Target object determination method and device, equipment, storage medium and program product

Abstract

The invention provides a target object determination method and device, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the steps that behavior events of candidate objects in a target time period and first category labels of the candidate objects are acquired; matching the first category label of the candidate object with a preset target category label to obtain a first matching result; matching the behavior event of the candidate object with a preset target behavior event to obtain a second matching result; and screening a target object from the candidate objects based on the first matching result and the second matching result. Therefore, the efficiency and accuracy of determining the target object can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device, electronic device, computer-readable storage medium, and computer program product for determining a target object. Background Art

[0002] When selecting target groups, that is, determining target users, related technologies mostly first obtain user behavior data, then determine the user's portrait based on the user behavior data, and then select based on the user's portrait. Summary of the invention

[0003] The embodiments of the present application provide a method, device, electronic device and computer-readable storage medium for determining a target object, which can improve the efficiency and accuracy of determining the target object.

[0004] The technical solution of the embodiment of the present application is implemented as follows:

[0005] The present invention provides a method for determining a target object, the method comprising:

[0006] Obtaining behavioral events of a candidate object within a target time period and a first category label of the candidate object;

[0007] Matching the first category label of the candidate object with a preset target category label to obtain a first matching result;

[0008] Matching the behavior event of the candidate object with a preset target behavior event to obtain a second matching result;

[0009] Based on the first matching result and the second matching result, a target object is screened from the candidate objects.

[0010] The present application provides a device for determining a target object, the device comprising:

[0011] An acquisition module, used to acquire the behavior events of the candidate object within a target time period and the first category label of the candidate object;

[0012] A first matching module, used to match the first category label of the candidate object with a preset target category label to obtain a first matching result;

[0013] A second matching module, used for matching the behavior event of the candidate object with a preset target behavior event to obtain a second matching result;

[0014] A screening module is used to screen a target object from the candidate objects based on the first matching result and the second matching result.

[0015] An embodiment of the present application provides an electronic device, including:

[0016] A memory for storing executable instructions;

[0017] The processor is used to implement the target object determination method provided in the embodiment of the present application when executing the executable instructions stored in the memory.

[0018] An embodiment of the present application provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor will execute the method for determining a target object provided by the embodiment of the present application.

[0019] The embodiment of the present application provides a computer program product, which includes a computer program or a computer executable instruction, and the computer program or the computer executable instruction is stored in a computer-readable storage medium. The processor of the electronic device reads the computer executable instruction from the computer-readable storage medium, and the processor executes the computer executable instruction, so that the electronic device executes the target object determination method provided in the embodiment of the present application.

[0020] The embodiment of the present application provides a computer program product, which includes computer executable instructions, and the computer executable instructions are stored in a computer readable storage medium. The processor of the electronic device reads the computer executable instructions from the computer readable storage medium, and the processor executes the computer executable instructions, so that the electronic device executes the target object determination method provided in the embodiment of the present application.

[0021] The embodiments of the present application have the following beneficial effects:

[0022] The category label of the candidate object is matched with the target category label to obtain a first matching result, and the behavior event of the candidate object is matched with the target behavior event to obtain a second matching result, thereby screening the target object from the candidate objects based on the first matching result and the second matching result. In this way, in addition to considering the behavior event of the object, the category label of the object is also combined to determine the target user. Compared with the scheme in the related art that only selects the target user based on the user's behavior data, the efficiency and accuracy of determining the target object are improved; at the same time, determining the target user in combination with the category label of the object is equivalent to further refining the objects belonging to the same category label, thereby re-determining the target object, further improving the accuracy of the determined target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic diagram of the architecture of a target object determination system provided in an embodiment of the present application;

[0024] Figure 2 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0025] Figure 3 It is a flowchart of a method for determining a target object provided in an embodiment of the present application;

[0026] Figure 4 is a schematic diagram of a new interface for configuring object information of a target object provided in an embodiment of the present application;

[0027] Figure 5 It is a flowchart of the code generation process provided by the embodiment of the present application;

[0028] Figure 6 It is a flowchart of the code running process provided by the embodiment of the present application;

[0029] Figure 7 It is a schematic diagram of the association information of attributes, the association information of behavior events, and the association information of behavior sequences provided in the embodiments of the present application;

[0030] Figure 8 It is a schematic diagram of the process of circling a user provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0032] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will 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.

[0033] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0034] 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.

[0035] Before further describing the embodiments of the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations.

[0036] 1) Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. Artificial intelligence technology is an interdisciplinary subject that covers a wide range of fields, including both hardware-level and software-level technologies. Basic AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies.

[0037] 2) Client, also known as the user end, refers to the program corresponding to the server that provides local services to users. Except for some applications that can only run locally, it is generally installed on an ordinary client and needs to cooperate with the server to run, that is, it requires corresponding servers and service programs in the network to provide corresponding services. In this way, specific communication connections need to be established on the client and server sides to ensure the normal operation of the application.

[0038] 3) Groovy is a development language that can interact with Java and directly call Java class libraries. Groovy code snippets support dynamic loading, dynamic compilation, dynamic execution, and smooth integration with Java.

[0039] 4) Crowd bag refers to a group of people with similar characteristics.

[0040] 5) BitMAP is a compressed bitmap index. In the big data labeling platform, it is used to label and select people who meet the selection criteria. It can accelerate the calculation and compress the storage, with very good results.

[0041] 6) Redis is an open source in-memory database, also known as a data structure server. It supports a variety of data structures, such as strings, hash tables, lists, sets, etc., and provides rich functions and flexible configuration options. Redis is usually used as a cache, message queue, session storage, and is applied to real-time data analysis, real-time counting and other scenarios.

[0042] During the research process, the inventor found that the relevant technologies mostly select target groups based on user behavior data. However, users have other information besides behavior data. Selecting target users based only on user behavior data will result in low accuracy and efficiency in selecting target users.

[0043] Based on this, an embodiment of the present application provides a method for determining a target object. In addition to considering the behavioral data of the object, the category label of the object is also combined to determine the target user. Compared with the solution in the related art that only selects the target user based on the user's behavioral data, the efficiency and accuracy in determining the target object are improved; at the same time, determining the target user in combination with the category label of the object is equivalent to further refining the objects belonging to the same category label, thereby re-determining the target object, further improving the accuracy of the determined target object.

[0044] See also Figure 1 , Figure 1 It is an architectural diagram of a target object determination system provided in an embodiment of the present application. To realize an application scenario of target object determination, a terminal (terminal 400 is shown as an example) is connected to a server 200 via a network 300. The network 300 may be a wide area network or a local area network, or a combination of the two. The terminal 400 is used for users to use a client 401, which is displayed on a display interface (display interface 401-1 is shown as an example). The terminal 400 and the server 200 are connected to each other via a wired or wireless network.

[0045] The terminal 400 is used to send the behavior events of the candidate object within the target time period and the first category label of the candidate object to the server 200;

[0046] Server 200 is used to obtain the behavioral events of the candidate object within the target time period and the first category label of the candidate object; match the first category label of the candidate object with a preset target category label to obtain a first matching result; match the behavioral events of the candidate object with a preset target behavioral event to obtain a second matching result; and filter the target object from the candidate objects based on the first matching result and the second matching result.

[0047] In some embodiments, the server 200 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (CDN, Content Deliver Network), and big data and artificial intelligence platforms. The terminal 400 may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a set-top box, an intelligent voice interaction device, a smart home appliance, a vehicle-mounted terminal, an aircraft, and a mobile device (e.g., a mobile phone, a portable music player, a personal digital assistant, a dedicated messaging device, a portable gaming device, an intelligent speaker, and a smart watch), etc., but is not limited thereto. The terminal device and the server may be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiments of the present application.

