Target object portrait construction method, system and storage medium

Abstract

The present invention discloses a method, system and storage medium for constructing a target object portrait, which is applied to the field of information technology and can dynamically update the target object portrait in real time and effectively improve the accuracy of the target object portrait. The method includes: analyzing the target object's use behavior events and constructing behavior event data; wherein the behavior event data includes a number of target object behavior events; creating a first behavior tree according to the behavior event data; wherein the first behavior tree includes a number of behavior nodes, and the behavior nodes correspond to the target object behavior events; obtaining the target object behavior data through a preset event-driven model, so as to update the first behavior tree according to the target object behavior data and generate a second behavior tree; and constructing the target object portrait by analyzing the second behavior tree.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a method, system and storage medium for constructing a target object portrait. Background Art

[0002] With the advent of the big data era, target object portraits are increasingly valued in different products and dimensions. In actual application scenarios, knowing and understanding the target object has become the key to core competitiveness. In related technologies, target object portraits are mainly constructed by obtaining the target object attributes or behavioral characteristics of the target object. Massive target object data is required to accurately locate the target object's needs. Therefore, the above technical problems need to be solved urgently. Summary of the invention

[0003] In order to solve at least one of the above technical problems, the present invention proposes a target object portrait construction method, system and storage medium, which can dynamically update the target object portrait in real time and effectively improve the accuracy of the target object portrait.

[0004] In one aspect, an embodiment of the present invention provides a method for constructing a target object portrait, comprising the following steps:

[0005] Analyze the target object's usage behavior events to construct behavior event data; wherein the behavior event data includes a number of target object behavior events;

[0006] Creating a first behavior tree according to the behavior event data; wherein the first behavior tree includes a plurality of behavior nodes, and the behavior nodes correspond to the target object behavior events;

[0007] Acquire target object behavior data through a preset event-driven model, so as to update the first behavior tree according to the target object behavior data and generate a second behavior tree;

[0008] The target object portrait is constructed by analyzing the second behavior tree.

[0009] According to some embodiments of the present invention, the preset event-driven model includes an intermediary topology;

[0010] The updating the first behavior tree according to the target object behavior data to generate a second behavior tree includes:

[0011] Each behavior event in the target object behavior data is sent to an initial event queue, and managed and controlled through an event intermediary to select the corresponding behavior node in the first behavior tree to generate the second behavior tree; wherein the event intermediary includes a control node of the first behavior tree, and the node type of the control node includes a selection node.

[0012] According to some embodiments of the present invention, the managing and controlling through an event mediator to select the corresponding behavior node in the first behavior tree to generate the second behavior tree includes:

[0013] Generate corresponding pending events through the event mediator according to each behavior event in the initial event queue, and send them to the corresponding event channel, so that the pending events are processed by the corresponding event processor to obtain the execution result;

[0014] The structure of the first behavior tree is updated according to the execution result to generate the second behavior tree.

[0015] According to some embodiments of the present invention, constructing the target object portrait by analyzing the second behavior tree includes:

[0016] A target object behavior pattern analysis is performed through a target object portrait processor according to the second behavior tree and the execution result to generate the target object portrait.

[0017] According to some embodiments of the present invention, before executing the step of sending each behavior event in the target object behavior data to the initial event queue, the method further includes:

[0018] Perform preset data processing on the target object behavior data to obtain conversion data; wherein the preset data processing includes data cleaning and data format conversion.

[0019] According to some embodiments of the present invention, before executing the step of processing the event to be processed by the corresponding event processor to obtain an execution result, the method further includes:

[0020] Determine whether the event to be processed meets the precondition;

[0021] When it is determined that the event to be processed meets the precondition, the corresponding event to be processed is received by the event processor.

[0022] According to some embodiments of the present invention, when determining that the event to be processed satisfies the precondition, receiving the corresponding event to be processed through the event processor includes:

[0023] When it is determined that the event to be processed meets a first preset condition, the event to be processed corresponding to the event is received by the event processor; wherein the first preset condition includes execution success or execution failure;

[0024] Alternatively, when the event to be processed meets a second preset condition, the corresponding event to be processed is received by the event processor; wherein the second preset condition includes sub-conditions that meet a preset number.

[0025] On the other hand, an embodiment of the present invention further provides a target object portrait construction system, including:

[0026] The first module is used to analyze the target object's usage behavior events and construct behavior event data; wherein the behavior event data includes a number of target object behavior events;

[0027] A second module is used to create a first behavior tree according to the behavior event data; wherein the first behavior tree includes a plurality of behavior nodes, and the behavior nodes correspond to the target object behavior events;

[0028] A third module is used to obtain target object behavior data through a preset event-driven model, so as to update the first behavior tree according to the target object behavior data and generate a second behavior tree;

[0029] The fourth module is used to construct the target object portrait by analyzing the second behavior tree.

