interactive events.

However, an interactive event involves both parties to the interaction, and the status of each participant itself can be dynamically changed. Therefore, it is very difficult to accurately express the characteristics of the interactive participants comprehensively considering the various characteristics of the interactive parties. Therefore, it is hoped that there will be an improved solution to analyze and process the interactive objects in the interactive event more effectively, so as to obtain feature vectors suitable for subsequent analysis.

Summary of the invention

One or more embodiments of this specification describe methods and devices for processing interactive data, in which the interactive events participating in the interactive objects and the influence of other objects in the interactive events are considered, and the interactive objects are processed into feature vectors, which is beneficial to subsequent interaction with the interactive objects. Analysis and analysis of interaction events.

According to a first aspect, there is provided a method for processing interaction data, the method comprising: obtaining a dynamic interaction graph constructed according to an interaction event set, wherein the interaction event set includes a plurality of interaction events, and each interaction event includes at least , The two objects at which the interaction behavior occurs and the interaction time; the dynamic interaction graph includes any first node, and the first node corresponds to the first object in the interaction event that occurred at the first time, and the first node Pointing to the M associated nodes corresponding to the N associated events through the connecting edge, the N associated events all occur at the second time, and all include the first object as one of the interactive objects, and the second time is, Looking back from the first time forward, the time before the interaction behavior of the first object occurred; the dynamic interaction graph includes at least one multi-element node whose number of associated nodes is greater than 2; in the dynamic interaction graph, it is determined A first target subgraph corresponding to a first target node, where the first target subgraph includes nodes within a predetermined range that start from the first target node and reach via connecting edges; based on the first target subgraph To determine the first feature vector corresponding to the first target node by including the node features of each node and the direction relationship of the connecting edges between the nodes; at least use the first feature vector to communicate with the first target node Related business processing.

In one embodiment, the object includes a user, and the interaction event includes at least one of the following: a click event, a social event, and a transaction event.

In an embodiment, the above-mentioned M associated nodes are 2N nodes, respectively corresponding to two objects included in each associated event in the N associated events.

According to this embodiment, the dynamic interaction graph can be obtained in the following ways: obtaining an existing dynamic interaction graph constructed based on an existing set of interaction events; obtaining P new interaction events that occurred at the first update time; in the existing dynamic interaction 2P new nodes are added in the figure, and the 2P new nodes respectively correspond to the two objects included in each new interaction event in the P new interaction events; for each new node, if there is an association Node, add a connecting edge from the newly added node to its associated node.

In another embodiment, the aforementioned M associated nodes are N+1 nodes, respectively corresponding to N other objects interacting with the first object in the N associated events, and the first object itself.

According to this embodiment, the dynamic interaction graph can be obtained in the following ways: obtaining an existing dynamic interaction graph constructed based on an existing set of interaction events; obtaining P newly added interaction events occurring at the first update time; determining the P newly added interaction events Q different objects involved in the interaction event; adding Q new nodes to the existing dynamic interaction graph, the Q new nodes corresponding to the Q different objects; for each new node, If there is an associated node, add a connecting edge from the newly added node to its associated node.

According to an embodiment, the above-mentioned first target node is a node: in the dynamic interaction graph, there is no connecting edge pointing to the node.

In an embodiment, the nodes within the predetermined range include: nodes within a connecting edge of a preset order K; and/or nodes whose interaction time is within a preset time range.

According to one embodiment, each interaction event also includes the event characteristics of the interaction event; in this case, the node characteristics of each node may include the attribute characteristics of the object corresponding to each node, and the characteristics of the interaction event where each node is located. Event characteristics.

According to an embodiment, the performed service processing related to the first target node may include predicting the classification category of the object corresponding to the first target node according to the first feature vector.

According to an embodiment, the method further includes, in the dynamic interaction graph, determining a second target subgraph corresponding to a second target node, where the second target subgraph includes starting from the second target node, Nodes within the predetermined range that are reached via the connecting edge; based on the node characteristics of each node contained in the second target subgraph and the direction relationship of the connecting edges between the nodes, determine the corresponding to the second target node The second feature vector.

Based on the above embodiment, the performed service processing related to the first target node may further include predicting the first target node and the second target node according to the first feature vector and the second feature vector Whether the represented objects will interact.

Or, in one embodiment, the first target node and the second target node are two nodes corresponding to the first interaction event; in this case, the service processing may include, according to the first feature vector and the second feature vector , Predict the event category of the first interaction event.

According to an embodiment, the first feature vector corresponding to the first target node can be determined by the following method: inputting the first target subgraph into a pre-trained neural network model, the neural network model based on the first target subgraph The node features of each node included in the graph and the direction relationship of the connecting edges between the nodes are outputted as the first feature vector.

Further, in different embodiments, the neural network model includes one of the following: a neural network model based on LSTM, a neural network model based on RNN, and a neural network model based on Transformer

According to a second aspect, there is provided an apparatus for processing interaction data, the apparatus comprising: an interaction graph obtaining unit configured to obtain a dynamic interaction graph constructed according to an interaction event set, wherein the interaction event set includes a plurality of interaction events , Each interaction event includes at least two objects where the interaction behavior occurs and the interaction time; the dynamic interaction graph includes any first node, and the first node corresponds to the first one of the interaction events occurring at the first time. Object, the first node points to the M associated nodes corresponding to the N associated events through the connecting edge, the N associated events all occur at the second time, and all include the first object as one of the interactive objects, The second time is, looking back from the first time, the time before the interaction of the first object occurs; the dynamic interaction graph includes at least one multi-node with more than 2 associated nodes; a subgraph The determining unit is configured to determine, in the dynamic interaction graph, a first target subgraph corresponding to a first target node, where the first target subgraph includes a predetermined value that starts from the first target node and arrives via a connecting edge. Nodes within the range; a subgraph processing unit configured to determine the first target node corresponding to the first target node based on the node characteristics of each node contained in the first target subgraph and the direction relationship of the connecting edges between the nodes A feature vector; a service processing unit configured to use at least the first feature vector to perform service processing related to the first target node.

According to a third aspect, there is provided a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the method of the first aspect.

According to a fourth aspect, there is provided a computing device, including a memory and a processor, characterized in that executable code is stored in the memory, and when the processor executes the executable code, the method of the first aspect is implemented .

According to the method and device provided in the embodiments of this specification, a dynamic interaction diagram is constructed based on a set of interaction events, and the dynamic interaction diagram reflects the timing relationship of each interaction event and the mutual influences between interactive objects transmitted through each interaction event. In addition, there are multiple interaction events occurring simultaneously in the above-mentioned interaction event set, and multiple nodes connected to multiple associated nodes are allowed to exist in the corresponding dynamic interaction graph, thereby enriching the relationship information contained in the dynamic interaction graph. Therefore, based on the subgraph related to the node corresponding to the interactive object to be analyzed in the dynamic interaction graph, the feature vector of the interactive object can be extracted. The feature vector obtained in this way introduces the influence of other interactive objects in each interactive event on it, so that the in-depth characteristics of the interactive object can be comprehensively expressed, and business processing can be better performed.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following will briefly introduce the drawings used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. A person of ordinary skill in the art can obtain other drawings based on these drawings without creative work.