[0048] See also Figure 2 , Figure 2 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. In practical applications, the electronic device can be Figure 1 The server 200 or terminal 400 shown, see Figure 2 , Figure 2 The electronic device shown includes: at least one processor 410, a memory 450, at least one network interface 420 and a user interface 430. The various components in the terminal 400 are coupled together via a bus system 440. It is understood that the bus system 440 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 440 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 440 is not shown in FIG. Figure 2 Various buses are labeled as bus system 440 .

[0049] Processor 410 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0050] The user interface 430 includes one or more output devices 431 that enable presentation of media content, including one or more speakers and / or one or more visual display screens. The user interface 430 also includes one or more input devices 432, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

[0051] The memory 450 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard disk drives, optical disk drives, etc. The memory 450 may optionally include one or more storage devices that are physically remote from the processor 410.

[0052] The memory 450 includes a volatile memory or a non-volatile memory, and may also include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), and the volatile memory may be a random access memory (RAM). The memory 450 described in the embodiments of the present application is intended to include any suitable type of memory.

[0053] In some embodiments, memory 450 can store data to support various operations, examples of which include programs, modules, and data structures, or a subset or superset thereof, as exemplarily described below.

[0054] Operating system 451, including system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks;

[0055] A network communication module 452, used to reach other electronic devices via one or more (wired or wireless) network interfaces 420, exemplary network interfaces 420 include: Bluetooth, Wireless Compatibility Certification (WiFi), and Universal Serial Bus (USB), etc.;

[0056] a presentation module 453 for enabling presentation of information via one or more output devices 431 (e.g., display screen, speaker, etc.) associated with the user interface 430 (e.g., a user interface for operating peripherals and displaying content and information);

[0057] The input processing module 454 is used to detect one or more user inputs or interactions from one of the one or more input devices 432 and translate the detected inputs or interactions.

[0058] In some embodiments, the device provided in the embodiments of the present application can be implemented in software. Figure 2The target object determination device 455 stored in the memory 450 is shown, which can be software in the form of a program and a plug-in, etc., and includes the following software modules: an acquisition module 4551, a first matching module 4552, a second matching module 4553 and a screening module 4554. These modules are logical, and therefore can be arbitrarily combined or further split according to the functions implemented. The functions of each module will be described below.

[0059] In other embodiments, the device provided in the embodiments of the present application can be implemented in hardware. As an example, the target object determination device provided in the embodiments of the present application can be a processor in the form of a hardware decoding processor, which is programmed to execute the target object determination method provided in the embodiments of the present application. For example, the processor in the form of a hardware decoding processor can adopt one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field programmable gate arrays (FPGAs) or other electronic components.

[0060] In some embodiments, the terminal or server can implement the target object determination method provided in the embodiment of the present application by running a computer program. For example, the computer program can be a native program or software module in the operating system; it can be a local (Native) application (APP, Application), that is, a program that needs to be installed in the operating system to run, such as an instant messaging APP, a web browser APP; it can also be a small program, that is, a program that can be run only by downloading it to a browser environment; it can also be a small program that can be embedded in any APP. In short, the above-mentioned computer program can be an application, module or plug-in in any form.

[0061] Based on the above description of the target object determination system and electronic device provided by the embodiment of the present application, the target object determination method provided by the embodiment of the present application is described below. In actual implementation, the target object determination method provided by the embodiment of the present application can be implemented by the terminal or the server alone, or by the terminal and the server in collaboration, so that Figure 1 The server 200 in the embodiment of the present application independently executes the method for determining the target object provided in the embodiment of the present application as an example. Figure 3 , Figure 3 is a flow chart of a method for determining a target object provided in an embodiment of the present application. Figure 3 The steps shown are explained.

[0062] Step 101: The server obtains the behavior events of the candidate object within a target time period and the first category label of the candidate object.

[0063] In actual implementation, the server receives a target object determination request carrying the object identification of a candidate object sent by the terminal, parses the target object determination request to determine the object identification of the candidate object, and then based on the object identification of the candidate object, collects the behavioral events of the candidate object within the target time period and the first category label of the candidate object in real time at a preset collection frequency.

[0064] It should be noted that the object identifier of the candidate object can be the ID of the candidate object, and the collection frequency corresponds to the target time period. When the collection frequency is once an hour, the target time period can be one hour, and when the collection frequency is once every two hours, the target time period is two hours. At the same time, the behavioral event of the candidate object within the target time period can be at least one behavioral event that the target object has performed in the past target time period, such as a cash withdrawal application, a consumption limit adjustment application, a credit account opening, a pop-up window click, a sign-in, etc.; and the first category label of the candidate object can indicate the category to which the candidate object belongs. For example, the object can be divided into multiple levels, such as ordinary users, silver card users, gold card users, etc., and different category labels correspond to different levels; or the object can be divided based on different businesses, and different category labels correspond to different businesses. The category label of the object indicates the business whose adaptability to the object reaches the adaptability threshold, such as the business that reaches the maximum adaptability, etc., and this is not limited in the embodiments of the present application.

[0065] In actual implementation, before obtaining the behavior events of the candidate object in the target time period and the first category label of the candidate object, it is also possible to obtain pre-set configuration information; parse the configuration information to obtain the pre-set target behavior events and target category labels. The process of obtaining the pre-set configuration information may be to receive the configuration information sent by the terminal; wherein the target behavior events and target category labels in the configuration information are input based on the display interface of the terminal.

[0066] It should be noted that the target behavior event and the target category label can be set based on the display interface of the terminal. Specifically, the terminal can display a new interface for configuring the object information of the target object. The object information of the target object can include the attribute information, behavior event, event sequence, category label, etc. of the target object; wherein the attribute information can be the age, mobile phone location, native place, gender, etc. of the target object, and the event sequence of the target object can be an event set of at least part of the behavior events performed by the target object within the target time period, determined based on the target execution order. For example, when the behavior events performed by the target object include browsing the web page, signing in, accepting tasks, cash withdrawal applications, consumption limit adjustment applications, credit account opening, pop-up window clicks, and signing in, the event sequence can be an event set formed by the three behavior events of browsing the web page, signing in, and accepting tasks, wherein browsing the web page is the first position in the event sequence, signing in is the second position in the event sequence, and accepting tasks is the third position in the event sequence. The behavior events and category labels are as described in the behavior events and the first category label in the previous text, and this embodiment of the present application will not be repeated.

[0067] For example, see Figure 4 , Figure 4 is a schematic diagram of a new interface for configuring object information of a target object provided in an embodiment of the present application, based on Figure 4 , the dotted box 401 indicates the target attribute information of the configured target object, the dotted box 402 indicates the configured target behavior event, the dotted box 403 indicates the target event sequence of the configured target object, and the dotted box 404 indicates the configured target category label.

[0068] It should be noted that after configuring the object information of the target object based on the new interface, you can also generate target code based on the configured object information. Specifically, after parsing the configuration information to obtain the pre-set target behavior events and target category labels, generate target code based on the target behavior events and target category labels, so as to execute the target object determination process by running the target code.

[0069] Among them, when the configuration information also includes at least one of the preset target attribute information and target event sequence, the target code will be generated in combination with the corresponding target attribute information and / or target event sequence, as well as the target behavior event and target category label.

[0070] In this way, the target behavior event, target category expression, target attribute information and target event sequence are directly set through the display interface, which improves the convenience and flexibility of determining the target object.