[0030] On the other hand, an embodiment of the present invention further provides a target object portrait construction system, including:

[0031] at least one processor;

[0032] at least one memory for storing at least one program;

[0033] When the at least one program is executed by the at least one processor, the at least one processor implements the target object portrait construction method as described in the above embodiment.

[0034] On the other hand, an embodiment of the present invention further provides a computer storage medium, which stores a program executable by a processor, and the program executable by the processor is used to implement the method for constructing a target object portrait as described in the above embodiment when executed by the processor.

[0035] According to a method, system and storage medium for constructing a target object portrait according to an embodiment of the present invention, there are at least the following beneficial effects: the embodiment of the present invention first analyzes the target object's usage behavior events and constructs behavior event data. Among them, the behavior event data in the embodiment of the present invention includes several target object behavior events. Then, the embodiment of the present invention creates a first behavior tree including several behavior nodes according to the behavior event data, and the behavior nodes correspond to the target object behavior events. Further, the embodiment of the present invention obtains the target object behavior data through a preset event-driven model to update the constructed first behavior tree according to the target behavior data, thereby generating a second behavior tree, and then the target object portrait can be constructed by analyzing the second behavior tree, which effectively improves the accuracy of the target object portrait. In addition, the embodiment of the present invention can respond to the behavior of the target object in real time through the event-driven behavior tree, thereby realizing real-time dynamic update of the target object portrait, and can dynamically adjust the behavior tree according to the behavior changes of the target object, so that the target object portrait is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 is a flow chart of a method for constructing a target object portrait provided by an embodiment of the present invention;

[0037] Figure 2 It is a schematic flow chart of the steps of updating a first behavior tree according to target object behavior data to generate a second behavior tree provided by an embodiment of the present invention;

[0038] Figure 3 It is a schematic flow chart of steps for performing management control through an event intermediary to select a corresponding behavior node in a first behavior tree and generate a second behavior tree, provided by an embodiment of the present invention;

[0039] Figure 4 It is a schematic flow chart of steps for constructing a target object portrait by analyzing the second behavior tree provided by an embodiment of the present invention;

[0040] Figure 5 is a schematic diagram of a step flow of an event processor provided by an embodiment of the present invention receiving a corresponding event to be processed;

[0041] Figure 6 It is a schematic diagram of the steps of obtaining target object behavior data through a preset event-driven model provided by an embodiment of the present invention;

[0042] Figure 7 It is a schematic diagram of the target object portrait construction system architecture provided by an embodiment of the present invention;

[0043] Figure 8 It is a schematic diagram of an application scenario of a target object binding device provided by an embodiment of the present invention;

[0044] Fig. 9 This is a modular schematic diagram of a target object portrait construction system provided by an embodiment of the present invention.

[0045] Fig.10 It is a principle block diagram of the target object portrait construction system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The embodiments described in the embodiments of this application should not be regarded as limitations of this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0047] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0049] Before introducing the embodiments of the present application, the relevant terms involved in the present application are first explained.

[0050] Tree structure: It is a non-linear data structure consisting of nodes and edges. Each node can have multiple child nodes, but only one parent node. Tree structures are usually used to represent hierarchical relationships. Accordingly, the root node of the tree structure is unique and has no parent node, while the leaf node is a node without child nodes.

[0051] Target object portrait: also known as user portrait, refers to a method of depicting the characteristics and features of the target object by analyzing and mining the multi-dimensional data of the target object.

[0052] Event-driven model: a computing model that drives the execution of a program based on the occurrence of events and corresponding processing. It is triggered by the occurrence of external events rather than in a fixed order or time interval. Accordingly, in the event-driven model, the program is usually managed by an event loop. Among them, the event loop will constantly monitor the occurrence of events and select the corresponding handler for processing according to the type of event and related information.

[0053] With the advent of the big data era, target object portraits are increasingly valued in different products and dimensions. In actual application scenarios, knowing and understanding the target object has become the key to core competitiveness. In related technologies, target object portraits are mainly constructed by obtaining the target object attributes or behavioral characteristics of the target object. Massive target object data is required to accurately locate the target object's needs. Therefore, the above technical problems need to be solved urgently.

