Information recommendation method and device, electronic equipment and computer readable storage medium

Abstract

The invention provides an information recommendation method and device, electronic equipment and a computer readable storage medium. The method comprises the steps that a first object data set and recommendation configuration information in a first application are obtained, and the recommendation configuration information at least comprises a first recommendation configuration condition; performing extraction processing on the first object data set according to the first recommendation configuration condition to obtain a second object data set; recommendation information is determined based on the first recommendation configuration condition, and the recommendation information is used for being displayed in a second application of the terminal equipment associated with the second object; and sending recommendation information to a terminal device associated with the second object in response to the fact that the recommendation condition is met. Through the method and the device, the cross-application information recommendation efficiency can be improved.

Description

Technical Field

[0001] This application relates to the field of Internet application technologies, and in particular, to an information recommendation method, apparatus, electronic device, and computer-readable storage medium. Background Art

[0002] With the development of Internet technologies, there are various ways of information recommendation. In related technologies, for cross-application information recommendation processing, recommendation information is sent to the terminal devices of objects in units of communities, or to the terminal devices of objects using each application program.

[0003] However, in related technologies, sending recommendation information to the terminal devices of each object in full affects the experience of the objects and reduces the user retention rate. In addition, during the information recommendation process, operators manually send recommendation messages to a large number of objects, and it is inevitable that there are situations such as missed sending or multiple sending of recommendation information, which increases the operating labor cost of information recommendation. Moreover, the excessive number of objects to be pushed also results in low information recommendation efficiency.

[0004] In related technologies, there is no good way to improve the efficiency of cross-application information recommendation. Summary of the Invention

[0005] Embodiments of this application provide an information recommendation method, apparatus, electronic device, and computer-readable storage medium, which can improve the efficiency of cross-application information recommendation.

[0006] The technical solution of the embodiments of this application is implemented as follows:

[0007] Embodiments of this application provide an information recommendation method, and the method includes:

[0008] Obtain a first object data set and recommendation configuration information in a first application, where the recommendation configuration information includes at least a first recommendation configuration condition, and the first object data set includes object data of multiple different first objects;

[0009] Perform extraction processing on the first object data set according to the first recommendation configuration condition to obtain a second object data set, where the second object data set includes object data of multiple different second objects, and the second objects are first objects that meet the first recommendation configuration condition;

[0010] Determine recommendation information based on the first recommendation configuration condition, where the recommendation information is used to be displayed in a second application on a terminal device associated with the second object, and the second application is different from the first application;

[0011] In response to meeting the recommendation condition, send the recommendation information to the terminal device associated with the second object.

[0012] An embodiment of the present application provides an information recommendation device, including:

[0013] A data acquisition module configured to acquire a first object data set and recommendation configuration information in a first application, where the recommendation configuration information includes at least a first recommendation configuration condition, and the first object data set includes object data of a plurality of different first objects;

[0014] A data extraction module configured to perform extraction processing on the first object data set according to the first recommendation configuration condition to obtain a second object data set, where the second object data set includes object data of a plurality of different second objects, and the second object is a first object that meets the first recommendation configuration condition;

[0015] A determination module configured to determine recommendation information based on the first recommendation configuration condition, where the recommendation information is used to be displayed in a second application of a terminal device of the second object, and the second application is different from the first application;

[0016] A recommendation module configured to send the recommendation information to a terminal device associated with the second object in response to meeting the recommendation condition.

[0017] An embodiment of the present application provides an electronic device, and the electronic device includes:

[0018] A memory for storing computer-executable instructions;

[0019] A processor, when executing the computer-executable instructions stored in the memory, implements the information recommendation method provided by the embodiment of the present application.

[0020] An embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions or a computer program, which, when executed by a processor, implements the information recommendation method provided by the embodiment of the present application.

[0021] An embodiment of the present application provides a computer program product including computer-executable instructions or a computer program, which, when executed by a processor, implements the information recommendation method provided by the embodiment of the present application.

[0022] The embodiment of the present application has the following beneficial effects:

[0023] Extract and process the first object data set based on the first recommendation configuration condition, and screen to obtain the second object data set, so as to be able to recommend information to specific objects in a targeted manner; determine the corresponding recommendation information for the second object based on the first recommendation configuration condition, so that the recommendation information matches the information of the second object, improving the relevance between the recommendation information and the second object; and push the recommendation information to the terminal device of the second object, so that the recommendation information is displayed in the second application, realizing cross-application of the recommendation information, expanding the recommendation channels, and improving the recommendation efficiency. Compared with the solution of uniformly delivering recommendation information in the related art, it can save the computing resources for executing information recommendation. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a schematic diagram of the application mode of the information recommendation method provided by an embodiment of the present application;

[0025] Figure 2 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application;

[0026] Figure 3A is a first flowchart of the information recommendation method provided by an embodiment of the present application;

[0027] Figure 3B is a second flowchart of the information recommendation method provided by an embodiment of the present application;