[0071] It should be noted that the first category label of the candidate object obtained is similar to the category label mentioned above, and the first category label is used to indicate that the category label is the current category label of the corresponding candidate object.

[0072] In some embodiments, before obtaining the behavioral events of the candidate object within the target time period and the first category label of the candidate object, it is also necessary to determine the candidate object, specifically, to obtain the attribute information of the second initial object; respectively match the attribute information of each second initial object with the pre-set target attribute information to obtain a third matching result; select the target third matching result whose matching degree reaches the target matching degree and determine the second initial object corresponding to the target third matching result as the candidate object.

[0073] It should be noted that the attribute information, as mentioned above, may be the age, mobile phone location, gender, etc. of the object, and the target attribute information is the pre-set age, mobile phone location, gender, etc.; and the target matching degree may also be pre-set, for example, it may be the maximum matching degree, etc.; at the same time, the number of target third matching results may be one or more, that is, the number of candidate objects may be one or more, and this is not limited in the embodiments of the present application.

[0074] In this way, by first performing preliminary screening of objects based on the attribute information of the second initial object, the number of objects required to be determined when determining the target object can be reduced, which not only improves the efficiency of determining the target object, but also improves the accuracy of determining the target object.

[0075] Step 102: Match the first category label of the candidate object with a preset target category label to obtain a first matching result.

[0076] It should be noted that the target category label is pre-set as described in the method above, which will not be elaborated here; and the process of matching the first category label of the candidate object with the pre-set target category label to obtain the first matching result, that is, matching the first category label of the candidate object with the pre-set target category label to obtain a first matching result indicating that the first category label of the candidate object is the same as the target category label, or obtaining a first matching result indicating that the first category label of the candidate object is different from the target category label; wherein the number of candidate objects can be one or more, when the number of candidate objects is multiple, the first category label of each candidate object is matched with the target category label respectively to obtain multiple first matching results, and then based on each first matching result, it is determined whether the corresponding candidate object is the target object.

[0077] Step 103: Match the behavior event of the candidate object with a preset target behavior event to obtain a second matching result.

[0078] In actual implementation, the second matching result is used to indicate whether the behavior event matches the target behavior event. Thus, the behavior event of the candidate object is matched with the preset target behavior event to obtain the second matching result. The process may be to match the behavior event with the target behavior event to obtain an event matching result. If there is an event matching result indicating that the corresponding behavior event matches the corresponding target behavior event, a second matching result indicating that the behavior event matches the target behavior event is obtained. If each event matching result indicates that the corresponding behavior event does not match the corresponding target behavior event, a second matching result indicating that the behavior event does not match the target behavior event is obtained.

[0079] It should be noted that the number of behavior events can be one or more, and the number of target behavior events can also be one or more; next, the situations when the number of behavior events is one or more, and the number of target behavior events is one or more, are explained respectively.

[0080] In some embodiments, when the number of behavioral events is one, the behavioral event of the candidate object is directly matched with a preset target behavioral event to obtain a second matching result indicating that the behavioral event matches the target behavioral event, or a second matching result indicating that the behavioral event does not match the target behavioral event.

[0081] Among them, the number of target behavior events can also be one or more. When the number of target behavior events is multiple, the number of second matching results obtained is also multiple. If the second matching result indicates that the behavior event matches the target behavior event, it means that there is a second matching result indicating that the behavior event matches the target behavior event, that is, the behavior event matches one of the target behavior events; if the second matching result indicates that the behavior event does not match the target behavior event, it means that each second matching result indicates that the behavior event does not match the target behavior event, that is, the behavior event does not match each target behavior event.

[0082] It should be noted that when the number of behavior events and the number of target behavior events are both one, an event matching result is obtained. In the above process, if each event matching result indicates that the corresponding behavior event does not match the corresponding target behavior event, a second matching result indicating that the behavior event does not match the target behavior event is obtained. This means that when this unique event matching result indicates that the corresponding behavior event does not match the corresponding target behavior event, a second matching result indicating that the behavior event does not match the target behavior event is obtained.

[0083] In other embodiments, when the number of behavior events is multiple, the number of behavior events is N, and the number of target behavior events is M, where N is an integer greater than 1 and M is a positive integer; thus, the process of matching the behavior events of the candidate object with the preset target behavior events to obtain the second matching result may be to match the N behavior events with the M target behavior events respectively to obtain M*N event matching results; when there is an event matching result indicating that the corresponding behavior event matches the corresponding target behavior event, that is, as long as there is a matching target behavior event for one behavior event, a second matching result indicating that the behavior event matches the target behavior event is obtained; when each event matching result indicates that the corresponding behavior event does not match the corresponding target behavior event, a second matching result indicating that the behavior event does not match the target behavior event is obtained.

[0084] It should be noted that matching N behavior events with M target behavior events respectively to obtain M*N event matching results means matching each behavior event with each target behavior event respectively, so that as long as there is an event matching result indicating that the corresponding behavior event has a matching target behavior event, a second matching result indicating that the behavior event matches the target behavior event is obtained;

[0085] Alternatively, the process of determining the second matching result indicating that the behavior event matches the target behavior event may also be, based on each event matching result, when each behavior event has a matching target behavior event, obtaining the second matching result indicating that the behavior event matches the target behavior event; when there is an event matching result indicating that the corresponding behavior event does not match the corresponding target behavior event, obtaining the second matching result indicating that the behavior event does not match the target behavior event. This embodiment of the application does not limit this.

[0086] Step 104: Filter the target object from the candidate objects based on the first matching result and the second matching result.

[0087] In actual implementation, the process of screening the target object from the candidate objects based on the first matching result and the second matching result may be that when the first category label of the candidate object represented by the first matching result matches the target category label, and the behavior event of the candidate object represented by the second matching result matches the target behavior event, the candidate object is determined as the target object; otherwise, the corresponding candidate object is not the target object.

[0088] In some embodiments, the target object can also be determined in combination with the number of executions of the behavior event. Specifically, after matching the behavior event of the candidate object with a preset target behavior event to obtain a second matching result, if the second matching result indicates that the behavior event matches the target behavior event, the number of executions of the behavior event and the number of executions of the target behavior event are obtained; the number of executions of the behavior event is compared with the number of executions of the target behavior event to obtain a first comparison result; thus, the process of screening the target object from the candidate objects based on the first matching result and the second matching result can be screening the target object from the candidate objects based on the first matching result, the second matching result and the first comparison result.

[0089] It should be noted that the number of executions corresponding to the target behavior event is pre-set. If the number of executions of the behavior event is not less than the number of executions corresponding to the target behavior event, a first comparison result indicating that the number of executions of the behavior event has reached the number of executions corresponding to the target behavior event is obtained. If the number of executions of the behavior event is less than the number of executions corresponding to the target behavior event, a first comparison result indicating that the number of executions of the behavior event has not reached the number of executions corresponding to the target behavior event is obtained.

[0090] Wherein, as mentioned above, the number of behavior events and target behavior events can be multiple, therefore, comparing the number of executions of the behavior event with the number of executions corresponding to the target behavior event is to compare the matching behavior event with the target behavior event; thus, when the number of executions of the behavior event reaches the number of executions of the corresponding target behavior event, a first comparison result is obtained to indicate that the number of executions of the behavior event reaches the number of executions corresponding to the target behavior event; when the number of executions of each behavior event does not reach the number of executions of the corresponding target behavior event, a first comparison result is obtained to indicate that the number of executions of the behavior event does not reach the number of executions corresponding to the target behavior event;

[0091] Alternatively, when the number of executions of each behavior event reaches the number of executions of the corresponding target behavior event, a first comparison result is obtained to indicate that the number of executions of the behavior event reaches the number of executions corresponding to the target behavior event; when the number of executions of a behavior event does not reach the number of executions of the corresponding target behavior event, a first comparison result is obtained to indicate that the number of executions of the behavior event does not reach the number of executions corresponding to the target behavior event. This embodiment of the application does not limit this.