Figure 1A shows a two-part diagram of the interaction relationship in an example;

FIG. 1B shows an interactive relationship network diagram in another example;

Fig. 2 shows a schematic diagram of an implementation scenario according to an embodiment;

Fig. 3 shows a flowchart of a method for processing interactive data according to an embodiment;

Figure 4 shows a dynamic interaction diagram constructed according to an embodiment;

Figure 5 shows a dynamic interaction diagram constructed according to another embodiment;

Figure 6 shows an example of a target subgraph in one embodiment;

Figure 7 shows an example of a target subgraph in another embodiment;

Figure 8 shows a flowchart of training a neural network model in one embodiment;

Figure 9 shows a flowchart of training a neural network model in another embodiment;

Fig. 10 shows a schematic block diagram of an apparatus for processing interactive data according to an embodiment.

Detailed ways

The following describes the solutions provided in this specification with reference to the accompanying drawings.

As mentioned earlier, it is hoped that based on the sequence of interaction events, the participants in the interaction event, that is, the interaction object, can be characterized and modeled.

In one solution, a static interaction relationship network diagram is constructed based on historical interaction events, so that each interaction object is analyzed based on the interaction relationship network diagram. Specifically, participants in each historical event can be used as nodes, and connecting edges can be established between nodes that have an interactive relationship, so as to form the foregoing interactive network graph.

Fig. 1A and Fig. 1B respectively show the interactive relationship network diagram in a specific example. More specifically, Figure 1A shows a bipartite graph, which contains user nodes (U1-U4) and product nodes (V1-V3). If a user has purchased a product, it will be between the user and the product. Construct a connecting edge between. Figure 1B shows a user transfer relationship diagram, in which each node represents a user, and there is a connecting edge between two users who have made transfer records.

However, it can be seen that although FIG. 1A and FIG. 1B show the interaction relationship between objects, they do not contain the timing information of these interaction events. Simply embedding the graph based on such an interactive relationship network graph, the obtained feature vector does not express the influence of the time information of the interactive event on the node. Moreover, the scalability of such a static graph is not strong enough, and it is difficult to flexibly handle the situation of newly-added interactive events and newly-added nodes.

In another solution, for each interactive object to be analyzed, a behavior sequence of the object is constructed, and the characteristic expression of the object is extracted based on the behavior sequence. However, such a behavior sequence only characterizes the behavior of the object to be analyzed, and interactive events are events involving multiple parties, and the participants will indirectly transmit influence through the interaction events. Therefore, this method does not express the influence between the participating objects in the interaction event.

Taking the above factors into consideration, according to one or more embodiments of this specification, a dynamically changing set of interaction events is constructed into a dynamic interaction graph, wherein each interaction object involved in each interaction event corresponds to each node in the dynamic interaction graph. An arbitrary node is connected to a number of associated nodes, where the associated node is the node corresponding to the interaction event that the object corresponding to the arbitrary node participated in last time. For the interactive object to be analyzed, the subgraph part related to the corresponding node is obtained from the dynamic interaction graph, and the feature vector expression of the interactive object is obtained based on the node characteristics of the nodes contained in the subgraph part and the connection relationship between the nodes.

Fig. 2 shows a schematic diagram of an implementation scenario according to an embodiment. As shown in Figure 2, the set of interaction events composed of multiple interaction events can be obtained. More particularly, the interaction may be a set of events more interaction events chronologically organized into a sequence of interactive events _{_{<E 1, E 2, ...}} , E N>, where each element represents an interactive event E _i, may be expressed is a form of interactive features set _{_{E i = (a i, b}} i, t i), where a _i and b _i are the two objects interact in the event E _i, t _i is the time of interaction. Due to factors such as the accuracy of time measurement, multiple interaction events are allowed to occur at the same time.

According to an embodiment of the present specification, a dynamic interaction diagram 200 is constructed based on the set of interaction events. In FIG. 200, the individual interactive objects each interaction event a _{_i,} b _i represented by nodes, and establishes a connection between the edges containing the same event object. Since multiple interaction events are allowed to occur at the same time, the dynamic interaction graph 200 contains at least one multi-element node, and the multi-element node can be connected to 3 or more associated nodes. The structure of the dynamic interaction graph 200 will be described in more detail later.

For the target node corresponding to a target interaction object to be analyzed, the corresponding target subgraph in the dynamic interaction graph can be determined. Generally, the target subgraph includes nodes that can be reached through a certain range of connected edges starting from the target node. This subgraph reflects the influence of other objects in the interaction event directly or indirectly associated with the target interaction object on the target node.

Then, based on the node feature and node connection relationship of each node in the target subgraph, the feature vector corresponding to the target node is obtained. The feature vector obtained in this way can extract the timing information of the associated interaction events and the influence between the interaction objects in each interaction event, so as to more accurately express the in-depth characteristics of the target interaction object represented by the target node. Such feature vectors can be subsequently applied to various machine learning models and various business scenarios. For example, reinforcement learning can be performed based on the feature vector thus obtained, or cluster analysis can be performed based on the feature vector, for example, clustering users into groups of people. You can also perform classification prediction based on such feature vectors, for example, predict whether there will be interaction between two objects (such as whether a user will buy a certain product), and predict the business type of a certain object (such as the risk of a certain user). Level), the event category of an interactive event can also be predicted based on the feature vectors of two objects in an interactive event, and so on.

The specific implementation of the above concept is described below.

Fig. 3 shows a flowchart of a method for processing interactive data according to an embodiment. It is understandable and understandable that the method can be executed by any device, device, platform, or device cluster with computing and processing capabilities. The following describes each step in the method for processing interactive data as shown in FIG. 3 in conjunction with specific embodiments.

First, in step 31, a dynamic interaction graph constructed according to the set of interaction events is obtained.

As mentioned above, it is possible to obtain an interaction event set composed of multiple interaction events, where each interaction event has two interaction objects and interaction time. Thus, any interaction events E _i may be expressed as a set of interactive features _{_{E i = (a i, b}} i, t i), where a _i and b _i are two events E _i interactive object, such as a first target With the second object, t _i is the interaction time.

For example, in an e-commerce platform, the interaction event may be a user's purchase behavior, where the first object may be a certain user, and the second object may be a certain commodity. In another example, the interaction event may be a user's click behavior on a page block, where the first object may be a certain user, and the second object may be a certain page block. In another example, the interaction event may be a transaction event, for example, a user transfers money to another user, or a user makes a payment to a store or platform. In another example, the interaction event may be a social event that a user occurs through a social platform, such as chatting, calling, sending red envelopes, and so on. In other business scenarios, interaction events can also be other interaction behaviors that occur between two objects.