[0028] Figure 3C is a third flowchart of the information recommendation method provided by an embodiment of the present application;

[0029] Figure 3D is a fourth flowchart of the information recommendation method provided by an embodiment of the present application;

[0030] Figure 3E is a fifth flowchart of the information recommendation method provided by an embodiment of the present application;

[0031] Figure 4 is a flowchart of account association provided in the related art;

[0032] Figure 5 is a first interface diagram for selecting a target user provided by an embodiment of the present application;

[0033] Figure 6 is a second interface diagram of the recommended configuration information provided by an embodiment of the present application;

[0034] Figure 7 is a third interface diagram of the information recommendation progress provided by an embodiment of the present application;

[0035] Figure 8 is a flowchart of the information recommendation method provided by an embodiment of the present application;

[0036] Figure 9 It is a schematic diagram of the fourth interface for the system configuration to provide the first recommended configuration condition in the embodiments of the present application;

[0037] Figure 10 It is a schematic diagram of the process for triggering the first recommended configuration condition provided by the embodiments of the present application;

[0038] Figure 11 It is a schematic diagram of splitting the media information flow into sub-media information flows provided by the embodiments of the present application;

[0039] Figure 12 It is a schematic diagram of the fifth interface for recommending additional information provided by the embodiments of the present application;

[0040] Figure 13 It is a schematic diagram of the interaction process of the information recommendation method provided by the embodiments of the present application. Detailed implementation manners

[0041] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be construed as limitations on the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present application.

[0042] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0043] In the following description, the terms "first / second / third" are only used to distinguish similar objects and do not represent a specific order for the objects. It can be understood that "first / second / third" can be interchanged with a specific order or sequence when allowed, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0044] It should be noted that the relevant data collection and processing in the present application (for example: obtaining user historical data in a game scenario) should strictly comply with the requirements of relevant national laws and regulations during actual application, obtain the informed consent or separate consent of the personal information subject, and carry out subsequent data use and processing behaviors within the scope of authorization of laws, regulations and the personal information subject.

[0045] In the embodiments of the present application, the term "module" or "unit" refers to a computer program with a predetermined function or a part of a computer program, which works together with other relevant parts to achieve a predetermined goal, and can be fully or partially implemented by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, one processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of an overall module or unit that includes the function of that module or unit.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field 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.

[0047] Before further elaborating on the embodiments of the present application, the nouns and terms involved in the embodiments of the present application are described, and the nouns and terms involved in the embodiments of the present application are subject to the following explanations.

[0048] 1) Database (ClickHouse, CK): It is an open-source columnar database for online analytical processing (OLAP).

[0049] 2) Object Storage (Cloud Object Storage, COS): It is a distributed storage service without a directory hierarchy, without data format restrictions, capable of accommodating massive amounts of data, and supporting access via the HTTP / HTTPS protocol.

[0050] 3) Message Queue (Pulsar): It is a distributed message queue.

[0051] The embodiments of the present application provide an information recommendation method, an information recommendation device, an electronic device, and a computer-readable storage medium, which can achieve cross-application recommendation of information, expand the recommendation channels, and improve the recommendation efficiency.

[0052] The following describes the exemplary applications of the electronic device provided in the embodiments of the present application. The electronic device provided in the embodiments of the present application can be implemented as various types of user terminals such as terminal devices, such as laptop computers, tablet computers, desktop computers, set-top boxes, smart TVs, mobile devices (for example, mobile phones, portable music players, personal digital assistants, dedicated messaging devices, portable gaming devices), vehicle-mounted terminals, virtual reality (VR) devices, augmented reality (AR) devices, etc., or can also be implemented as a server. Below, the exemplary applications when the electronic device is implemented as a server will be described.

[0053] Refer to Figure 1 ,Figure 1 It is a schematic diagram of the application mode of the information recommendation method provided by the embodiments of the present application; for example, Figure 1 involves a server 200, a network 300, a terminal device 400, and a database 500. The terminal device 400 is connected to the server 200 through the network 300. The network 300 can be a wide area network, a local area network, or a combination of the two.

[0054] In some embodiments, the database 500 stores a large amount of user log data in game applications. The server 200 is used to classify users based on the logs in the game applications and send recommendation information to the user's terminal device. The terminal device 400 can be the user's mobile phone. A first application and a second application are installed in the terminal device 400. The first application is a game application, and the second application is a social application.

[0055] For example, the server 200 obtains a first object data set in the game application from the database 500, and performs extraction processing on the first object data set according to the first recommendation configuration condition to obtain a second object data set. When receiving a recommendation request uploaded by the user through the terminal device 400, the server 200 determines the recommendation information based on the first recommendation configuration condition, and sends the recommendation information to the terminal device 400 through the network 300. The user can view the recommendation information in the social application on the terminal device 400.