[0092] It should be noted that when the second matching result indicates that the behavior event does not match the target behavior event, the execution times can no longer be compared, that is, the first comparison result is directly obtained that the execution times of the indicating behavior event do not reach the execution times corresponding to the target behavior event.

[0093] In this way, when a behavior event matches a target behavior event, the target object is determined by comparing the number of executions of the behavior event with the corresponding number of executions of the target behavior event. Compared with the solution of directly matching the behavior event with the target behavior event to obtain the detection result, this avoids the situation where the user only occasionally executes the corresponding behavior event, and improves the accuracy of the determined target object.

[0094] In actual implementation, the process of screening the target object from the candidate objects based on the first matching result, the second matching result and the first comparison result may be that if the candidate object is determined to meet the first target condition based on the first matching result, the second matching result and the first comparison result, the candidate object is selected as the target object; wherein the first target condition includes at least one of the following: the first category label is the same as the target category label; the behavior event matches the target behavior event; the behavior event matches the target behavior event, and the number of executions of the behavior event is not less than the number of executions of the matched target behavior event.

[0095] It should be noted that the process of determining whether the first category label is the same as the target category label, the process of determining whether the behavior event matches the target behavior event, and the process of determining whether the number of executions of the behavior event is not less than the number of executions of the matching target behavior event when the behavior event matches the target behavior event are as described above, and the embodiments of the present application will not be elaborated here.

[0096] In some embodiments, the target object can also be determined in combination with the behavior sequence of the candidate object. Specifically, after obtaining the behavior events performed by the candidate object and the category label of the candidate object, it is also possible to, if the number of behavior events performed by the candidate object is P, construct an event sequence corresponding to the P behavior events, where P is a positive integer greater than or equal to 2; match the event sequence with a pre-set target event sequence to obtain a fourth matching result; thereby, the process of screening the target object from the candidate objects based on the first matching result and the second matching result can be to screen the target object from the candidate objects based on the first matching result, the second matching result and the fourth matching result.

[0097] It should be noted that the event sequence is as described above and will not be repeated here; the process of constructing an event sequence corresponding to P behavioral events can be based on the behavioral events executed by the candidate object, and in accordance with the execution order of the candidate object, an event set is generated, and the event set is used as the event sequence executed by the candidate object. Among them, the behavioral events executed by the candidate object used when constructing the event sequence can be all the behavioral events executed by the candidate object, or can be part of the behavioral events executed by the candidate object, and this embodiment of the application does not limit this.

[0098] In actual implementation, the process of matching the event sequence with a preset target event sequence to obtain a fourth matching result may be to match the behavior events in the event sequence with the target behavior events in the target event sequence respectively to obtain a sequence matching result; if the sequence matching result indicates that there is a matching target behavior event for each behavior event, then based on the execution order of the behavior events and the execution order of the target behavior events, the fourth matching result is determined; wherein the fourth matching result is used to indicate whether the execution order of the event sequence is the same as the execution order of the target event sequence.

[0099] It should be noted that, since the event sequence includes multiple behavioral events and the target event sequence also includes multiple target behavioral events, the process of matching the behavioral events in the event sequence with the target behavioral events in the target event sequence to obtain sequence matching results is similar to the process of matching N behavioral events with M target behavioral events to obtain M*N event matching results as described above, which is not elaborated in the embodiments of the present application; at the same time, when the sequence matching result indicates that there are behavioral events that do not match the target behavioral events, a fourth matching result is directly obtained to indicate that the execution order of the event sequence is different from the execution order of the target event sequence.

[0100] In actual implementation, the behavioral events in the event sequence are matched with the target behavioral events in the target event sequence respectively. Before obtaining the sequence matching result, it is also possible to detect whether the event sequence is within the target time period. Only when the event sequence is within the target time period will the behavioral events in the event sequence be matched with the target behavioral events in the target event sequence respectively; for the process of detecting whether the event sequence is within the target time period, specifically, the first execution time of the first behavioral event in the event sequence and the second execution time of the last behavioral event are obtained, and the second execution time is subtracted from the first execution time to obtain a time difference. When the time difference is less than or equal to the time difference threshold, it is determined that the event sequence is within the target time period. When the time difference is greater than the time difference threshold, it is determined that the event sequence is not within the target time period.

[0101] It should be noted that the time difference threshold can be preset, for example, five minutes or half an hour, etc. In this way, only when the event sequence is within the target time period, the behavior events in the event sequence will be matched with the target behavior events in the target event sequence, ensuring the continuity of the behavior events in the event sequence executed by the object, thereby improving the accuracy of determining the target object in the subsequent process.

[0102] In actual implementation, the process of determining the fourth matching result based on the execution order of the behavior events and the execution order of the target behavior events may be to compare the execution order of each behavior event with the execution order of the matching target behavior event to obtain a second comparison result; if each second comparison result indicates that the execution order of the corresponding behavior event is the same as the execution order of the matching target behavior event, then a fourth matching result is obtained that indicates that the execution order of the event sequence is the same as the execution order of the target event sequence; if there is a second comparison result indicating that the execution order of the corresponding behavior event is different from the execution order of the matching target behavior event, then a fourth matching result is obtained that indicates that the execution order of the event sequence is different from the execution order of the target event sequence.

[0103] It should be noted that the process of comparing the execution order of each behavior event with the execution order of the matching target behavior event to obtain the second comparison result can be to compare the execution order of the behavior event with the matching target behavior event in the target event sequence from the first behavior event in the event sequence to obtain the second comparison result corresponding to the behavior event; when the second comparison result represents the execution order of the corresponding behavior event, which is the same as the execution order of the matching target behavior event, then compare the next behavior event with the execution order of the matching target behavior event in the target event sequence to obtain the second comparison result corresponding to the behavior event, and repeat this process until the last behavior event in the event sequence is reached, and a fourth matching result indicating that the execution order of the event sequence is the same as the execution order of the target event sequence is obtained;

[0104] Among them, in the above process, when the second comparison result represents the execution order of the corresponding behavior event, which is different from the execution order of the matching target behavior event, a fourth matching result is obtained to indicate that the execution order of the event sequence is different from the execution order of the target event sequence.

[0105] It should be noted that the number of event sequences and target event sequences may also be one or more. When the number of event sequences is multiple, the above process is performed for each event sequence, wherein when there is an event sequence whose execution order is the same as the execution order of the matched target event sequence, a fourth matching result indicating that the execution order of the event sequence is the same as the execution order of the target event sequence is obtained; and when the execution order of each event sequence is different from the execution order of the matched target event sequence, a fourth matching result indicating that the execution order of the event sequence is different from the execution order of the target event sequence is obtained;

[0106] Alternatively, when the execution order of each event sequence is the same as the execution order of the matching target event sequence, a fourth matching result is obtained to indicate that the execution order of the event sequence is the same as the execution order of the target event sequence; when there is an event sequence whose execution order is different from the execution order of the matching target event sequence, a fourth matching result is obtained to indicate that the execution order of the event sequence is different from the execution order of the target event sequence. This embodiment of the present application is not limited to this.