In one embodiment, according to the characteristics of the interaction event, the two objects interacting may be objects of different types, such as objects of the first type and objects of the second type. For example, when the interaction event is a purchase behavior in an e-commerce platform, the first type of object may be a certain user, and the second type of object may be a certain commodity. In other embodiments, the two objects involved in the interaction event may be objects of the same type. For example, in an instant messaging scenario, the interaction event may be an instant communication between two users. At this time, both the first object and the second object are users and belong to the same type of objects. In still other embodiments, whether to distinguish the types of two interactive objects can be set according to the needs of the business. For example, for the transfer interaction event, in the foregoing example, it can be considered that the two users belong to the same type of object. In other examples, according to business needs, the user who transfers the amount may be regarded as an object of the first type, and the user who is the recipient is regarded as an object of the second type.

Further, in an embodiment, the interaction feature group corresponding to each interaction event may also include event feature or behavior feature f. In this way, each interaction feature group can be expressed as X _i = (a _i , b _i , t _i ,f). Specifically, the event feature or behavior feature f may include background and context information of the occurrence of the interaction event, some attribute features of the interaction behavior, and so on.

For example, in the case where the interaction event is a user click event, the event feature f may include the type of terminal used by the user to click, browser type, app version, etc.; in the case where the interaction event is a transaction event, the event The feature f may include, for example, transaction type (commodity purchase transaction, transfer transaction, etc.), transaction amount, transaction channel, and so on.

Interactivity events described above as well as in the event interactive objects a _i, b _i of example.

For the interaction time t _i , it needs to be understood that in actual operation, the time is always measured and recorded in an appropriate duration unit. For example, in some service platforms, the unit duration for recording the interaction time can be hours h or minutes m. Therefore, multiple interaction events are likely to occur within the unit duration. Even if it takes a short duration as a unit, such as seconds or even milliseconds, for some service platforms that interact very frequently, such as Alipay, there will inevitably be multiple interaction events within a unit of time.

In addition, there are some cases of batch interaction. For example, the user edits a message in advance, selects a group of friends, and then performs a batch group sending operation. This is equivalent to initiating an interaction event with multiple friends at the same time. For another example, a user adds multiple items to the shopping cart and then selects batch settlement, which is equivalent to simultaneously initiating interaction events with multiple items.

For at least the above two reasons, it is often the case that the interaction time recorded by multiple interaction events is the same. For such situations, this article is sometimes referred to as multiple interactive events occurring at the same time, without distinguishing their precise time and sequence.

In a specific example, it is assumed that an interaction event set S is obtained. The interaction events in the interaction event set S are arranged in chronological order and expressed in the form of interaction feature groups, which can be recorded as follows:

Among them, a, b, c, d, e, f, u, v are interaction objects, interaction events E ₂ and E ₃ all occur at _{time t 2} and interaction events E ₄ , E ₅ and E ₆ all occur at t ₃ At time, the interaction events E ₇ and E ₈ both occurred at time _{t 4.}

For the set of interaction events described above, a dynamic interaction diagram can be constructed to depict the association relationships between interaction events and interaction objects. Specifically, the objects contained in the interaction events occurring at each time can be used as the nodes of the dynamic interaction graph. In this way, a node can correspond to an object that interacts at a time, but the same physical object may correspond to multiple nodes. For example, the physical object v at time t ₆ u interact with an object, the node may correspond to construct v (t _6), c interact with objects in the time t _5, the node may correspond to construct v (t _5). Therefore, it can be considered that the nodes in the dynamic interaction graph correspond to the interactive object at a certain interaction time, or in other words, correspond to the state of the interactive object at a certain interaction time.

For each node in the dynamic interaction graph, construct the connecting edge in the following way: For any node i, it is called the first node for simplicity; assuming that it corresponds to the first object at the first interaction time t, then in the interaction In the event sequence, backtracking from the first interaction time t, that is, backtracking in the direction earlier than the first interaction time t, it is determined that the last time when the first object interacted is the second time (t-), and The N interaction events that occur in the second time and the first object participates in are regarded as the N associated events of the first node, and the M nodes corresponding to the N associated events are regarded as the associated nodes, and it is established to point from the first node i to M The connecting edge of the associated node. Due to the possibility of multiple interaction events occurring at the same time, N may be greater than 1. In this way, the dynamic interaction graph may include multiple nodes, that is, nodes with more than two connected associated nodes.

In one embodiment, when constructing the dynamic interaction graph, corresponding nodes are respectively established for the two objects of each interaction event. In this way, the aforementioned N associated events correspond to 2N nodes, and these 2N nodes are regarded as the aforementioned M associated nodes.

Fig. 4 shows a dynamic interaction diagram constructed according to an embodiment. Specifically, the left side of FIG. 4 shows a schematic diagram of an interaction sequence that organizes the foregoing interaction event set S in chronological order, and the right side shows a dynamic interaction diagram. In this dynamic interaction graph, two interaction objects in each interaction event are respectively regarded as nodes. The following takes nodes u(t ₆ ) and v(t ₆ ) as examples to describe the construction of connecting edges.

It can be understood that the node u(t ₆ ) represents the object u at _{time t 6.} Therefore, starting from time t ₆ and backtracking, it can be determined that the time when the object u had an interactive behavior last time is t ₄ , during which time t ₄ participated in two related events E ₇ and E ₈ , namely, the interaction event E ₇ Both E and E ₈ contain the object u as one of the interactive objects. Therefore, the four nodes corresponding to the associated events E ₇ and E ₈ are the associated nodes of _{the node u(t 6 ).} In Fig. 4, in order to distinguish the object node u in the _{events E 7} and E ₈ _{, they are denoted as u 1} (t ₄ ) and u ₂ (t ₄ ). Thus, a connecting edge from the node u(t ₆ ) to its 4 associated nodes is established.

The node v(t ₆ ) represents the object v at _{time t 6.} Therefore, starting from time t ₆ and looking back forward, it can be determined that the time when the object v had an interactive behavior last time is t ₅ , during which time t ₅ participated in an associated event E ₉ . Therefore, the two nodes v(t ₅ ) and c(t ₅ ) corresponding to the associated event E ₉ are the associated nodes of node v(t _{6 ).} Then, a connecting edge from the node v(t ₆ ) to the two associated nodes is established. For each other node, the above-mentioned method can be used to determine its associated event and associated node, so as to establish a connection edge to the associated node. In the dynamic interaction graph shown in Figure 4, the nodes u(t ₆ ) and c(t ₅ ) are all multi-element nodes.

In another embodiment, when constructing a dynamic interaction graph, for multiple interaction events that occur at the same time, different interaction objects involved in the multiple interaction events are determined, and corresponding nodes are established for each different interaction object. In other words, if multiple interaction events that occur at the same time contain the same object, only one node is established for the same object. In this way, when establishing a connection edge, if there are N associated events corresponding to the first node of the first object, then these N associated events correspond to N+1 associated nodes, corresponding to the first object itself, and N N other objects interacting with the first object in the associated event.