[0056] In some embodiments, the information recommendation method of the embodiments of the present application can also be applied to the following application scenarios: in the online shopping scenario, based on the historical purchase behavior data of the user in the shopping APP, the target users matching the recommendation information are screened out, and the latest shopping activity information is pushed to the terminal devices of the target users; in the video viewing scenario, based on the historical browsing behavior data of the user in the video APP, the users interested in the video content to be recommended are screened out, and different video recommendation information is pushed to the terminal devices of member users and non-member users respectively.

[0057] The embodiments of the present application can be implemented through database technology. A database, in short, can be regarded as a place for storing electronic files in an electronic filing cabinet. Users can perform operations such as adding, querying, updating, and deleting data in the files. The so-called "database" is a data set stored together in a certain way, shared by multiple users, having the smallest possible redundancy, and independent of the application program.

[0058] A Database Management System (DBMS) is a computer software system designed to manage databases and generally has basic functions such as storage, retrieval, security, backup, etc. Database management systems can be classified according to the database models they support, such as relational, XML (Extensible Markup Language); or according to the types of computers they support, such as server clusters, mobile phones; or according to the query languages they use, such as Structured Query Language (SQL), XQuery; or according to the key performance metrics, such as maximum scale, highest running speed; or other classification methods. Regardless of the classification method used, some DBMSs can cross categories. For example, they can support multiple query languages simultaneously.

[0059] Embodiments of this application can also be implemented through cloud technology. Cloud technology is a general term for network technology, information technology, integration technology, management platform technology, application technology, etc. based on the cloud computing business model. It can form a resource pool and be used on demand, which is flexible and convenient. Cloud computing technology will become an important support. The back-end services of technical network systems require a large amount of computing and storage resources, such as video websites, picture websites, and more portal websites. With the high development and application of the Internet industry, as well as the promotion of demands such as search services, social networks, mobile commerce, and open collaboration, in the future, each item may have its own hash code identification mark and needs to be transmitted to the back-end system for logical processing. Data at different levels will be processed separately, and various types of industry data require a powerful system back-end support, which can only be achieved through cloud computing.

[0060] Embodiments of this application can also be implemented through natural language processing. Natural Language Processing (NLP) is an important direction in the fields of computer science and artificial intelligence. It studies various theories and methods that can enable effective communication between humans and computers using natural language. Natural language processing involves natural language, that is, the language people use in daily life, and is closely related to linguistic research. At the same time, it involves computer science and mathematics. The pre-trained model, an important technology for model training in the field of artificial intelligence, is developed from the large language model (LLM) in the NLP field. After fine-tuning, the large language model can be widely applied to downstream tasks. Natural language processing technology usually includes technologies such as text processing, semantic understanding, machine translation, robot question answering, and knowledge graphs.

[0061] In some embodiments, the server 200 may be implemented as multiple servers, such as a game server and a recommendation server. Among them, the game server is used to store the historical behavior and interest portrait data of users, and the recommendation server is used to send recommendation information to the terminal devices associated with the users.

[0062] In some embodiments, the server may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It may also be 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, CDN, and big data and artificial intelligence platforms. The electronic device may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal device and the server may be directly or indirectly connected through wired or wireless communication methods, which are not limited in the embodiments of the present application.

[0063] See Figure 2 , Figure 2 is a schematic structural diagram of the electronic device provided by the embodiments of the present application. The electronic device may be Figure 1 the server 200 in Figure 2 The server 200 shown in Figure 2 includes: at least one processor 410, a memory 450, and at least one network interface 420. Each component in the server 200 is coupled together through a bus system 440. It can be understood that the bus system 440 is used to realize the 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 clear illustration, in all kinds of buses are labeled as the bus system 440.

[0064] The processor 410 may be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or any conventional processor, etc.

[0065] The memory 450 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memories, hard disk drives, optical disc drives, etc. The memory 450 optionally includes one or more storage devices that are physically located away from the processor 410.

[0066] The memory 450 includes volatile memory, non-volatile memory, or both volatile and non-volatile memory. The non-volatile memory can be a read-only memory (ROM), and the volatile memory can 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.

[0067] In some embodiments, the memory 450 is capable of storing data to support various operations. Examples of such data include programs, modules, and data structures, or subsets or supersets thereof, which are exemplarily described below.

[0068] The operating system 451 includes system programs for handling various basic system services and performing hardware-related tasks, such as the framework layer, the core library layer, the driver layer, etc., for implementing various basic services and handling hardware-based tasks.

[0069] The network communication module 452 is used to reach other electronic devices via one or more (wired or wireless) network interfaces 420. Exemplary network interfaces 420 include: Bluetooth, Wi-Fi (Wireless Fidelity), and USB (Universal Serial Bus), etc.

[0070] In some embodiments, the device provided by the embodiments of the present application can be implemented in software. Figure 2 Shown is an information recommendation device 455 stored in the memory 450, which can be software in the form of programs and plugins, etc., including the following software modules: a data acquisition module 4551, a data extraction module 4552, a determination module 4553, and a recommendation module 4554. These modules are logical, and thus can be arbitrarily combined or further split according to the functions to be implemented. The functions of each module will be described hereinafter.