[0054] An embodiment of the present invention provides a method, system and storage medium for constructing a target object portrait, which can dynamically update the target object portrait in real time and effectively improve the accuracy of the target object portrait. Figure 1 The method of the embodiment of the present invention includes but is not limited to step S110, step S120, step S130 and step S140.

[0055] Specifically, the method application process of the embodiment of the present invention includes but is not limited to the following steps:

[0056] S110: Analyze the target object's usage behavior events and construct behavior event data, wherein the behavior event data includes a number of target object behavior events.

[0057] S120: Create a first behavior tree according to the behavior event data, wherein the first behavior tree includes a plurality of behavior nodes, and the behavior nodes correspond to the target object behavior events.

[0058] S130: Acquire target object behavior data through a preset event-driven model, update the first behavior tree according to the target object behavior data, and generate a second behavior tree.

[0059] S140: Analyze the second behavior tree to construct a target object portrait.

[0060] During the working process of this specific embodiment, the embodiment of the present invention first analyzes the target object usage behavior events to construct behavior event data. Specifically, the behavior event data in the embodiment of the present invention includes several target object behavior events. Among them, the target object usage behavior events in the embodiment of the present invention refer to the operation behaviors of the target object when performing related operations, such as clicking, browsing, and sliding. Correspondingly, the target object behavior events in the embodiment of the present invention refer to some events that the target object may perform in the system by classifying and arranging the target object usage behavior events, such as binding devices, verifying devices, and querying events. The embodiment of the present invention defines the events that may occur in the system by classifying and arranging the target object usage behavior events, thereby constructing corresponding behavior event data. Then, the embodiment of the present invention creates a first behavior tree according to the behavior event data. Specifically, the first behavior tree in the embodiment of the present invention includes several behavior nodes, and these behavior nodes correspond to the target object behavior events. It is easy to understand that the embodiment of the present invention describes the behavior of the target object through the first behavior tree. Among them, each behavior node of the first behavior tree in the embodiment of the present invention represents a target object behavior event, that is, each node of the first behavior tree represents a target object behavior. Accordingly, the connection between behavior nodes in the embodiment of the present invention represents the relationship between the two behavior nodes.

[0061] Further, the embodiment of the present invention obtains the target object behavior data through a preset event-driven model, so as to update the first behavior tree according to the target object behavior data and generate a second behavior tree. Specifically, the target object behavior data in the embodiment of the present invention refers to the event data triggered by the target object behavior. Correspondingly, the preset event-driven model in the embodiment of the present invention refers to a model that drives the program through the occurrence and processing of events. Among them, the embodiment of the present invention updates the first behavior tree by using the target object behavior data as an event input, thereby generating a second behavior tree. For example, when the embodiment of the present invention monitors an event occurrence in the first behavior tree through the preset event-driven model, the target object behavior data is obtained. The embodiment of the present invention finds the corresponding behavior node in the first behavior tree according to the target object behavior data to update the state of the behavior node, thereby updating the first behavior tree and generating a second behavior tree. Finally, the embodiment of the present invention constructs a target object portrait by analyzing the second behavior tree. Specifically, the embodiment of the present invention analyzes the second behavior tree to understand the user's behavior pattern, extracts and describes the corresponding target object behavior and features, and then constructs a target object portrait, which effectively improves the accuracy of the target object portrait. It is easy to understand that the embodiment of the present invention can respond to the behavior of the target object in real time and update the target object portrait in real time by constructing the behavior tree through a preset event-driven model. In addition, the embodiment of the present invention can adjust and optimize the behavior tree according to the behavior changes of the target object by constructing the behavior tree through event-driven, thereby making the target object portrait more accurate. At the same time, the embodiment of the present invention can also construct a personalized target object portrait through an event-driven behavior tree, and construct a corresponding target object portrait according to the behavior of each target object.

[0062] It should be noted that in the embodiment of the present invention, the behavior tree is built by the preset event-driven module, and the target object portrait is built according to the built behavior tree, which can easily add new events and behaviors, so that the target object portrait can be expanded with the development of the business, and the scalability is poor. At the same time, the behavior tree can clearly show the behavior path of the target object, making the construction process of the target object portrait well explainable.

[0063] Combination Figure 1 , refer to Figure 2 In some embodiments of the present invention, the preset event-driven model includes an intermediary topology. Accordingly, in the embodiments of the present invention, updating the first behavior tree according to the target object behavior data to generate the second behavior tree includes but is not limited to the following steps:

[0064] S210: Send each behavior event in the target object behavior data to the initial event queue, and manage and control it through the event mediator to select the corresponding behavior node in the first behavior tree to generate a second behavior tree. The event mediator includes a control node of the first behavior tree, and the node type of the control node includes a selection node.