Fig. 5 shows a dynamic interaction diagram constructed according to another embodiment. Specifically, the left side of FIG. 5 shows the aforementioned interaction event set S, and the right side shows a dynamic interaction diagram. In the dynamic interaction graph, corresponding nodes are respectively established for different interaction objects in the interaction events that occur at the same time. The difference between the dynamic interaction diagram of FIG. 5 and that of FIG. 4 is that the nodes of the same object in the multiple interaction events that occur at the same time in FIG. 4 are merged into one node. For example, for two interaction events E ₇ , E ₈ that both occur at time t ₄ , which involve three different interaction objects a, b, u, then three nodes a(t ₄ ) are established for the interaction event at that time , B(t ₄ ), u(t ₄ ). This is equivalent to _{merging u 1} (t ₄ ) and u ₂ (t ₄ ) in Fig. 4 into one node u(t ₄ ). In this case, in one example, can be shown by the dashed double arrows between the nodes of the interactions occur, for example, shown by the dashed double arrow in FIG. 5, at time t _4, there is an interaction with a target u Behavior, there is interaction between objects b and u, but there is no interaction between objects a and b.

The following still takes the nodes u(t ₆ ) and v(t ₆ ) as examples to describe the construction of connecting edges.

As mentioned earlier, the node u(t ₆ ) represents the object u at _{time t 6.} Starting from time t ₆ and looking back, it can be determined that the time when the object u had an interactive behavior last time is t ₄ , during which time t ₄ participated in two related events E ₇ and E ₈ , namely, interactive events E ₇ and E ₈ all contain the object u as one of the interactive objects. The three nodes a(t ₄ ), b(t ₄ ), and u(t ₄ ) corresponding to the associated events E ₇ and E ₈ are associated nodes of the node u(t _{6 ).} Then, a connecting edge from the node u(t ₆ ) to the three associated nodes is established.

From the node v(t ₆ ), a connecting edge pointing to the two nodes v(t ₅ ) and c(t ₅ ) corresponding to the associated event E ₉ can be established. This process is the same as the description in conjunction with FIG. 4 and will not be repeated. For each of the other nodes in Figure 5, the above-mentioned methods can be used to determine the associated events and associated nodes, so as to establish a connection edge to the associated node. In the dynamic interaction graph shown in Figure 5, the nodes u(t ₆ ) and c(t ₅ ) are all multi-element nodes.

The above describes the method and process of constructing a dynamic interaction graph based on the set of interaction events. For the method of processing interactive data shown in FIG. 3, the process of constructing a dynamic interactive graph can be performed in advance or on site. Correspondingly, in one embodiment, in step 31, a dynamic interaction diagram is constructed on-site according to the interaction event set. The construction method is as described above. In another embodiment, a dynamic interaction graph may be constructed based on a set of interaction events in advance. In step 31, read or receive the formed dynamic interaction graph.

It can be understood that the dynamic interaction graph constructed in the above manner has strong scalability and can be dynamically updated according to newly added interaction events very easily. Correspondingly, step 31 may also include a process of updating the dynamic interaction graph.

Specifically, an existing dynamic interaction diagram constructed based on an existing interaction event set can be obtained, and then as time is updated, new interaction events that occur during the update time are continuously detected, and the existing dynamic interaction diagram is updated according to the new interaction events .

In one embodiment, the existing dynamic interaction graph adopts the form of FIG. 4, and each interaction event corresponds to two nodes. In this case, assuming that P new interaction events that occurred at the first update time are obtained, then 2P new nodes are added to the existing dynamic interaction graph, and the 2P new nodes respectively correspond to P Two objects included in each of the new interactive events. Then, for each newly added node, find its associated events and associated nodes in the aforementioned manner. If there is an associated node, add a connecting edge from the newly added node to its associated node.

In another embodiment, the existing dynamic interaction graph adopts the form of FIG. 5, and different objects in simultaneous interaction events correspond to different nodes. In this case, after acquiring the P newly-added interaction events that occurred at the first update time, first determine the Q different objects involved in the P newly-added interaction events. If the same interaction object does not exist in the P newly added interaction events, then Q=2P; if the same interaction object exists in the P newly added interaction events, then Q<2P. Then, Q new nodes are added to the existing dynamic interaction graph, and the Q new nodes respectively correspond to Q different objects. Then, for each newly added node, find its associated events and associated nodes in the aforementioned manner. If there is an associated node, add a connecting edge from the newly added node to its associated node.

In summary, in step 31, a dynamic interaction graph constructed based on the set of interaction events is obtained.

Next, in step 32, in the acquired dynamic interaction graph, a first target subgraph corresponding to the first target node is determined, where the first target subgraph includes a predetermined range that starts from the first target node and reaches via the connecting edge Within the node.

It should be understood that the first target node may be a node corresponding to a certain target interaction object to be analyzed. However, as mentioned earlier, an entity object can correspond to multiple nodes, expressing the state of the entity object at different times. In order to express the latest state of the target interaction object to be analyzed, in one embodiment, such a node is selected as the first target node, that is, in the dynamic interaction graph, there is no connecting edge pointing to the node. That is to say, select the node corresponding to the time when the object to be analyzed recently interacted as the first target node. For example, in the dynamic interaction diagrams shown in Figures 4 and 5, when you want to analyze the interactive object u, you can select the node u(t ₆ ) as the target node. However, this is not required. In other embodiments, for example, for training purposes, other nodes may also be selected as the first target node. For example, in order to analyze the object u, the node u(t ₄ ) may also be selected as the first target node.

Starting from the first target node, nodes within a predetermined range reached via the connecting edge form a first target subgraph corresponding to the first target node. In an embodiment, the nodes within the foregoing predetermined range may be nodes that are reachable by connecting edges of at most a preset order K. Here, the order K is a preset hyperparameter, which can be selected according to business conditions. It can be understood that the preset order K reflects the number of steps of historical interaction events that are traced forward when the information of the target node is expressed. The larger the number K is, the more historical interactive information of order is considered.

In another embodiment, the nodes within the foregoing predetermined range may also be nodes whose interaction time is within the predetermined time range. For example, backtracking from the interaction time of the target node for a duration of T (for example, one day), within the range of duration and reachable through the connecting edge.

In another embodiment, the above-mentioned predetermined range considers both the order of the connected edges and the time range. In other words, the nodes within the predetermined range refer to nodes whose connection edges passing through the preset order K at most are reachable and whose interaction time is within the predetermined time range.

For simplicity, in the following example, the connection edge of the preset order K is taken as an example for description.