[0071] In some embodiments, the terminal device or the server can implement the information recommendation method provided by the embodiments of the present application by running a computer program. For example, the computer program can be a native program or a software module in the operating system; it can be a native application (APP, Application), that is, a program that needs to be installed in the operating system to run, such as a game APP or an instant messaging APP; it can also be a small program, that is, a program that only needs to be downloaded into the browser environment to run; it can also be a small program that can be embedded into any APP. In short, the above computer program can be any form of application program, module, or plugin.

[0072] The exemplary applications and implementations of the server device provided in the embodiments of the present application will be combined to illustrate the information recommendation method provided in the embodiments of the present application.

[0073] Next, the information recommendation method provided in the embodiments of the present application will be described. As mentioned above, the electronic device for implementing the information recommendation method in the embodiments of the present application can be a terminal device, a server, or a combination of both. Therefore, the execution subject of each step will not be repeated hereinafter.

[0074] Refer to Figure 3A , Figure 3A which is the first flowchart of the information recommendation method provided in the embodiments of the present application, and will be described in combination with the steps shown in Figure 3A .

[0075] In step 301, obtain the first object data set and recommendation configuration information in the first application.

[0076] Here, the recommendation configuration information includes at least the first recommendation configuration condition. The first object data set includes object data of multiple different first objects. The first object is a user or a user account in the first application. The recommendation configuration condition is configured based on the matching of user information and recommendation information. The first application can be a game application, a video application, or a shopping application. In the embodiments of the present application, a game application is used as an example for illustration.

[0077] Exemplarily, the object data of the first object includes the historical behavior and interest portrait data of the user account in the game application. The user historical behavior data includes the daily login duration of the user account in the game application, game interaction behavior, recharge amount, etc. The user interest portrait data includes user gender, user age, user location, user preference content, etc.

[0078] Exemplarily, a technician can pre-configure the target users to be recommended in the first object data set. Refer to Figure 5 , Figure 5 which is the first interface diagram for selecting target users provided in the embodiments of the present application. In the set target user interface 502, the area 501 vertically displays custom setting options, including: task target, user package creation method, please select tags, package volume estimation, etc. Package volume estimation is to set the range of churn days of the target users to be screened, and please select tags is to set the churn days tags of the target users.

[0079] Exemplarily, the recommendation configuration information further includes recommendation information, and the content of the recommendation information includes but is not limited to forms such as text, pictures, and text and pictures. For example: The game activity recommendation information is sent to the user terminal device in the form of a combination of text information and picture content.

[0080] In some embodiments, the first recommended configuration condition includes at least one of the following:

[0081] Condition 1: The level of the first object in the first application reaches a preconfigured level.

[0082] For example, the level can be the account's membership privilege level, or the game level of the virtual character corresponding to the account. The pre-configured level is set according to the actual application scenario. For example, the pre-configured level for the virtual character's game level can be set to level 30, and customized recommendation information will be sent to the terminal devices of users with a level greater than or equal to 30.

[0083] Condition 2: The time during which the first object has not logged into the first application reaches a second preconfigured time.

[0084] For example, the second pre-configured duration is set according to the actual application scenario. For example, if the second pre-configured duration is set to 30 days, users who have not logged into the game application for more than 30 days are considered churned users, and targeted recall recommendation information is sent to the churned users.

[0085] Condition 3: The total consumption of the first object for the first application is within the preconfigured quota range.

[0086] For example, the total amount of consumption can be the actual amount or the amount of points spent by the first subject's virtual character in the first application. The pre-configured limit range can be set according to the actual application scenario requirements. For example, if the pre-configured limit range is set to greater than 3,000 yuan, a recommendation message will be sent to users who have recharged more than 3,000 yuan.

[0087] Continue to refer Figure 3A In step 302, the first object data set is extracted and processed according to the first recommended configuration condition to obtain a second object data set.

[0088] Here, the second object data set includes object data of a plurality of different second objects, where the second objects are first objects that meet the first recommended configuration condition.

[0089] The contents of the first recommended configuration condition have been explained above and will not be repeated here.

[0090] In some embodiments, see Figure 3B , Figure 3B This is a second flow chart of the information recommendation method provided in an embodiment of the present application. Figure 3A Step 302 shown may be performed by Figure 3B Steps 3021 to 3022 are implemented as described below.

[0091] In step 3021, perform format conversion processing on the first recommended configuration condition to obtain the converted first recommended configuration condition.

[0092] Exemplarily, the converted first recommended configuration condition is in the form of a structured query language, such as an SQL statement, and the logic of the configured first recommended configuration condition is converted into an SQL statement.

[0093] In step 3022, call the converted first recommended configuration condition to perform query processing in the first object data set to obtain a second object data set that meets the first recommended configuration condition.