[0065] In this specific embodiment, the preset event-driven model in the embodiment of the present invention includes an intermediary topology. Among them, the intermediary topology is an architectural pattern for processing and transmitting time, which coordinates and processes events through an intermediary to achieve a loosely coupled system architecture. Specifically, the embodiment of the present invention first sends each behavior event in the target object behavior data to the initial event queue, and manages and controls it through the event intermediary to select the corresponding behavior node in the first behavior tree for update to generate a second behavior tree. Accordingly, the initial event queue in the embodiment of the present invention refers to an event queue composed of each target object behavior event obtained by the preset event-driven model. In addition, the event intermediary in the embodiment of the present invention is an important component of the preset event-driven model, and the workflow of the initial event is managed and controlled by the event intermediary. Among them, in the embodiment of the present invention, the event intermediary is used as the control node of the first behavior tree to determine the executed child node. Accordingly, due to the characteristics of the event intermediary, the control node type in the embodiment of the present invention is a selection node type. It is easy to understand that the embodiment of the present invention uses a preset event-driven model as the operating framework and an intermediary topology, namely a scheduler topology, to manage and control the workflow of the initial event through an event intermediary, thereby selecting the corresponding behavior node for updating and constructing a second behavior tree, which can respond to the target object behavior in real time and update the target object portrait in a timely manner.

[0066] Reference Figure 3 In some embodiments of the present invention, management control is performed through an event mediator to select a corresponding behavior node in the first behavior tree to generate a second behavior tree, including but not limited to the following steps:

[0067] S310: Generate corresponding to-be-processed events through an event intermediary according to each behavior event in the initial event queue, and send them to corresponding event channels, so that the to-be-processed events are processed by corresponding event processors to obtain execution results.

[0068] S320: Update the structure of the first behavior tree according to the execution result, and generate a second behavior tree.

[0069] In this specific embodiment, the embodiment of the present invention first generates corresponding pending events through an event intermediary according to each behavior event in the initial event queue. Specifically, in the embodiment of the present invention, the pending events are generated by the event intermediary according to the corresponding behavior events in the initial event queue. Among them, the behavior events in the initial event queue are the initial event information, and the pending events are generated by the event intermediary, but the pending events are not the events obtained after the initial events are processed, but the event information corresponding to the initial events. Then, the embodiment of the present invention sends the pending events to the corresponding event channel, so that the pending events are processed by the corresponding event processor to obtain the execution result. Specifically, the event channel in the embodiment of the present invention is the connection between two behavior nodes defined in the behavior tree. Accordingly, after the initial event is sent to the initial event queue, the event intermediary manages each behavior event in the queue, generates the corresponding pending events, and controls the corresponding event processor to process it, and then sends the pending events to the corresponding event channel, so that the corresponding event processor receives the pending events and processes them, and returns the corresponding processing results, that is, the execution results. It is easy to understand that in the embodiment of the present invention, each behavior node has a corresponding node state, and the corresponding execution result needs to be returned after the behavior node is executed. Furthermore, the embodiment of the present invention updates the structure of the first behavior tree according to the returned execution result, thereby constructing a second behavior tree. Specifically, when a behavior event occurs in the system through the preset event-driven model, the embodiment of the present invention uses the behavior event as the initial event and generates it in the event queue, that is, the initial event queue, and the event mediator generates the corresponding pending event and controls the selection of the corresponding event processor for processing, that is, the corresponding behavior node is checked in the first behavior tree for processing, and then the state of the corresponding behavior node in the first behavior tree is updated according to the returned execution result, so as to update the structure of the first behavior tree, dynamically adjust and optimize the behavior tree, and effectively improve the accuracy of the target portrait.

[0070] Combination Figure 1 , refer to Figure 4 In some embodiments of the present invention, by analyzing the second behavior tree, a target object portrait is constructed, including but not limited to the following steps:

[0071] S410: Analyze the target object behavior pattern through the target object portrait processor according to the second behavior tree and the execution result, and generate a target object portrait.