[0107] In actual implementation, the process of screening the target object from the candidate objects based on the first matching result, the second matching result and the fourth matching result may be that if it is determined that the candidate object satisfies the second target condition based on the first matching result, the second matching result and the fourth matching result, the candidate object is selected as the target object; wherein the second target condition includes at least one of the following: the first category label is the same as the target category label; the behavior event matches the target behavior event; the execution order of the event sequence is the same as the execution order of the target event sequence.

[0108] It should be noted that the process of determining whether the first category label is the same as the target category label, the process of determining whether the behavior event matches the target behavior event, and the process of releasing the execution order of the event sequence and the execution order of the target event sequence are the same, as described above, and the embodiments of the present application will not be elaborated here.

[0109] In this way, the target object is determined in combination with the execution order of the event sequence, which enriches the features used to determine the target object, and not only improves the efficiency of determining the target object, but also improves the accuracy of determining the target object.

[0110] In some embodiments, the target object can also be determined in combination with the behavior sequence of the candidate object and the number of executions of the behavior event. Specifically, after obtaining the behavior events executed by the candidate object and the category label of the candidate object, it is also possible to, when the second matching result indicates that the behavior event matches the target behavior event, obtain the number of executions of the behavior event and the number of executions corresponding to the target behavior event; compare the number of executions of the behavior event with the number of executions corresponding to the target behavior event to obtain a first comparison result; then, if the number of behavior events executed by the candidate object is P, construct an event sequence corresponding to the P behavior events, where P is a positive integer greater than or equal to 2; match the event sequence with a pre-set target event sequence to obtain a fourth matching result; thereby, based on the first matching result and the second matching result, the process of screening the target object from the candidate object can be, based on the first matching result, the second matching result, the fourth matching result and the first comparison result, screening the target object from the candidate object.

[0111] It should be noted that the process of comparing the number of executions of the behavior event with the number of executions corresponding to the target behavior event to obtain the first comparison result is as described above, and the process of constructing an event sequence corresponding to P behavior events and matching the event sequence with a pre-set target event sequence to obtain the fourth matching result is also as described above, and the embodiments of the present application will not be elaborated here.

[0112] Among them, for the process of screening the target object from the candidate objects based on the first matching result, the second matching result, the fourth matching result and the first comparison result, it can be that if it is determined that the candidate object meets the third target condition based on the first matching result, the second matching result, the fourth matching result and the first comparison result, the candidate object is selected as the target object; wherein the third target condition includes at least one of the following: the first category label is the same as the target category label; the behavior event matches the target behavior event; the behavior event matches the target behavior event, and the number of executions of the behavior event is not less than the number of executions of the matched target behavior event; the execution order of the event sequence is the same as the execution order of the target event sequence.

[0113] It should be noted that the process of determining whether the first category label is the same as the target category label, the process of determining whether the behavior event matches the target behavior event, the process of determining whether the execution order of the event sequence is the same as the execution order of the target event sequence, and the process of determining whether the number of executions of the behavior event is not less than the number of executions of the matching target behavior event when the behavior event matches the target behavior event, as described above, are not elaborated here in the embodiments of the present application.

[0114] In some embodiments, the determined target object has a validity period. Specifically, after screening the target object from the candidate objects based on the first matching result and the second matching result, the target object can also be labeled to obtain a second category label; the second category label can be labeled with a validity period to obtain a first validity time corresponding to the second category label.

[0115] It should be noted that the second category label is used to indicate that the candidate object is the target object, and the first effective time is used to indicate the validity period of the second category label; the first category label and the second category label are category labels of different dimensions. For example, when the first category label indicates the level of the object, the second category label can indicate different business types. For example, when the application scenario is to determine the target object that is compatible with the target business among ordinary users, if the first category label of object A indicates that the level of object A is ordinary, then based on the first category label of object A, determine whether object A is the target object. When object A is the target object, mark object A to obtain the second category label. The second category label corresponds to the target business, that is, object A is a user among ordinary users that is compatible with the target business.

[0116] It should be noted that the first effective time can be pre-set, for example, it can be one day or one week; when the first effective time indicates that the second category tag is within the validity period, the object corresponding to the second category tag is determined as the target object; when the first effective time indicates that the second category tag is not within the validity period, the object corresponding to the second category tag cannot be determined as the target object, that is, the second category tag is invalid.

[0117] In this way, the validity period of the target object is set based on the second category label and the first validity time, thereby avoiding the problem of low accuracy of the determined target object due to a long time after the target object is determined, and improving the validity of the determined target object.

[0118] In actual implementation, after marking the validity period of the second category tag and obtaining the first validity period corresponding to the second category tag, it is also possible to, if the first validity period indicates that the second category tag is within the validity period, obtain the information template corresponding to the second category tag; generate target information based on the information template; and send the target information to the terminal of the target object.

[0119] It should be noted that the information template can be a template corresponding to various information, such as a promotional information template such as an advertising template, or a reminder information template, such as an information template for reminding on holidays or birthdays, etc., and the embodiments of the present application do not limit this; in this way, different information can be generated based on different information templates. For example, when the information template is a promotional information template, the target information generated is promotional information; when the information template is a reminder information template, the target information generated is reminder information; in this way, based on the information template corresponding to the second category label, the information to be sent can be quickly generated, thereby improving the efficiency of information generation.

[0120] In some embodiments, the process of determining candidate objects may also be that, before obtaining the behavioral events of the candidate objects within the target time period and the first category label of the candidate objects, each first initial object is detected to see whether it includes an invalid label to obtain a detection result, where the invalid label is used to indicate that the corresponding first initial object cannot be determined as a target object during the second effective time; based on the detection result, multiple first initial objects are determined as first initial objects including invalid labels and first initial objects not including invalid labels; and the first initial object not including invalid labels is determined as a candidate object.

[0121] It should be noted that when the first initial object carries an invalid label, no matter whether the first category label of the first initial object is the same as the target category label, or whether the behavior event of the first initial object matches the target behavior event, the first initial object cannot be determined as the target object; at the same time, there is a one-to-one correspondence between the invalid label and the second effective time, and the second effective time is pre-set, which can be one day or one week, etc. Based on this, before determining the target object, it is necessary to detect whether it carries an invalid label, so that the first initial object that does not carry an invalid label is determined as a candidate object.

[0122] In this way, when an object cannot be determined as a target object, the corresponding object can be allowed to carry an invalid tag, thereby avoiding determining the corresponding object as a target object. In this way, the flexibility and practicality of the target object determination process can be improved.

[0123] In actual implementation, after determining multiple first initial objects as first initial objects including invalid labels and first initial objects not including invalid labels based on the detection results, it is also possible to determine the valid time period corresponding to the invalid label based on the second valid time; if the target time is not in the valid time period, delete the invalid label included in the first initial object, and determine the first initial object with the invalid label deleted as a candidate object.

[0124] It should be noted that the target time is used to indicate the moment of determining the target object, that is, the current moment of executing the embodiment of the present application; the valid period corresponding to the invalid tag refers to the period during which the object corresponding to the invalid tag cannot be determined as the target object, so when it is not within this period, it means that the invalid tag is invalid, that is, the corresponding object can be determined as the target object, therefore, the invalid tag carried by the first initial object is deleted, and the first initial object without the invalid tag is determined as the candidate object. In this way, by setting the validity period of the invalid tag, the situation where the object corresponding to the invalid tag cannot be determined as the target object is avoided, and the flexibility and practicality of the target object determination process are improved.