Figure 6 shows an example of a target subgraph in one embodiment. In the example in Fig. 6, suppose u(t ₆ ) in Fig. 4 is the first target node, and the preset order K=2, then starting from u(t ₆ ), traverse along the direction of the connecting edge, passing 2 The nodes that can be reached by the connecting edge of the level are shown in the gray nodes in the figure. These gray nodes and the connection relationship between them are the first target subgraph corresponding to _{the first target node u(t 6 ).}

Fig. 7 shows an example of a target subgraph in another embodiment. In the example of Fig. 7, suppose u(t ₆ ) in Fig. 5 is the first target node, and the preset order K=2, then starting from u(t ₆ ), traverse along the direction of the connecting edge, passing 2 The nodes that can be reached by the connecting edge of the level are shown in the gray nodes in the figure. These gray nodes and the connection relationship between them are the first target subgraph corresponding to _{the first target node u(t 6 ).}

Next, in step 33, a first feature vector corresponding to the first target node is determined based on the node characteristics of each node included in the first target subgraph and the direction relationship of the connecting edges between the nodes.

Specifically, the node characteristics may include the attribute characteristics of the object represented by the node. For example, in the case where the node represents the user, the node feature may include the attribute characteristics of the user, such as age, occupation, education level, location, etc.; in the case where the node represents the product, the node feature may include the attribute feature of the product. For example, product category, shelf time, sales volume, etc. In the case where the node represents other interactive objects, the original node characteristics can be obtained accordingly.

In an embodiment, as described above, the feature group of the interaction event further includes an event feature f. In this case, the node feature may also include the event feature f of the event where the node is located. If the dynamic interaction diagram in the form of Figure 5 is used, a node can correspond to multiple interaction events occurring at the same time, then the node characteristics of the node may include the synthesis of the event characteristics f of multiple events that the node participates in at the same time.

In order to determine the first feature vector corresponding to the first target node, in one embodiment, the node feature of each node in the first target subgraph can be obtained, and then, according to the distance of each node from the first target node in the subgraph, It assigns corresponding weights, and synthesizes the node features of each node based on the weights to obtain the first feature vector corresponding to the first target node. The distance between a certain node and the first target node can be determined based on the number of connection edges experienced from the first target node to the node, or based on the interaction time T1 of the interaction event where the first target node is located and the interaction corresponding to the certain node The time difference between time T2 is determined. Of course, a relatively high weight can be preset for the first target node itself. Therefore, based on the node characteristics of each node included in the first target subgraph and considering the connection relationship of these nodes, the first feature vector corresponding to the first target node is determined.

In another embodiment, a graph embedding algorithm or graph embedding model may be used to perform graph embedding on the first target subgraph, thereby obtaining the first feature vector corresponding to the first target node. There are already a variety of supervised or unsupervised graph embedding algorithms or graph embedding models. Based on the characteristics and needs of the actual business, an appropriate algorithm or model can be selected to obtain the first feature vector.

According to one embodiment, in step 33, the first target sub-graph is input into a pre-trained neural network model, and the neural network model is based on the node characteristics of each node contained in the first target sub-graph and the relationship between the nodes. The direction relationship of the connecting edge is output, and the first feature vector is output.

In one embodiment, the neural network model is a neural network model based on RNN. In this case, a node sequence is formed according to the directional relationship between the nodes in the first target subgraph, and the RNN neural network model is used to sequentially process the nodes in the node sequence to obtain the first feature vector of the first target node.

In another embodiment, the neural network model is a neural network model based on LSTM. The LSTM neural network model is an improvement of the RNN neural network model. It also processes each node based on the node timing relationship represented by the connection edge between the nodes. More specifically, for any current node in the first target subgraph, the LSTM neural network model performs the following processing: at least according to the node characteristics of the current node, the respective intermediate vectors and hidden vectors of several associated nodes pointed to by the current node , To determine the implicit vector and intermediate vector of the current node. In this way, the LSTM neural network model sequentially iteratively processes each node according to the direction relationship of the connecting edge between each node in the first target subgraph, so as to obtain the implicit vector of the first target node as the first feature vector.

In another embodiment, the neural network model is a neural network model based on Transformer. In this case, first form a node sequence according to the directional relationship between the nodes in the first target subgraph, and assign a position code to each node in the node sequence. The position code reflects the relative relationship of the node in the first target subgraph. The position of the first target node, for example, how many connecting edges are away from it, etc. Then the node sequence and position code are input into the Transfomer neural network model, so that the Transformer neural network model calculates the first feature vector of the first target node based on the node feature and position code of each node in the node sequence.

In other embodiments, the neural network model may also be a neural network model based on other network structures and algorithms, which will not be listed here.

Above, the first feature vector corresponding to the first target node is determined based on the first target subgraph in various ways. Since the first target subgraph reflects the time-series interaction history (for example, K related interaction events) information related to the interactive object corresponding to the first target node, the first feature vector thus obtained not only expresses the interactive object The characteristics of itself can also express the influence that the interactive object has received in previous interactive events, thereby fully characterizing the characteristics of the interactive object.

Therefore, in step 34, at least the above-mentioned first feature vector is used to perform service processing related to the first target node.

In an embodiment, the foregoing business processing may be to predict the classification category of the object corresponding to the first target node based on the first feature vector obtained above.

For example, in the case where the object corresponding to the first target node is a user, the user category of the user may be predicted based on the first feature vector, such as the category of the group to which it belongs, the category of risk level, and so on. In the case where the object corresponding to the first target node is an item, the category of the item may be predicted based on the first feature vector, such as the category of the business to which it belongs, the category of a suitable group of people, the category of the scene being purchased, and so on.

In an embodiment, the service processing may further include analyzing and predicting interaction events related to the first target node. Since interaction events generally involve two objects, it is also necessary to analyze the feature vector of another node.

Specifically, another node, called the second target node, can be analyzed in a manner similar to

steps

32 and 33 in FIG. 3. That is to say, in the dynamic interaction graph, a second target subgraph corresponding to the second target node is determined, and the second target subgraph includes nodes within the predetermined range starting from the second target node and arriving via the connecting edge. ; Then, based on the node characteristics of each node included in the second target subgraph and the direction relationship of the connecting edges between the nodes, the second feature vector corresponding to the second target node is determined. The specific execution process is similar to the description of

steps

32 and 33 in conjunction with the first target node, and will not be repeated here.

In one embodiment, the above-mentioned second target node is any node in the dynamic interaction graph that is different from the object represented by the first target node, such as v(t ₆ ) in FIG. 4 and FIG. 5. In this way, after the first feature vector corresponding to the first target node and the second feature vector corresponding to the second target node are respectively determined, the first target node and the second target node can be predicted based on the first feature vector and the second feature vector. Whether the object represented by the target node will interact.

For example, in an example, the first target node represents a certain user, and the second target node represents a certain commodity. Then, according to the first feature vector and the second feature vector, it is possible to predict whether the user will purchase the commodity. In another example, the first target node represents a certain user, and the second target node represents a certain page block. Based on the first feature vector and the second feature vector, it is possible to predict whether the user will click on the page block.