[0072] In this specific embodiment, the embodiment of the present invention analyzes the second behavior tree and the execution results of each event processor through the target object portrait processor, thereby generating a target object portrait. Specifically, the target object portrait processor in the embodiment of the present invention refers to an event processor for performing target object portrait analysis. After the event mediator obtains feedback that each step is successfully executed, that is, after each of the previous steps is successfully confirmed, the embodiment of the present invention executes the target object portrait processor to understand the behavior pattern of the target object according to the updated second behavior tree, and at the same time, in combination with the processing results of each event processor, that is, the execution result, the behavior and characteristics of the target object are comprehensively analyzed, thereby generating a corresponding target object portrait. Exemplarily, when the event mediator in the embodiment of the present invention selects a node to be processed, a pending event A, a pending event B, and a pending event C, the embodiment of the present invention first selects the corresponding event channel through the event middle, thereby sending each event to the corresponding event processor for processing, and at the same time, after each event processor is processed, it returns a confirmation to the event mediator, that is, returns the execution result. Then, when the event mediator obtains the confirmation returned by each event processor, according to the corresponding execution result and the updated second behavior tree, the target object behavior pattern analysis is performed through the target object portrait processor, thereby generating a target object portrait.

[0073] In some embodiments of the present invention, before executing the step of sending each behavior event in the target object behavior data to the initial event queue, the target object portrait construction method provided by the embodiment of the present invention further includes but is not limited to the following steps:

[0074] Perform preset data processing on the target object behavior data to obtain conversion data. The preset data processing includes data cleaning and data format conversion.

[0075] In this specific embodiment, the target object behavior data acquired by the embodiment of the present invention needs to be updated and converted for subsequent processing and analysis. Specifically, after the target object behavior data is acquired by the embodiment of the present invention in an event-driven manner, the target behavior data is first preprocessed, that is, the preset data processing is performed to obtain the corresponding conversion data, thereby updating the initial event and converting the data into a format that can be analyzed. Accordingly, the preset data processing in the embodiment of the present invention includes data cleaning and data format conversion. Among them, data cleaning in the embodiment of the present invention refers to filtering, denoising, and error correction operations on the acquired original event data, that is, the target object behavior data, so as to ensure the accuracy and consistency of the data. For example, data cleaning in the embodiment of the present invention may include removing duplicate data, missing or abnormal value processing, and data error correction, etc., by removing duplicate data to alleviate the problem of repeated analysis and processing, and by interpolating or filling missing values ​​to alleviate the problem of missing data values, or by deleting or replacing abnormal values ​​to alleviate the problem of abnormal data values. In addition, the embodiment of the present invention can alleviate the errors or consistency problems in the data by performing data error correction on the target object behavior data. Accordingly, data format conversion in the embodiment of the present invention refers to converting the original event data, i.e., the target object behavior data, into a specific data format. For example, in the embodiment of the present invention, the target object behavior data can be converted into a data format through one of the conversion operations of data type conversion, data structure conversion, and data standardization, so as to facilitate the subsequent processing and analysis of the data. Among them, data type conversion in the embodiment of the present invention refers to converting the data type of the target object behavior data, such as converting character type data into numeric type data. Data structure conversion in the embodiment of the present invention refers to converting the target object behavior data from a certain data structure to a preset data structure. In addition, data standardization in the embodiment of the present invention refers to formatting the target object behavior data according to a preset standard to meet the needs of subsequent processing or storage. It is easy to understand that the embodiment of the present invention can effectively ensure data quality by performing preset data processing on the target object behavior data to obtain converted data, thereby reducing the cost of subsequent data analysis and improving data analysis efficiency.

[0076] Reference Figure 5 In some embodiments of the present invention, before executing the step of processing the event to be processed by the corresponding event processor to obtain the execution result, the target object portrait construction method provided by the embodiment of the present invention also includes but is not limited to the following steps:

[0077] S510: Determine whether the event to be processed meets the precondition.

[0078] S520: When it is determined that the event to be processed meets the precondition, the corresponding event to be processed is received through the event processor.

[0079] In this specific embodiment, before the event processor receives the pending event and processes it, the embodiment of the present invention first needs to determine whether the pending event meets the precondition. Specifically, the specific behaviors of the target object in the embodiment of the present invention are all materialized as corresponding behavior nodes in the behavior tree, that is, the corresponding event processor, and each behavior node is set with corresponding preconditions. Among them, the precondition in the embodiment of the present invention refers to the conditions that need to be met before establishing the relationship between the current node and the next node, that is, the prerequisites that need to be met to connect the event processor. Accordingly, when it is determined that the pending event meets the precondition, the embodiment of the present invention receives the corresponding pending event through the event processor, and then can verify or process the corresponding pending event. It is easy to understand that before the corresponding event processor receives the pending event, it first determines whether the current state of the condition meets the implementation state of the event processor through the precondition, etc. By judging the precondition, it can ensure that all behavior nodes are performing actual operation behaviors.