[0125] In some embodiments, after determining the second class of objects that do not include invalid labels as candidate objects, the determined candidate objects can also be used as the second initial objects described above, thereby obtaining the attribute information of the second initial objects; matching the attribute information of each second initial object with the pre-set target attribute information to obtain a third matching result; selecting the target third matching result whose matching degree reaches the target matching degree and determining the second initial object corresponding to the target third matching result as the target candidate object; then obtaining the behavior events of the target candidate object within the target time period and the first category label of the target candidate object; matching the first category label of the target candidate object with the pre-set target category label to obtain the first matching result; matching the behavior events of the target candidate object with the pre-set target behavior events to obtain the second matching result; based on the first matching result and the second matching result, screening the target object from the target candidate objects. In this implementation, the second initial object can be the same as or different from the first initial object.

[0126] It should be noted that the process of obtaining the attribute information of the second initial object; matching the attribute information of each second initial object with the preset target attribute information to obtain the third matching result; selecting the target third matching result whose matching degree reaches the target matching degree and determining the second initial object corresponding to the target third matching result as the target candidate object is as described above and will not be repeated here;

[0127] The process of obtaining the behavioral events of the target candidate object within the target time period and the first category label of the target candidate object; matching the first category label of the target candidate object with the preset target category label to obtain a first matching result; matching the behavioral events of the target candidate object with the preset target behavioral events to obtain a second matching result; and screening the target object from the target candidate objects based on the first matching result and the second matching result is also similar to the process of obtaining the behavioral events of the candidate object within the target time period and the first category label of the candidate object; matching the first category label of the candidate object with the preset target category label to obtain a first matching result; matching the behavioral events of the candidate object with the preset target behavioral events to obtain a second matching result; and screening the target object from the candidate objects based on the first matching result and the second matching result as described above, which will not be repeated here;

[0128] In other embodiments, as described above, after selecting the target third matching result whose matching degree reaches the target matching degree and determining the second initial object corresponding to the target third matching result as the candidate object, the candidate object can also be used as the first initial object, so as to detect whether each first initial object includes an invalid label to obtain a detection result, and the invalid label is used to indicate that the corresponding first initial object is not determined as the target object in the second effective time; based on the detection result, multiple first initial objects are determined as the first initial object including the invalid label and the first initial object not including the invalid label; the first initial object not including the invalid label is determined as the target candidate object; then the behavior events of the target candidate object within the target time period and the first category label of the target candidate object are obtained; the first category label of the target candidate object is matched with the pre-set target category label to obtain a first matching result; the behavior events of the target candidate object are matched with the pre-set target behavior events to obtain a second matching result; based on the first matching result and the second matching result, the target object is screened from the target candidate objects.

[0129] It should be noted that the candidate object (i.e., the target candidate object) can be determined by combining the process of screening the second initial object and the process of screening the first initial object, and the order of execution of the process of screening the second initial object and the process of screening the first initial object is not limited in the embodiment of the present application; in this way, the candidate object is determined by combining the process of screening the second initial object and the process of screening the first initial object, which further refines the process of determining the candidate object compared to only using the process of screening the second initial object or the process of screening the first initial object to determine the candidate object, thereby improving the accuracy and efficiency of subsequent determination of the target object. In this embodiment, the first initial object and the second initial object may be the same or different.

[0130] By using the above-mentioned embodiment of the present application, the category label of the candidate object is matched with the target category label to obtain a first matching result, and the behavior event of the candidate object is matched with the target behavior event to obtain a second matching result, thereby screening the target object from the candidate objects based on the first matching result and the second matching result. In this way, in addition to considering the behavior event of the object, the category label of the object is also combined to determine the target user. Compared with the scheme in the related art that only selects the target user based on the user's behavior data, the efficiency and accuracy of determining the target object are improved; at the same time, combining the category label of the object to determine the target user is equivalent to further refining the objects belonging to the same category label, thereby re-determining the target object, further improving the accuracy of the determined target object.

[0131] The following is an explanation of an exemplary application of the embodiments of the present application in a practical application scenario.

[0132] In the related technologies, marketing platforms rely on marketers to select groups based on portrait tags to perform data salvage and marketing push. However, this method is not timely enough and cannot capture fleeting marketing opportunities. For example, if a promotion-enthusiastic user is browsing clothes, timely push of clothing information that is on sale is the most effective; or if a price-sensitive user is hesitant and repeatedly checking a target product in the shopping cart, timely push of coupons is the most effective. Obviously, the above scenarios cannot be discovered and quickly responded to by marketers through manual means.

[0133] Based on this, the embodiment of the present application provides a solution for implementing dynamic rules for crowd packages based on Groovy. By leveraging the dynamic nature of Groovy, dynamically executable Groovy code snippets are generated. Through real-time judgment of user attributes and user behaviors, an automated, real-time, and dynamically rule-based marketing process is achieved.

[0134] In actual implementation, see Figure 5 and Figure 6 , Figure 5 is a flowchart of the code generation process provided by the embodiment of the present application, Figure 6 is a flowchart of the code running process provided by the embodiment of the present application, based on Figure 5 and Figure 6 The technical solution of this application includes three processes: first, the process of dynamically generating groovy code snippet logic; second, the process of real-time calculation of behavior events; and third, the process of real-time calculation of behavior sequences. Next, these three processes are explained respectively.

[0135] For the process of dynamically generating groovy code snippet logic, based on Figure 5 First, the code snippet template, the logical operator and the rule operator are defined, and then after receiving the relevant parameters of the rule conditions for indicating the attributes of the crowd package, the behavior events and the behavior sequence, the defined configuration information is parsed based on the relevant parameters of the rule conditions, so as to obtain the associated information of the attributes, the associated information of the behavior events and the associated information of the behavior sequence. For example, see Figure 7 , Figure 7 It is a schematic diagram of the association information of attributes, the association information of behavior events, and the association information of behavior sequences provided by the embodiment of the present application. Then, after obtaining the association information of attributes, the association information of behavior events, and the association information of behavior sequences, groovy code is generated based on the association information of attributes, the association information of behavior events, and the association information of behavior sequences, and executed.

[0136] For the real-time calculation process of behavioral events, based on Figure 6 ,like Figure 6 As shown in steps 1 to 7, after executing the generated groovy code, the user's event data stream is obtained, and based on the event data stream, the event message is obtained, wherein the event message includes the user ID, event timestamp, event attribute code, event attribute value, event comparison operator, etc.; based on the obtained event message, all behavior events in the crowd package rule are traversed to determine whether the behavior event in the event data stream matches any behavior event in the rule, and then all judgment results are logically operated. If the logical calculation result of the output behavior event is true, the next step of the behavior sequence calculation process is continued, otherwise it is terminated.

[0137] For the process of real-time calculation of behavior sequences, based on Figure 6 ,like Figure 6 As shown in steps 8 to 16, when the logical calculation result of the output behavior event is true, determine whether the occurrence time in the behavior sequence is within the specified time window, that is, whether the difference between the execution time of the first behavior event and the last behavior event in the behavior sequence is less than the time difference threshold. When it is less than the time difference threshold, match each behavior event in the user's behavior sequence with each behavior event in the behavior sequence in the rule to obtain a sequence matching result; when the sequence matching result indicates that each behavior event in the user's behavior sequence has a matching target behavior event (that is, the behavior event in the behavior sequence in the rule), determine whether the execution order of the user's behavior sequence is the same as the execution order of the behavior sequence in the rule, that is, starting from the first behavior event in the behavior sequence, match the behavior event with the matching target behavior event respectively. The execution order of the events is compared. When the execution order of the corresponding behavior event is the same as the execution order of the matched target behavior event, the next behavior event is compared with the execution order of the matched target behavior event in the target event sequence, and this is repeated until the last behavior event in the event sequence is reached, and a judgment result indicating that the execution order of the user's behavior sequence is the same as the execution order of the behavior sequence in the rule is obtained; wherein, when there is a behavior event whose execution order is different from the execution order of the matched target behavior event, a judgment result indicating that the execution order of the user's behavior sequence is different from the execution order of the behavior sequence in the rule is obtained; when the execution order of the user's behavior sequence is the same as the execution order of the behavior sequence in the rule, the user ID of the user is written into the crowd package, that is, the user is circled. For example, see Figure 8 , Figure 8 is a schematic diagram of the process of selecting a user provided by an embodiment of the present application, based on Figure 8,When a user triggers a rule condition, if the user is a target user, the user’s ID is written into the crowd package.