[0094] Exemplarily, use the SQL statement to perform a query operation in the database (CK), quickly filter out the required information from a large amount of user game application internal log data, and the execution result of the query processing is the user information of the second object. Store the object data set of the queried second object in the file system (COS).

[0095] Exemplarily, refer to Figure 9 , Figure 9 is the fourth interface schematic diagram of the system configuration first recommended configuration condition provided by the embodiments of the present application. In area 901, the recommended configuration condition can be set. For example, extract users who have been lost for more than 30 days, and the condition can be set to vtemp13 = '1' and is_stay_helper_friend = '1' and length(external_userid)>10.

[0096] In the embodiments of the present application, by performing extraction processing on the first object data set through the first recommended configuration condition, a second object data set can be obtained, realizing user classification based on the logs in the game application and performing targeted information recommendation for specific objects. Compared with the method of information recommendation to all users in the related art, it can save the computing resources required for information recommendation.

[0097] Continue to refer to Figure 3A , in step 303, determine the recommended information based on the first recommended configuration condition.

[0098] Here, the recommended information is used to be displayed in the second application of the terminal device associated with the second object, and the second application is different from the first application.

[0099] Exemplarily, as exemplified above, the first application can be a game application, and the second application is an application that can be used to receive recommended information. For example: the second application is an instant messaging application or a social application; for example: send game activity recommended information to the terminal device associated with the user's account, and display the game activity recommended information in the community of the instant messaging software in the terminal device.

[0100] In some embodiments, referring to Figure 3C , Figure 3C is the third process schematic diagram of the information recommendation method provided by the embodiments of the present application. Figure 3A The shown step 303 can be implemented by Figure 3C steps 3031A to 3032A below, which will be specifically described.

[0101] In step 3031A, obtain the mapping relationship between the first recommendation configuration condition and the recommendation information.

[0102] Exemplarily, the mapping relationship between the recommendation information and the first recommendation configuration condition is pre-stored in the database. The recommendation information can be pre-written by the operator. Or, the recommendation information is generated by calling the GPT model based on the prompt words provided by the operator.

[0103] In step 3032A, based on the mapping relationship, query the recommendation information corresponding to the first recommendation configuration condition in the recommendation configuration information.

[0104] Exemplarily, based on the mapping relationship between the first recommendation configuration condition and the recommendation information, find the recommendation information that matches the first recommendation configuration condition, and read the corresponding recommendation information configured by the operator, where the first recommendation configuration condition can set the specified recommendation time and recommendation frequency.

[0105] In some embodiments, referring to Figure 3D , Figure 3D is the fourth process schematic diagram of the information recommendation method provided by the embodiments of the present application. Figure 3A The shown step 303 can also be implemented by Figure 3D steps 3031B to 3033B below, which will be specifically described.

[0106] In step 3031B, obtain the pre-configured recommendation information template.

[0107] Here, the pre-configured recommendation information template includes: the maximum length of the recommendation information, the type of the recommendation information.

[0108] Exemplarily, the type of the recommendation information includes media information such as images, texts, audios or videos. The maximum length of the recommendation information can be set by the limitation conditions for sending messages in the second application. For example: if the maximum length of a single message sent in the second application is N characters, then the maximum length of the recommendation information can be N. N is a positive integer.

[0109] In step 3032B, based on the object data of each second object and the first recommendation configuration condition, call a neural network model to perform information generation processing to obtain the recommendation information content.

[0110] For example, based on the second object data and the first recommendation configuration condition, a text processing model is called to generate recommendation information. The text processing model can be a BERT model, which uses a bidirectional encoder and a transformer to model text. It can also consider the order of the text to better understand the meaning of the text. The text processing model can also be a transformer model (Transformer), which takes a text sequence as input and generates another text sequence as output. The input text sequence can be pre-written by the operator.

[0111] In step 3033B, the recommended information content is filled into the pre-configured recommended information template to obtain the recommended information.

[0112] For ease of understanding, the mechanism of delivering recommendation information is explained in this example. Figure 6 , Figure 6 It is a schematic diagram of the second interface of the recommended configuration information provided in the embodiment of the present application. As shown in area 601, the recommended configuration information interface displays in vertical columns the form of delivery content, delivery cycle, delivery frequency, delivery push time, award validity period, delivery calendar preview, and multiple customizable setting options such as the employee to be notified and the delivery name. The set recommendation information is sent to the user terminal device, and the delivery effect preview is shown in area 602. The award validity period means that the unclaimed reward of the first application recommended in the recommendation information is time-limited. For example: the unclaimed reward in the first application can be claimed within the preset time period. If the user's account does not log in to the first application within the preset time period, the reward cannot be claimed.

[0113] In an embodiment of the present application, by determining the corresponding recommendation information of the second object based on the first recommendation configuration condition, the recommendation information is matched with the information of the second object, thereby improving the relevance of the recommendation information and the second object, thereby improving the recommendation effect and enhancing the user's experience of information recommendation.