[0080] Combination Figure 5 , refer to Figure 6 In some embodiments of the present invention, when it is determined that the event to be processed meets the precondition, the corresponding event to be processed is received by the event processor, including but not limited to the following steps:

[0081] S610: When it is determined that the event to be processed meets the first preset condition, the event processor receives the corresponding event to be processed, wherein the first preset condition includes execution success or execution failure.

[0082] S620: When the event to be processed meets the second preset condition, the event processor receives the corresponding event to be processed, wherein the second preset condition includes a preset number of sub-conditions.

[0083] In this specific embodiment, the precondition of the embodiment of the present invention includes a first preset condition and a second preset condition. Among them, when the event to be processed meets the first preset condition or the second preset condition, the embodiment of the present invention receives the event to be processed through the corresponding event processor. Specifically, the first preset condition in the embodiment of the present invention includes successful execution or failed execution. It is easy to understand that the execution result in the first preset condition of the embodiment of the present invention only includes successful execution and failed execution, and no other operations are performed, that is, the precondition does not perform other operations other than success or failure, thereby ensuring that all behavior nodes are performing actual operation behaviors. In addition, the second preset condition in the embodiment of the present invention includes sub-conditions that meet a preset number. It is easy to understand that the precondition in the embodiment of the present invention may include several sub-conditions. When a preset number of sub-conditions in these sub-conditions meet the preset requirements, it is considered that the event to be processed meets the second preset condition, so that the corresponding event to be processed is received through the event processor. For example, in the embodiment of the present invention, the precondition includes 4 sub-conditions. Before receiving the event to be processed, the event processor first judges the 4 sub-conditions of the precondition to determine whether the event to be processed meets the precondition. If the condition threshold is three quarters, then when it is determined that three sub-conditions in the precondition are satisfied, it is considered that the event to be processed satisfies the second preset condition, and the corresponding event to be processed is received by the event processor. On the contrary, when it is determined that the number of sub-conditions that meet the conditions in the precondition is less than three quarters of the total number of sub-conditions, it is considered that the event to be processed does not meet the second preset condition, and the event processor does not accept the event to be processed. For another example, if the condition threshold is 2, then when it is determined that two or more sub-conditions in the precondition are satisfied, it is considered that the event to be processed meets the second preset condition, and the event processor receives the event to be processed. On the contrary, when the number of sub-conditions satisfied in the precondition is less than 2, it is considered that the event to be processed does not meet the second preset condition, so the event processor does not accept the event to be processed. It is easy to understand that the embodiment of the present invention can select the corresponding behavior node for event processing by judging through the precondition, and then update the relevant nodes of the behavior tree, realize dynamic adjustment and optimization of the behavior tree, and make the constructed target object portrait more accurate.

[0084] Reference Figure 7 , Figure 7: is a schematic diagram of the target object portrait construction system architecture provided by the present invention. Among them, the target object portrait construction system architecture of the embodiment of the present invention is constructed by a preset event-driven model to construct a highly scalable and high-performance application system. Correspondingly, the target object portrait construction system in the embodiment of the present invention adopts an intermediary topology structure to manage and control the workflow of the initial event through an event intermediary. At the same time, the embodiment of the present invention first analyzes and organizes the target object usage behavior events to construct behavior event data, including several target object behavior events, such as device verification, device binding, device login, etc. Then, the embodiment of the present invention creates a first behavior tree according to the behavior event data. Among them, the first behavior tree includes several behavior nodes, and each behavior node corresponds to each target object behavior event in the behavior event data. Then, the embodiment of the present invention obtains the target object behavior data through a preset event-driven model, that is, the preset event-driven model is used to monitor the events occurring in the system to receive the target object behavior data in an asynchronous manner. Correspondingly, after receiving the target object behavior data, the embodiment of the present invention updates the first behavior tree according to the target object behavior data to generate a second behavior tree. Specifically, after receiving the target object behavior event asynchronously, i.e., the target object behavior data, the embodiment of the present invention uses it as the initial time to start the entire event flow. First, the embodiment of the present invention sends each behavior event in the target object selection data to the event queue to obtain the initial event queue. Then, the embodiment of the present invention manages and controls each behavior event in the event queue through an event mediator, thereby selecting a corresponding event channel, and processing the behavior event through a corresponding behavior node processor, thereby updating the behavior nodes in the first behavior tree and generating a second behavior tree. Among them, the embodiment of the present invention generates corresponding pending events through an event mediator according to each behavior event in the initial event queue, and then sends it to the corresponding event channel, so that the pending events can be processed by the corresponding behavior node processor, i.e., the event processor. Correspondingly, each behavior node in the embodiment of the present invention will return the corresponding execution result to the event mediator after the processing is completed. In addition, any process of each behavior node in the embodiment of the present invention supports interrupt operation to support the selection node, i.e., the event mediator, to make selections and decisions. Then, the embodiment of the present invention updates the structure of the first behavior tree according to the returned execution result, and then constructs the second behavior tree.