In another embodiment, the first target node and the second target node are two nodes corresponding to the first interaction event that has occurred. Then, the event category of the first interaction event can be predicted based on the first feature vector corresponding to the first target node and the second feature vector corresponding to the second target node.

For example, in an example, the user represented by the first target node has confirmed to purchase the commodity represented by the second target node, thereby generating the first interaction event. When the user requests payment, it can predict whether the first interaction event is a fraudulent transaction suspected of cashing out according to the first feature vector and the second feature vector, so as to determine whether the current payment is allowed. In yet another example, the user represented by the first target node has performed a comment operation, such as liking or posting a text comment, on the item (such as a movie) represented by the second target node, thereby generating the first interaction event. After that, based on the first feature vector and the second feature vector, it can be predicted whether the first interaction event is a real operation, so as to exclude some false comments about naval operations.

Therefore, on the basis of generating a dynamic interaction graph, expressing the nodes therein as feature vectors can facilitate subsequent analysis and prediction of the objects represented by the nodes or events related to multiple nodes.

As mentioned above, in order to obtain the feature vector of the target node, according to one or more embodiments, a neural network model is used to analyze and process the target subgraph corresponding to the target node. It can be understood that the neural network model relies on a large number of parameters in the calculation process of determining the feature vector of the target node, and these parameters need to be determined by training the neural network model. In different embodiments, the neural network model can be trained through different tasks, especially the business processing tasks in step 34. The following describes the training process of the neural network.

In one embodiment, the neural network model is trained by predicting the interaction behavior. Fig. 8 shows a flowchart of training a neural network model in this embodiment. As shown in Fig. 8, in step 81, historical interaction events are acquired. In a specific example, historical interaction events can be obtained from the aforementioned collection of interaction events. The two objects included in the historical interaction event are called the first sample object and the second sample object.

In step 82, in the dynamic interaction graph, a first sample subgraph corresponding to the first sample object and a second sample subgraph corresponding to the second sample object are respectively determined. Specifically, first, the first sample node and the second sample node are respectively determined in the dynamic interaction graph, where the first sample node corresponds to the first sample object under the historical time of the historical interaction event, and the second sample node Corresponds to the second sample object at the historical time. Then, the first sample node and the second sample node are respectively used as target nodes, and the corresponding first sample subgraph and second sample subgraph are determined in a similar manner to step 32 in FIG. 3.

Then, in step 83, the above-mentioned first sample subgraph and the second sample subgraph are respectively input into the neural network model, and the first sample vector corresponding to the first sample object and the second sample vector corresponding to the second sample object are respectively obtained . The specific process of the neural network model determining the sample vector of the sample object based on the pointing relationship of the nodes in the subgraph is as described above in conjunction with step 33, and will not be repeated.

Next, in step 84, according to the first sample vector of the first sample object and the second sample vector of the second sample object, predict whether the first sample object and the second sample object will interact, and obtain the prediction result. Generally, a two-class classifier can be used to predict whether two sample objects will interact, and the obtained prediction result is usually expressed as the probability of the two sample objects interacting.

Therefore, in step 85, the prediction loss is determined based on the above prediction result. It can be understood that the above-mentioned first sample object and second sample object come from historical interaction events, so the interaction has actually occurred, which is equivalent to knowing the relationship label between the two sample objects. According to the loss function form such as the cross entropy calculation method, the loss of this prediction can be determined based on the above prediction result.

Then, in step 86, the neural network model is updated based on the predicted loss. Specifically, methods such as gradient descent and back propagation can be used to adjust the parameters in the neural network to update the neural network model until the prediction accuracy of the neural network model reaches a certain requirement.

The foregoing uses two sample objects in historical interaction events to predict the relationship between objects, which is equivalent to using positive samples for training. In an embodiment, two sample objects that have not interacted with each other can also be found in the dynamic interaction graph as negative samples for further training, so as to achieve a better training effect.

According to another embodiment, the neural network model is trained by predicting the classification of interactive objects. Fig. 9 shows a flow chart of training the neural network model in this embodiment. As shown in FIG. 9, in step 91, a sample object is selected from the set of interaction events, and the classification label of the sample object is obtained. The sample object can be any interaction object in any event, and the classification label for the sample object can be a label related to a business scenario. For example, in the case where the sample object is a user, the classification label may be a pre-set group classification label or a user risk level classification label; in the case where the sample object is a commodity, the classification label may be a commodity classification label. Such labels can be generated by manual labeling, or generated through other business-related processing.

In step 92, in the dynamic interaction graph, a sample subgraph corresponding to the sample object is determined. Specifically, a certain node corresponding to the sample object can be determined in the dynamic interaction graph. Since one entity object can correspond to multiple nodes in the dynamic interaction graph, preferably, the node corresponding to the sample object at the most recent interaction time can be selected here. With this node as the target node, the corresponding sample subgraph is determined in a similar manner to step 32 in FIG. 3.

Then, in step 93, the above-mentioned sample subgraph is input into the neural network model to obtain the sample vector of the sample object. This process is the same as that described in step 33, and will not be repeated here.

Next, in step 94, the classification of the sample object is predicted based on the sample vector of the sample object, and the prediction result is obtained. A classifier can be used to predict each probability that the sample object belongs to each category as the prediction result.

Then, in step 95, the prediction loss is determined based on the prediction result and the classification label. Specifically, for example, a cross-entropy calculation method can be used to predict each probability and classification label in the result, and determine the loss of this prediction.

In step 96, the neural network model is updated based on the predicted loss. In this way, the neural network model is trained by predicting the task of classifying sample objects.

In summary, in the solution of an embodiment of the present specification, a dynamic interaction diagram is constructed based on a set of interaction events, and the dynamic interaction diagram reflects the timing relationship of each interaction event and the mutual influence between interactive objects transmitted through each interaction event. In addition, there are multiple interaction events occurring simultaneously in the above-mentioned interaction event set, and multiple nodes connected to multiple associated nodes are allowed to exist in the corresponding dynamic interaction graph, thereby enriching the relationship information contained in the dynamic interaction graph. Therefore, based on the subgraph related to the node corresponding to the interactive object to be analyzed in the dynamic interaction graph, the feature vector of the interactive object can be extracted. The feature vector obtained in this way introduces the influence of other interactive objects in each interactive event on it, so that the in-depth characteristics of the interactive object can be comprehensively expressed, and business processing can be better performed.