[0138] In this way, by dynamically generating groovy code snippets, the crowd package rule conditions are turned into rules engines, which means that the crowd package conditions can be dynamically configured at will. This makes it convenient for business data analysts to filter data and operate refined operations. At the same time, by transforming rules to filter data streams for real-time calculations, precise marketing triggering and reach can be achieved.

[0139] By using the above-mentioned embodiment of the present application, the category label of the candidate object is matched with the target category label to obtain a first matching result, and the behavior event of the candidate object is matched with the target behavior event to obtain a second matching result, thereby screening the target object from the candidate objects based on the first matching result and the second matching result. In this way, in addition to considering the behavior event of the object, the category label of the object is also combined to determine the target user. Compared with the scheme in the related art that only selects the target user based on the user's behavior data, the efficiency and accuracy of determining the target object are improved; at the same time, combining the category label of the object to determine the target user is equivalent to further refining the objects belonging to the same category label, thereby re-determining the target object, further improving the accuracy of the determined target object.

[0140] The following is a description of an exemplary structure of the target object determination device 455 provided in the embodiment of the present application implemented as a software module. In some embodiments, Figure 2 As shown, the software modules stored in the target object determination device 455 of the memory 450 may include:

[0141] An acquisition module 4551 is used to acquire the behavior events of the candidate object within the target time period and the first category label of the candidate object;

[0142] A first matching module 4552, used to match the first category label of the candidate object with a preset target category label to obtain a first matching result;

[0143] The second matching module 4553 is used to match the behavior event of the candidate object with a preset target behavior event to obtain a second matching result;

[0144] The screening module 4554 is used to screen the target object from the candidate objects based on the first matching result and the second matching result.

[0145] In some embodiments, the device further includes a labeling module, which is used to label the target object to obtain a second category label; and to label the second category label with a validity period to obtain a first validity period corresponding to the second category label.

[0146] In some embodiments, the device also includes an information generation module, which is used to obtain an information template corresponding to the second category tag if the first effective time indicates that the second category tag is within the validity period; generate target information based on the information template; and send the target information to the terminal of the target object.

[0147] In some embodiments, the device also includes a detection module, which is used to detect whether each first initial object includes an invalid label to obtain a detection result, wherein the invalid label is used to indicate that the corresponding first initial object is not determined as a target object at the second effective time; based on the detection result, multiple initial objects are determined as a first initial object including an invalid label and a first initial object not including an invalid label; and the first initial object not including an invalid label is determined as the candidate object.

[0148] In some embodiments, the device also includes a label deletion module, which is used to determine the valid time period corresponding to the invalid label based on the second valid time; if the target time is not in the valid time period, delete the invalid label included in the first initial object, and determine the first initial object from which the invalid label is deleted as the candidate object.

[0149] In some embodiments, the device also includes a third matching module, which is used to obtain attribute information of the second initial object; match the attribute information of each of the second initial objects with pre-set target attribute information to obtain a third matching result; select a target third matching result whose matching degree reaches the target matching degree and determine the second initial object corresponding to the target third matching result as the candidate object.

[0150] In some embodiments, the second matching result is used to indicate whether the behavior event matches the target behavior event, the number of the behavior events is N, the number of the target behavior events is M, and M and N are positive integers; the second matching module 4553 is also used to match the behavior event with the target behavior event to obtain an event matching result; if there is an event matching result indicating that the corresponding behavior event matches the corresponding target behavior event, a second matching result indicating that the behavior event matches the target behavior event is obtained; if each of the event matching results indicates that the corresponding behavior event does not match the corresponding target behavior event, a second matching result indicating that the behavior event does not match the target behavior event is obtained.

[0151] In some embodiments, the device also includes a first comparison module, which is used to obtain the number of executions of the behavior event and the number of executions of the target behavior event if the second matching result indicates that the behavior event matches the target behavior event; compare the number of executions of the behavior event with the number of executions of the target behavior event to obtain a first comparison result; and the screening module 4554 is also used to screen the target object from the candidate objects based on the first matching result, the second matching result and the first comparison result.

[0152] In some embodiments, the screening module 4554 is also used to select the candidate object as the target object if it is determined that the candidate object satisfies the first target condition based on the first matching result, the second matching result and the first comparison result; wherein the first target condition includes at least one of the following: the first category label is the same as the target category label; the behavior event matches the target behavior event; the behavior event matches the target behavior event, and the number of executions of the behavior event is not less than the number of executions of the matched target behavior event.

[0153] In some embodiments, the device also includes a fourth matching module, which is used to construct an event sequence corresponding to P behavioral events if the number of behavioral events performed by the candidate object is P, and P is greater than or equal to 2, where P is a positive integer; match the event sequence with a pre-set target event sequence to obtain a fourth matching result; the screening module 4554 is also used to screen the target object from the candidate objects based on the first matching result, the second matching result and the fourth matching result.

[0154] In some embodiments, the screening module 4554 is also used to select the candidate object as the target object if it is determined that the candidate object satisfies the second target condition based on the first matching result, the second matching result and the fourth matching result; wherein the second target condition includes at least one of the following: the first category label is the same as the target category label; the behavior event matches the target behavior event; the execution order of the event sequence is the same as the execution order of the target event sequence.

[0155] In some embodiments, the fourth matching module is also used to match the behavioral events in the event sequence with the target behavioral events in the target event sequence respectively to obtain a sequence matching result; if the sequence matching result indicates that each of the behavioral events has a matching target behavioral event, then the fourth matching result is determined based on the execution order of the behavioral events and the execution order of the target behavioral events.

[0156] In some embodiments, the fourth matching module is also used to compare the execution order of each of the behavioral events with the execution order of the matching target behavioral events to obtain a second comparison result; if each of the second comparison results indicates that the execution order of the corresponding behavioral events is the same as the execution order of the matching target behavioral events, a fourth matching result is obtained to indicate that the execution order of the event sequence is the same as the execution order of the target event sequence; if there is a second comparison result indicating that the execution order of the corresponding behavioral event is different from the execution order of the matching target behavioral event, a fourth matching result is obtained to indicate that the execution order of the event sequence is different from the execution order of the target event sequence.

[0157] In some embodiments, the device further includes a second acquisition module, the second acquisition module being configured to acquire preset configuration information; and parse the configuration information to obtain the preset target behavior event and the target category label.

[0158] The present application embodiment provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes the above-mentioned method for determining a target object in the present application embodiment, for example, Figure 3 A method for determining a target object is shown.

[0159] The present application embodiment provides a computer-readable storage medium storing executable instructions, wherein the executable instructions are stored. When the executable instructions are executed by a processor, the processor will execute the target object determination method or job matching method provided in the present application embodiment, for example, Figure 3 A method for determining a target object is shown.

[0160] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface storage, optical disk, or CD-ROM; or it may be various devices including one or any combination of the above memories.

[0161] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0162] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0163] As an example, the executable instructions may be deployed to be executed on one electronic device, or on multiple electronic devices located at one site, or on multiple electronic devices distributed at multiple sites and interconnected by a communication network.