[0085] In addition, before sending each behavior event in the target object behavior data to the initial event queue, the embodiment of the present invention first performs preset data processing on the target object behavior data to obtain corresponding conversion data. For example, the preset data processing in the embodiment of the present invention includes data cleaning or data format conversion. At the same time, before the event processor receives the corresponding pending event, the embodiment of the present invention first determines whether the pending event meets the precondition. When it is determined that the pending event meets the precondition, the event processor of the embodiment of the present invention receives the corresponding pending event. Specifically, the precondition in the embodiment of the present invention includes a first preset condition and a second preset condition. When the pending event meets one of the first preset condition or the second preset condition, the embodiment of the present invention receives the corresponding pending event through the event processor. Among them, the first preset condition in the embodiment of the present invention includes execution success or execution failure, and the second preset condition includes sub-conditions that meet a preset number. Finally, the embodiment of the present invention constructs a target object portrait by analyzing the second behavior tree. Among them, the embodiment of the present invention performs target object pattern analysis through the target object portrait processor according to the second behavior function and the corresponding execution result to construct a target object portrait.

[0086] For example, refer to Figure 8 , taking the application scenario of a target object binding device as an example, after the target object is bound to the device in the embodiment of the present invention, an initial event is generated through a preset event driving module, and the initial event is sent to a dedicated event channel connected between two nodes defined in the first behavior tree, so as to transmit event information through this event channel. Correspondingly, after receiving the initial event, the event intermediary in the embodiment of the present invention generates a corresponding pending event for verifying the device, and sends the pending event to the device verification event channel. Among them, before the device verification event processor receives the pending event, the embodiment of the present invention first determines whether it meets the precondition, and then preferentially determines whether the current state of the pending event meets the implementation state of the processor. Next, the embodiment of the present invention determines whether the type of the device is correct and whether the device has been bound to other target objects. When it is determined that the pending event meets the conditions, the device verification event processor receives and verifies the pending event, and then returns the execution result to the event intermediary, that is, returns the confirmation information. Similarly, the query room event processor and the binding device processor in the embodiment of the present invention also execute the above steps and return the corresponding execution results, which will not be repeated here. Furthermore, after the event mediator obtains the execution results of the previous steps that are successfully confirmed, the embodiment of the present invention continues to execute the target object portrait processor to analyze the characteristic information of the target object, and understand the behavior pattern of the target object according to the corresponding behavior tree, thereby constructing a corresponding target object portrait.

[0087] Reference Fig. 9An embodiment of the present invention further provides a target object portrait construction system, including:

[0088] The first module 710 is used to analyze the target object's usage behavior events and construct behavior event data, wherein the behavior event data includes a number of target object behavior events.

[0089] The second module 720 is used to create a first behavior tree according to the behavior event data, wherein the first behavior tree includes a plurality of behavior nodes, and the behavior nodes correspond to the target object behavior events.

[0090] The third module 730 is used to obtain the target object behavior data through a preset event-driven model, so as to update the first behavior tree according to the target object behavior data and generate a second behavior tree.

[0091] The fourth module 740 is used to construct a target object portrait by analyzing the second behavior tree.

[0092] The contents of the method embodiments of the present invention are all applicable to the system embodiments. The functions specifically implemented by the system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method.

[0093] Reference Fig.10 An embodiment of the present invention further provides a target object portrait construction system, including:

[0094] At least one processor 810.

[0095] At least one memory 820 is used to store at least one program.

[0096] When at least one program is executed by at least one processor 810, the at least one processor 810 implements the target object portrait construction method described in the above embodiment.

[0097] The contents of the method embodiments of the present invention are all applicable to the system embodiments. The functions specifically implemented by the system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method.

[0098] An embodiment of the present invention also provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are executed by one or more control processors, for example, to execute the steps of the target object portrait construction method described in the above embodiment.

[0099] The contents of the method embodiments of the present invention are all applicable to the system embodiments. The functions specifically implemented by the system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method.