According to another embodiment, an apparatus for processing interactive data is provided. The apparatus can be deployed in any device, platform, or device cluster with computing and processing capabilities. Fig. 10 shows a schematic block diagram of an apparatus for processing interactive data according to an embodiment. As shown in FIG. 10, the processing device 100 includes:

The interaction graph obtaining unit 101 is configured to obtain a dynamic interaction graph constructed according to a set of interaction events, wherein the set of interaction events includes a plurality of interaction events, and each interaction event includes at least two objects on which the interaction behavior occurs and the interaction time; The dynamic interaction graph includes any first node, the first node corresponds to the first object in the interaction event that occurs at the first time, and the first node points to the M corresponding to the N associated events through the connecting edge. Associated nodes, the N associated events all occur at a second time, and all include the first object as one of the interactive objects, and the second time is backtracking from the first time, the The time before the interaction of the first object occurs; the dynamic interaction graph includes at least one multi-node with the number of associated nodes greater than two; the subgraph determining unit 102 is configured to determine a relationship with the first target in the dynamic interaction graph A first target subgraph corresponding to a node, where the first target subgraph includes nodes within a predetermined range that start from the first target node and reach via connecting edges; the subgraph processing unit 103 is configured to be based on the first target node. The node features of each node included in the target subgraph and the direction relationship of the connecting edges between the nodes determine the first feature vector corresponding to the first target node; the service processing unit 104 is configured to use at least the first The feature vector performs service processing related to the first target node.

In this case, the interaction graph obtaining unit 101 is specifically configured to: obtain an existing dynamic interaction graph constructed based on an existing set of interaction events; obtain P new interaction events that occurred at the first update time; There are 2P new nodes added to the dynamic interaction graph, and the 2P new nodes respectively correspond to the two objects included in each new interaction event in the P new interaction events; for each new node, if If there is an associated node, add a connecting edge from the newly added node to its associated node.

In another embodiment, the M associated nodes are N+1 nodes, which respectively correspond to the N other objects interacting with the first object in the N associated events, and the first object itself .

In this case, the interaction graph acquiring unit 101 is specifically configured to: acquire an existing dynamic interaction graph constructed based on an existing interaction event set; acquire P new interaction events that occur at the first update time; determine the P Q different objects involved in new interactive events; add Q new nodes to the existing dynamic interaction graph, and the Q new nodes correspond to the Q different objects; for each new Add a node, if it has an associated node, add a connecting edge from the newly added node to its associated node.

In a possible implementation manner, the first target node is a node: in the dynamic interaction graph, there is no connecting edge pointing to the node.

According to an embodiment, the nodes within the predetermined range include: nodes within a connecting edge of a preset order K; and/or nodes whose interaction time is within a preset time range.

In one embodiment, each interaction event may also include the event characteristics of the interaction event; in this case, the node characteristics of each node may include the attribute characteristics of the object corresponding to each node, and the interaction event where each node is located. The characteristics of the event.

According to an embodiment, the service processing unit 104 is configured to predict the classification category of the object corresponding to the first target node according to the first feature vector.

According to an embodiment, the subgraph determining unit 102 is further configured to determine, in the dynamic interaction graph, a second target subgraph corresponding to a second target node, and the second target subgraph includes the subgraph from the The second target node starts and arrives at the nodes within the predetermined range via the connecting edge; the sub-graph processing unit 103 is further configured to be based on the node characteristics of each node included in the second target sub-graph, and the number of nodes The directional relationship of the connecting edges between the two determines the second feature vector corresponding to the second target node.

Based on this implementation manner, the service processing unit 104 may be further configured to predict whether the objects represented by the first target node and the second target node will meet according to the first feature vector and the second feature vector. Interaction occurs.

In an embodiment, the first target node and the second target node are two nodes corresponding to the first interaction event; at this time, the service processing unit 104 may be configured to, according to the first feature vector and the first feature vector The second feature vector predicts the event category of the first interaction event.

According to one embodiment, the sub-graph processing unit 103 is configured to input the first target sub-graph into a pre-trained neural network model, and the neural network model is based on each node contained in the first target sub-graph And output the first feature vector.

Further, in different embodiments, the neural network model may include one of the following: a neural network model based on LSTM, a neural network model based on RNN, and a neural network model based on Transformer.

Through the above device, the interactive objects are processed based on the dynamic interaction graph, and feature vectors suitable for subsequent analysis are obtained.

According to another embodiment, there is also provided a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the method described in conjunction with FIG. 3.

According to an embodiment of still another aspect, there is also provided a computing device, including a memory and a processor, the memory is stored with executable code, and when the processor executes the executable code, it implements the method described in conjunction with FIG. 3 method.

Those skilled in the art should be aware that, in one or more of the foregoing examples, the functions described in this application can be implemented by hardware, software, firmware, or any combination thereof. When implemented by software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on the computer-readable medium.

The specific implementations described above further describe the purpose, technical solutions and beneficial effects of this application in detail. It should be understood that the above are only specific implementations of this application and are not intended to limit the scope of this application. The scope of protection, any modification, equivalent replacement, improvement, etc. made on the basis of the technical solution of this application shall be included in the scope of protection of this application.

Claims

A method for processing interactive data, the method comprising:

Acquire a dynamic interaction diagram constructed according to an interaction event set, wherein the interaction event set includes a plurality of interaction events, each interaction event includes at least two objects where the interaction behavior occurs and the interaction time; the dynamic interaction diagram includes any The first node, the first node corresponds to the first object in the interaction event occurring at the first time, the first node points to the M associated nodes corresponding to the N associated events through the connecting edge, and the N The associated events all occur at the second time, and they all include the first object as one of the interactive objects. The second time is, going back from the first time, before the first object interacts. At a time; the dynamic interaction graph includes at least one multi-node with more than 2 associated nodes;

In the dynamic interaction graph, determining a first target subgraph corresponding to a first target node, where the first target subgraph includes nodes within a predetermined range starting from the first target node and arriving via a connecting edge;

Determine the first feature vector corresponding to the first target node based on the node characteristics of each node included in the first target subgraph and the direction relationship of the connecting edges between the nodes;

At least the first feature vector is used to perform service processing related to the first target node.
The method according to claim 1, wherein the object includes a user, and the interaction event includes at least one of the following: a click event, a social event, and a transaction event.
The method according to claim 1, wherein the M associated nodes are 2N nodes, respectively corresponding to two objects included in each associated event in the N associated events.
The method according to claim 3, wherein said obtaining a dynamic interaction graph constructed according to a set of interaction events comprises:

Obtain an existing dynamic interaction diagram constructed based on an existing interaction event set;

Obtain P new interaction events that occurred at the first update time;

Adding 2P newly-added nodes to the existing dynamic interaction graph, the 2P newly-added nodes respectively corresponding to two objects included in each newly-added interaction event in the P newly-added interaction events;

For each newly added node, if there is an associated node, add a connecting edge from the newly added node to its associated node.
The method according to claim 1, wherein the M associated nodes are N+1 nodes, respectively corresponding to the N other objects interacting with the first object in the N associated events, and the The first object itself.
The method according to claim 5, wherein said obtaining a dynamic interaction graph constructed according to a set of interaction events comprises:

Obtain an existing dynamic interaction diagram constructed based on an existing interaction event set;