[0114] Continue to refer Figure 3A In step 304, in response to satisfying the recommendation condition, recommendation information is sent to the terminal device associated with the second object.

[0115] In some embodiments, the recommendation information includes: historical recommendation information and current recommendation information. The recommendation conditions include at least one of the following:

[0116] Condition 1: Get the current recommended information.

[0117] For example, when the current recommendation information is obtained, the obtained current recommendation information is directly sent to the user terminal device. That is, the current recommendation information is immediately recommended to the user terminal device upon receipt.

[0118] Condition 2: The duration between the current moment and the first moment reaches a first pre-configured duration, where the first moment is the moment when historical recommendation information was last sent to the terminal device of the second object.

[0119] Exemplarily, when the duration between the current moment and the last time the recommendation information was sent reaches a specified duration, it is determined to send the recommendation information to the user terminal device. The first pre-configured duration is set according to the requirements of the actual application scenario.

[0120] Condition 3: The current moment reaches a pre-configured sending moment.

[0121] Exemplarily, when the current moment reaches a specified time, it is determined to send the recommendation information to the user terminal device; the pre-configured sending moment is a time point pre-set according to the requirements of the actual application scenario.

[0122] Condition 4: The current moment is within a pre-configured time period for sending the recommendation information.

[0123] Exemplarily, when the current moment is within a specified time period for sending the recommendation information, it is determined to send the recommendation information to the user terminal device; the pre-configured time period can be a time cycle set by the operator according to the requirements of the actual application scenario. For example: The recommendation cycle can be set to 3 days.

[0124] In actual applications, due to network failures, when the pre-configured sending moment is reached, the recommendation information may not be sent successfully. Setting the recommendation information to be sendable within a certain time period can increase the probability of successful sending, and sending in time segments can relieve the load on the server for sending the recommendation information.

[0125] Condition 5: Within the pre-configured time period, the number of recommendation information received by the terminal device of the second object is less than a quantity threshold.

[0126] Exemplarily, when the number of recommendation information received by the user within a specified time period is lower than a preset threshold, it is determined to send the recommendation information to the user terminal device. The quantity threshold can be set to 5. When the number of recommendation information received by the user is less than 5, the recommendation information continues to be sent to the user terminal device.

[0127] In some embodiments, the recommendation information is for display in the community conversation interface or personal conversation interface of the terminal device.

[0128] Exemplarily, when the recommendation information is sent separately to the user's account, the recommendation information is displayed in the personal conversation interface of the user terminal device. In this case, the customer service number is pre-associated with the user's personal account. For example: The user's account follows the customer service number, or the user's account and the customer service number are friends; when the recommendation information is sent to the user group in a group, the recommendation information is displayed in the community conversation interface of the user terminal device.

[0129] See Figure 3E , Figure 3E which is the fifth process schematic diagram of the information recommendation method provided by the embodiments of the present application. Before the step 304 shown in Figure 3A , steps 305 to 307 of Figure 3E can also be executed. The following is a specific description.

[0130] In step 305, obtain the object identifiers of multiple third objects.

[0131] Exemplarily, the third object is different from the first object. The third object is a customer service account used by an operator, and the object identifier is the customer service number identifier (ID) of multiple customer service numbers. The recommended information corresponding to each second object is stored in the form of a media information stream.

[0132] In step 306, split the media information stream into multiple different sub-media information streams.

[0133] In some embodiments, each sub-media information stream includes multiple pieces of recommended information. The number of pieces of recommended information included in each sub-media information stream can be the same or different.

[0134] In step 307, associate each sub-media information stream with a different object identifier respectively to obtain an association result.

[0135] Here, the association result indicates that each third object corresponds to a different sub-media information stream respectively. Between the associated customer service number and the second object, the customer service number sends recommended information to the terminal device of the second object.

[0136] Exemplarily, referring to Figure 11 , Figure 11 is the schematic diagram of splitting a media information stream into sub-media information streams provided by the embodiments of the present application. For the media information stream S2, use the idea of the keyby operator routing, that is, data with the same key will enter the same parallel sub-task, and each sub-task can process multiple different keys. In this way, the data is ensured to be in order, and each sub-task is directly isolated from each other. Based on different customer service number IDs, split a message queue stream into non-overlapping partitions, and each partition contains elements with the same customer service number, that is, the message streams belonging to the same customer service number are in one partition. For example, obtain the identifiers 1101 and 1102 corresponding to different customer service number IDs, and associate each sub-media information stream with the corresponding customer service number ID respectively.

[0137] Continue to refer to Figure 3E , after step 307, step 304 can be executed through Figure 3E steps 308 to 309 of

[0138] In step 308, the sub-media information stream associated with the object identifier of each third object is obtained.

[0139] For example, the sub-media information stream associated with the customer service number identifier is obtained from the recommended media information stream corresponding to the second object.