[0100] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0101] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0102] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0103] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0104] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0105] It will be appreciated by those skilled in the art that all or some of the steps and systems in the disclosed method above may be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that may be used to store desired information and may be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0106] The step numbers in the above method embodiment are only provided for the convenience of explanation and description, and no limitation is imposed on the order of the steps. The execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0107] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the described embodiments. Technical personnel familiar with the field may make various equivalent modifications or substitutions without violating the spirit of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A method for constructing a target object portrait, characterized in that: The following steps are involved: Analyze the target object's usage behavior events to construct behavior event data; wherein the behavior event data includes a number of target object behavior events; Creating a first behavior tree according to the behavior event data; wherein the first behavior tree includes a plurality of behavior nodes, and the behavior nodes correspond to the target object behavior events; Acquire target object behavior data through a preset event-driven model, so as to update the first behavior tree according to the target object behavior data and generate a second behavior tree; By analyzing the second behavior tree, a target object portrait is constructed; Wherein, the preset event-driven model includes an intermediary topology structure; The updating the first behavior tree according to the target object behavior data to generate a second behavior tree includes: Send each behavior event in the target object behavior data to an initial event queue, and manage and control it through an event intermediary to select the corresponding behavior node in the first behavior tree to generate the second behavior tree; wherein the event intermediary includes a control node of the first behavior tree, and the node type of the control node includes a selection node; The managing and controlling through the event mediator to select the corresponding behavior node in the first behavior tree to generate the second behavior tree includes: Generate corresponding pending events through the event mediator according to each behavior event in the initial event queue, and send them to the corresponding event channel, so that the pending events are processed by the corresponding event processor to obtain the execution result; The structure of the first behavior tree is updated according to the execution result to generate the second behavior tree.

2. The target object portrait construction method according to claim 1, characterized in that: The step of constructing the target object portrait by analyzing the second behavior tree includes: A target object behavior pattern analysis is performed through a target object portrait processor according to the second behavior tree and the execution result to generate the target object portrait.

3. The target object portrait construction method according to claim 1, characterized in that: Before executing the step of sending each behavior event in the target object behavior data to the initial event queue, the method further includes: Perform preset data processing on the target object behavior data to obtain conversion data; wherein the preset data processing includes data cleaning and data format conversion.

4. The method for constructing a target object portrait according to claim 1, characterized in that: Before executing the step of processing the event to be processed by the corresponding event processor to obtain the execution result, the method further includes: Determine whether the event to be processed meets the precondition; When it is determined that the event to be processed meets the precondition, the corresponding event to be processed is received by the event processor.

5. The method for constructing a target object portrait according to claim 4, characterized in that: When it is determined that the event to be processed satisfies the precondition, receiving the corresponding event to be processed through the event processor includes: When it is determined that the event to be processed meets a first preset condition, the event to be processed corresponding to the event is received by the event processor; wherein the first preset condition includes execution success or execution failure; Alternatively, when the event to be processed meets a second preset condition, the corresponding event to be processed is received by the event processor; wherein the second preset condition includes sub-conditions that meet a preset number.

6. A target object portrait construction system, characterized in that: include: The first module is used to analyze the target object's usage behavior events and construct behavior event data; wherein the behavior event data includes a number of target object behavior events; A second module is used to create a first behavior tree according to the behavior event data; wherein the first behavior tree includes a plurality of behavior nodes, and the behavior nodes correspond to the target object behavior events; A third module is used to obtain target object behavior data through a preset event-driven model, so as to update the first behavior tree according to the target object behavior data and generate a second behavior tree; A fourth module is used to construct a portrait of the target object by analyzing the second behavior tree; Wherein, the preset event-driven model includes an intermediary topology structure; The updating the first behavior tree according to the target object behavior data to generate a second behavior tree includes: Send each behavior event in the target object behavior data to an initial event queue, and manage and control it through an event intermediary to select the corresponding behavior node in the first behavior tree to generate the second behavior tree; wherein the event intermediary includes a control node of the first behavior tree, and the node type of the control node includes a selection node; The managing and controlling through the event mediator to select the corresponding behavior node in the first behavior tree to generate the second behavior tree includes: Generate corresponding pending events through the event mediator according to each behavior event in the initial event queue, and send them to the corresponding event channel, so that the pending events are processed by the corresponding event processor to obtain the execution result; The structure of the first behavior tree is updated according to the execution result to generate the second behavior tree.

7. A target object portrait construction system, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the target object portrait construction method as described in any one of claims 1 to 5.

8. A computer storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to implement the target object portrait construction method as described in any one of claims 1 to 5 when executed by the processor.

Images