Obtain P new interaction events that occurred at the first update time;

Determine Q different objects involved in the P new interaction events;

Adding Q new nodes to the existing dynamic interaction graph, the Q new nodes respectively corresponding to the Q different objects;

For each newly added node, if there is an associated node, add a connecting edge from the newly added node to its associated node.
The method according to claim 1, wherein the first target node is a node in which there is no connecting edge pointing to the node in the dynamic interaction graph.
The method according to claim 1, wherein the nodes within the predetermined range include:

Nodes within the connecting edges of the preset order K; and/or

Nodes whose interaction time is within the preset time range.
The method according to claim 3, wherein each interaction event further comprises an event characteristic of the interaction event;

The node characteristics of each node include the attribute characteristics of the object corresponding to each node, and the event characteristics of the interaction event where each node is located.
The method according to claim 1, wherein at least using the first feature vector to perform service processing related to the first target node comprises:

According to the first feature vector, the classification category of the object corresponding to the first target node is predicted.
The method according to claim 1, further comprising:

In the dynamic interaction graph, a second target subgraph corresponding to a second target node is determined, and the second target subgraph includes information within the predetermined range that starts from the second target node and arrives via a connecting edge. node;

The second feature vector corresponding to the second target node is determined based on the node characteristics of each node included in the second target subgraph and the direction relationship of the connecting edges between the nodes.
The method according to claim 11, wherein at least using the first feature vector to perform service processing related to the first target node comprises:

According to the first feature vector and the second feature vector, predict whether the objects represented by the first target node and the second target node will interact.
The method according to claim 11, wherein the first target node and the second target node are two nodes corresponding to a first interaction event; at least the first feature vector is used to communicate with the first The business processing related to the target node includes,

According to the first feature vector and the second feature vector, the event category of the first interaction event is predicted.
The method according to claim 1, wherein determining the first feature vector corresponding to the first target node comprises inputting the first target subgraph into a pre-trained neural network model, the neural network model being based on the The node feature of each node included in the first target subgraph and the direction relationship of the connecting edge between the nodes are outputted as the first feature vector.
The method according to claim 14, wherein the neural network model comprises one of the following: a neural network model based on LSTM, a neural network model based on RNN, and a neural network model based on Transformer.
A device for processing interactive data, the device comprising:

The interaction diagram obtaining unit is configured to obtain a dynamic interaction diagram constructed according to a set of interaction events, wherein the set of interaction events includes a plurality of interaction events, and each interaction event includes at least two objects on which the interaction behavior occurs and the interaction time; The dynamic interaction graph includes any first node, the first node corresponds to the first object in the interaction event occurring at the first time, and the first node points to M corresponding to the N associated events through the connecting edge. Associated node, the N associated events all occur at the second time, and all include the first object as one of the interactive objects, the second time is, going back from the first time, the first time The time before the interaction of an object; the dynamic interaction graph includes at least one multi-node with more than 2 associated nodes;

The subgraph determining unit is configured to determine, in the dynamic interaction graph, a first target subgraph corresponding to a first target node, the first target subgraph includes starting from the first target node and arriving via a connecting edge Nodes within the predetermined range;

A subgraph processing unit configured to determine a first feature vector corresponding to the first target node based on the node characteristics of each node included in the first target subgraph and the direction relationship of the connecting edges between the nodes;

The service processing unit is configured to use at least the first feature vector to perform service processing related to the first target node.
The device according to claim 16, wherein the object includes a user, and the interaction event includes at least one of the following: a click event, a social event, and a transaction event.
The apparatus according to claim 16, wherein the M associated nodes are 2N nodes, respectively corresponding to two objects included in each associated event in the N associated events.
The apparatus according to claim 18, wherein the interaction graph obtaining unit is configured to:

Obtain an existing dynamic interaction diagram constructed based on an existing interaction event set;

Obtain P new interaction events that occurred at the first update time;

Adding 2P newly-added nodes to the existing dynamic interaction graph, the 2P newly-added nodes respectively corresponding to two objects included in each newly-added interaction event in the P newly-added interaction events;

For each new node, if there is an associated node, add a connecting edge from the new node to its associated node.
The apparatus according to claim 16, wherein the M associated nodes are N+1 nodes, respectively corresponding to N other objects interacting with the first object in the N associated events, and the The first object itself.
The apparatus according to claim 20, wherein the interaction graph obtaining unit is configured to:

Obtain an existing dynamic interaction diagram constructed based on an existing interaction event set;

Obtain P new interaction events that occurred at the first update time;

Determine Q different objects involved in the P new interaction events;

Adding Q new nodes to the existing dynamic interaction graph, the Q new nodes respectively corresponding to the Q different objects;

For each newly added node, if there is an associated node, add a connecting edge from the newly added node to its associated node.
The apparatus according to claim 16, wherein the first target node is a node: in the dynamic interaction graph, there is no connecting edge pointing to the node.
The apparatus according to claim 16, wherein the nodes within the predetermined range comprise:

Nodes within the connecting edges of the preset order K; and/or

Nodes whose interaction time is within the preset time range.
The apparatus according to claim 18, wherein each interaction event further comprises an event characteristic of the interaction event;

The node characteristics of each node include the attribute characteristics of the object corresponding to each node, and the event characteristics of the interaction event where each node is located.
The apparatus according to claim 16, wherein the service processing unit is configured to predict the classification category of the object corresponding to the first target node according to the first feature vector.
The device according to claim 16, wherein:

The subgraph determining unit is further configured to determine, in the dynamic interaction graph, a second target subgraph corresponding to a second target node, where the second target subgraph includes starting from the second target node through Nodes within the predetermined range reached by the connecting edge;

The sub-graph processing unit is further configured to determine a second characteristic corresponding to the second target node based on the node characteristics of each node included in the second target sub-graph and the direction relationship of the connecting edges between the nodes vector.
The apparatus according to claim 26, wherein the service processing unit is configured to predict the objects represented by the first target node and the second target node based on the first feature vector and the second feature vector Whether interaction will occur.
The apparatus according to claim 26, wherein the first target node and the second target node are two nodes corresponding to a first interaction event; and the service processing unit is configured to, according to the first feature vector And the second feature vector to predict the event category of the first interaction event.
The apparatus according to claim 16, wherein the sub-graph processing unit is configured to input the first target sub-graph into a pre-trained neural network model, and the neural network model is based on the first target sub-graph The node features of each node included and the direction relationship of the connecting edges between the nodes are output, and the first feature vector is output.
The device according to claim 29, wherein the neural network model comprises one of the following: a neural network model based on LSTM, a neural network model based on RNN, and a neural network model based on Transformer.
A computer-readable storage medium having a computer program stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the method according to any one of claims 1-15.
A computing device, comprising a memory and a processor, characterized in that executable code is stored in the memory, and when the processor executes the executable code, the device described in any one of claims 1-15 is implemented method.