[0140] In step 309, based on the object identifier of the third object, recommendation information is sent to each target terminal device corresponding to the sub-media information flow.

[0141] For example, the recommendation information is sent to the target terminal device corresponding to the sub-media information stream according to the customer service number identifier, and the target terminal device is the terminal device of the second object corresponding to the sub-media information stream.

[0142] In the embodiment of the present application, based on the association between the customer service number identifier and the sub-media information stream, recommendation information is sent to the target terminal device corresponding to the sub-media information stream, thereby reducing the error rate and omission rate of information recommendation; by batch-delivering the information collected in the partition at regular intervals, the efficiency of information recommendation is improved, and the customer service number only needs to be confirmed a very small number of times, saving labor costs. Compared with the solution in the related art that requires operators to manually send recommendation information to the user community through their own terminal devices, the recommendation information to be sent is stored in the form of a recommendation media information stream, and the server sends the recommendation information in a targeted manner when the corresponding recommendation conditions are met, saving computing resources and improving the efficiency of sending recommendation information.

[0143] In some embodiments, Figure 3A After step 304 , in response to receiving the login record of the second object for the first application, additional information is sent to the terminal device associated with the second object.

[0144] For example, the additional information is associated with the recommended information, and the additional information matches the object data of the second object. When a lapsed user logs into the game application, additional information is sent to the terminal device of the lapsed user based on the historical behavior and interest portrait data of the lapsed user, and the content of the additional information is associated with the historical behavior and interest portrait data of the lapsed user; when an active user logs into the game application, additional information is sent to the terminal device of the active user based on the historical behavior and interest portrait data of the active user, and the content of the additional information is associated with the historical behavior and interest portrait data of the active user. Among them, the terminal device is any device with a conversation function, and the terminal device can use the social function through the second application. The recommended information can be displayed in a one-to-one chat interface or a multi-person chat interface.

[0145] In some embodiments, the types of additional information include: virtual supplies in the first application; recommended content in the first application; and virtual tasks in the first application, wherein the virtual tasks are performed by a virtual object associated with the second object.

[0146] Exemplarily, the virtual goods in the first application, such as: game equipment packages in the game application that match the user interest profile. The recommended content in the first application, such as: game event recommendation information in the game application. The virtual tasks in the first application, such as: game tasks in the game application. The additional information has timeliness, and the expiration date for the user to receive the game package or task can be set. Beyond the expiration date, the user cannot receive the corresponding virtual task or virtual goods, or the virtual goods received by the user have timeliness and cannot be used continuously beyond the expiration date.

[0147] Exemplarily, refer to Figure 12 , Figure 12 is the fifth interface schematic diagram of the recommended additional information provided by the embodiments of the present application. When the additional information type is game event recommendation information, in the session interface 1201, the additional information sent to the user terminal device can be displayed. For example, the content of a game event recommendation information is displayed as: "Dear, are you ready to embrace the new challenges this week? There is a new outfit and a brand-new skin is on the line... You can claim it. Check out more details."

[0148] Next, the information recommendation method provided by the embodiments of the present application will be further described. In some embodiments, the information recommendation method provided by the embodiments of the present application can be jointly implemented by the first terminal, the second terminal, and the server. Among them, the first terminal is the terminal on the user side, and the second terminal is the terminal on the customer service side. Refer to Figure 13 , Figure 13 is the interaction process schematic diagram of the information recommendation method provided by the embodiments of the present application, and will be described in combination with Figure 13 the steps shown. The first terminal 401 can be Figure 1 the terminal device 400, the second terminal 402 is the terminal device used by the operator, and the game server 201 and the recommendation server 202 can form Figure 1 the server 200.

[0149] In step 1301, the second terminal 402 sends the recommendation configuration information to the recommendation server 202.

[0150] In step 1302, the game server 201 obtains the first object data set in the first application.

[0151] In step 1303, the game server 201 uploads the first object data set to the recommendation server 202.

[0152] In step 1304, the recommendation server 202 performs extraction processing on the first object data set according to the first recommendation configuration condition to obtain the second object data set.

[0153] In step 1305, the recommendation server 202 determines recommendation information based on the first recommendation configuration condition.

[0154] In step 1306, the recommendation server 202 sends the recommendation information to the first terminal 401.

[0155] In step 1307, the first terminal 401 receives and displays the recommendation information.

[0156] In the embodiments of the present application, the first object data set is extracted and processed based on the first recommendation configuration condition, and the second object data set is screened out, so that information can be recommended to specific objects in a targeted manner; the recommendation information corresponding to the second object is determined based on the first recommendation configuration condition, so that the recommendation information matches the information of the second object, improving the relevance between the recommendation information and the second object; based on the object identifier of the third object, the recommendation information is sent to each target terminal device corresponding to the sub-media information flow respectively, reducing the number of times of confirming the accuracy of the information to be recommended; and the recommendation information is pushed to the terminal device of the second object, so that the recommendation information is displayed in the second application, realizing cross-application of the recommendation information, expanding the recommendation channels, and improving the recommendation efficiency. Compared with the solution of uniformly delivering recommendation information in the related art, the computing resources for executing information recommendation can be saved.