[0164] It should be noted that in the embodiments of the present application, it involves obtaining data related to the attribute information, category labels, behavioral events, and behavioral event sequences of the object. When the embodiments of the present application are applied to specific products or technologies, user permission or consent is required, and the collection, use, and processing of relevant data must comply with relevant laws, regulations, and standards of relevant countries and regions.

[0165] The above is only an embodiment of the present application and is not intended to limit the protection scope of the present application. Any modifications, equivalent substitutions and improvements made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims

1. A method for determining a target object, characterized in that: The method comprises: Obtaining behavioral events of a candidate object within a target time period and a first category label of the candidate object; Matching the first category label of the candidate object with a preset target category label to obtain a first matching result; Matching the behavior event of the candidate object with a preset target behavior event to obtain a second matching result; Based on the first matching result and the second matching result, a target object is screened from the candidate objects.

2. The method according to claim 1, characterized in that After screening the target object from the candidate objects based on the first matching result and the second matching result, the method further includes: Labeling the target object to obtain a second category label; The second category tag is marked with a validity period to obtain a first validity period corresponding to the second category tag.

3. The method according to claim 2, characterized in that After marking the validity period of the second category tag to obtain the first validity period corresponding to the second category tag, the method further includes: If the first validity period indicates that the second category tag is within the validity period, obtaining the information template corresponding to the second category tag; Based on the information template, generating target information; The target information is sent to the target object's terminal.

4. The method according to claim 1, characterized in that Before obtaining the behavior events of the candidate object within the target time period and the first category label of the candidate object, the method further includes: Detecting whether each first initial object includes an invalid tag to obtain a detection result, wherein the invalid tag is used to indicate that the corresponding first initial object is not determined as a target object during the second valid time; Based on the detection result, determining the plurality of first initial objects as first initial objects including invalid labels and first initial objects not including invalid labels; The first initial object that does not include an invalid label is determined as the candidate object.

5. The method according to claim 4, characterized in that After determining the plurality of initial objects as a first initial object including an invalid label and a first initial object not including an invalid label based on the detection result, the method further includes: Based on the second validity time, determining a validity period corresponding to the invalid tag; If the target time is not within the valid period, the invalid tag included in the first initial object is deleted, and the first initial object with the invalid tag deleted is determined as the candidate object.

6. The method according to claim 1, characterized in that Before obtaining the behavior events of the candidate object within the target time period and the first category label of the candidate object, the method further includes: Obtaining attribute information of the second initial object; Matching the attribute information of each of the second initial objects with the preset target attribute information respectively to obtain a third matching result; A target third matching result whose matching degree reaches the target matching degree is selected, and a second initial object corresponding to the target third matching result is determined as the candidate object.

7. The method according to claim 1, characterized in that The second matching result is used to indicate whether the behavior event matches the target behavior event; The step of matching the behavior event of the candidate object with a preset target behavior event to obtain a second matching result includes: Matching the behavior event with the target behavior event to obtain an event matching result; If the event matching result indicates that the corresponding behavior event matches the corresponding target behavior event, a second matching result indicating that the behavior event matches the target behavior event is obtained; If each of the event matching results indicates that the corresponding behavior event does not match the corresponding target behavior event, a second matching result indicating that the behavior event does not match the target behavior event is obtained.

8. The method according to claim 1, characterized in that After matching the behavior event of the candidate object with a preset target behavior event to obtain a second matching result, the method includes: If the second matching result indicates that the behavior event matches the target behavior event, then acquiring the number of executions of the behavior event and the number of executions of the target behavior event; Comparing the number of executions of the behavior event with the number of executions of the target behavior event to obtain a first comparison result; The step of screening a target object from the candidate objects based on the first matching result and the second matching result includes: Based on the first matching result, the second matching result, and the first comparison result, a target object is screened from the candidate objects.

9. The method according to claim 8, characterized in that The screening of the target object from the candidate objects based on the first matching result, the second matching result and the first comparison result includes: If it is determined that the candidate object meets the first target condition based on the first matching result, the second matching result and the first comparison result, the candidate object is selected as the target object; Wherein, the first target condition includes at least one of the following: The first category label is the same as the target category label; The behavioral event matches the target behavioral event; The behavior event matches the target behavior event, and the number of executions of the behavior event is not less than the number of executions of the matched target behavior event.

10. The method according to claim 1, characterized in that After obtaining the behavior events of the candidate object within the target time period and the first category label of the candidate object, the method further includes: If the number of behavior events performed by the candidate object is P, construct an event sequence corresponding to the P behavior events, where P is a positive integer greater than or equal to 2; Matching the event sequence with a preset target event sequence to obtain a fourth matching result; The step of screening a target object from the candidate objects based on the first matching result and the second matching result includes: Based on the first matching result, the second matching result, and the fourth matching result, a target object is screened from the candidate objects.

11. The method according to claim 10, characterized in that The screening of the target object from the candidate objects based on the first matching result, the second matching result, and the fourth matching result includes: If it is determined that the candidate object satisfies the second target condition based on the first matching result, the second matching result and the fourth matching result, the candidate object is selected as the target object; Wherein, the second target condition includes at least one of the following: The first category label is the same as the target category label; The behavioral event matches the target behavioral event; The execution order of the event sequence is the same as the execution order of the target event sequence.

12. The method according to claim 10, characterized in that The matching of the event sequence with a preset target event sequence to obtain a fourth matching result includes: Matching the behavior events in the event sequence with the target behavior events in the target event sequence respectively to obtain a sequence matching result; If the sequence matching result indicates that each of the behavior events has a matching target behavior event, the fourth matching result is determined based on the execution order of the behavior events and the execution order of the target behavior events.

13. The method according to claim 12, characterized in that The determining the fourth matching result based on the execution order of the behavior events and the execution order of the target behavior events includes: Comparing the execution order of each of the behavior events with the execution order of the matching target behavior events to obtain a second comparison result; If each of the second comparison results indicates that the execution order of the corresponding behavior event is the same as the execution order of the matched target behavior event, a fourth matching result is obtained indicating that the execution order of the event sequence is the same as the execution order of the target event sequence; If there is a second comparison result indicating that the execution order of the corresponding behavior event is different from the execution order of the matched target behavior event, a fourth matching result is obtained to indicate that the execution order of the event sequence is different from the execution order of the target event sequence.

14. The method according to claim 1, wherein: Before obtaining the behavior events of the candidate object within the target time period and the first category label of the candidate object, the method further includes: Get pre-set configuration information; The configuration information is parsed to obtain the preset target behavior event and the target category label.

15. A device for determining a target object, characterized in that: The device comprises: An acquisition module, used to acquire the behavior events of the candidate object within a target time period and the first category label of the candidate object; A first matching module, used to match the first category label of the candidate object with a preset target category label to obtain a first matching result; A second matching module, used for matching the behavior event of the candidate object with a preset target behavior event to obtain a second matching result; A screening module is used to screen a target object from the candidate objects based on the first matching result and the second matching result.

16. An electronic device, characterized in that: include: A memory for storing executable instructions; A processor, configured to implement the method for determining a target object as described in any one of claims 1 to 14 when executing executable instructions stored in the memory.

17. A computer-readable storage medium, characterized in that: Executable instructions are stored, which are used to cause a processor to execute and implement the method for determining a target object as described in any one of claims 1 to 14.

18. A computer program product comprising computer executable instructions, characterized in that: When the computer executable instructions are executed by a processor, the method for determining a target object according to any one of claims 1 to 14 is implemented.

Images