[0157] Next, an exemplary application of the information recommendation method in the embodiments of the present application in an actual game operation application scenario will be described.

[0158] With the continuous development of Internet technology, games have become a very important form of leisure and entertainment. To ensure the normal operation of the game platform, it is necessary to regularly recommend game activity information to game users. When recommending information to active users and lost users respectively, it is usually necessary to manually screen the users to be recommended and send the game activity information to be recommended to the user terminal devices.

[0159] In the process of sending the recommendation information, it is necessary to convert the user's account on the game platform into the account of the user's community. Refer to Figure 4 Figure 4 which is a schematic diagram of the account association process provided in the related art. Based on the interaction behavior of the user on the game platform, the user is classified to determine the target users for sending the recommendation information. The game accounts of the target users are converted into community accounts, corresponding customer service numbers are assigned, and the community accounts of the target users are associated with the customer service numbers.

[0160] In the related art, when sending recommendation information from the game platform to the user terminal device, the following problems exist:

[0161] (1) When sending game activity information to all users, it seriously harasses users, and may even cause users to delete friend relationships, reducing user retention rate. (2) When customer service operators manually send game activity information to users, there may be situations such as missed or duplicate messages. If the number of users to be pushed is large, the information recommendation efficiency cannot be improved.

[0162] In the embodiments of the present application, in view of the problems existing in the related art, an information recommendation method is proposed. Compared with the related art, the improvements include the following aspects:

[0163] (1) Based on the historical behavior and interest portrait data of users on the game platform, target users to be recommended are screened, and information is recommended to specific target users in a targeted manner.

[0164] (2) Connect the community and the game account system to achieve cross-application of recommended information.

[0165] Reference Figure 8 , Figure 8 is a schematic flowchart of the information recommendation method provided by the embodiments of the present application. The following will Figure 1 take the server 200 in Figure 8 as the execution subject, and in combination with

[0166] In step 810, the recommendation configuration conditions are converted into SQL statements, and the database is queried based on the SQL statements.

[0167] Exemplarily, a first object data set and recommendation configuration information are obtained. The first object data set includes object data of multiple different first objects. The first object data set is the historical data such as the behavior and interest portrait of users in the game application. Among them, the historical data of users is stored in the database CK. The recommendation configuration information includes at least a first recommendation configuration condition. The first object data set is extracted and processed according to the first recommendation configuration condition to obtain a second object data set. The second object data set includes object data of multiple different second objects. Among them, the second object is the first object that meets the first recommendation configuration condition.

[0168] Exemplarily, different user packages are generated based on different historical data characteristics of users. Refer to Figure 5 , Figure 5This is a schematic diagram of the first interface for selecting target users provided by an embodiment of the present application. Region 501 includes multiple configurable attributes, and the types include: task objective, user package creation method, please select tags, and package volume estimation. For the task objective, the corresponding options include: return, announcement, and others. Among them, the meaning of "return" is to create a task for recalling lost game users; the meaning of "announcement" is to create a task for sending notification information to all game users. For the user package creation method, the corresponding option includes: single-tag package extraction, which means extracting user package data in the way of setting a single tag. For tag selection, the corresponding option can be set to users who have been lost for more than 30 days (excluding those launched in the recent 30 days). For package volume estimation, the corresponding options include: users who have been lost for more than 8 days (excluding those launched in the recent 30 days), users who have been lost for more than 14 days (excluding those launched in the recent 30 days), and users who have been lost for more than 30 days (excluding those launched in the recent 30 days). Among them, the index type includes standard tags, which means tags unified by different business logics, and the index description includes that all users with bound openid have been lost. Interface 502 also includes a process guide, which horizontally displays the process guide for setting target users on the upper side. The process guide includes: 1. Select target users; 2. Select gift package list; 3. Delivery configuration; 4. Delivery release. The process guide is used to prompt operators on how to set the target users of the information to be recommended.

[0169] Exemplarily, format conversion processing is performed on the first recommendation configuration condition to obtain the converted first recommendation configuration condition, where the converted first recommendation configuration condition is in the form of a structured query language, that is, converted into an SQL statement. The converted first recommendation configuration condition is called to perform query processing in the first object data set to obtain a second object data set that meets the first recommendation configuration condition. Refer to Figure 9 , Figure 9 This is a schematic diagram of the fourth interface for the system to configure the first recommendation configuration condition provided by an embodiment of the present application. Recommendation configuration conditions are set in region 901, for example: extract users who have been lost for more than 30 days, and the condition is set as vtemp13 = '1' and is_stay_helper_friend = '1' and length(external_userid)>10.

[0170] In step 811, the user information obtained from the query result is stored in the file system.

[0171] Through step 811, it is realized to quickly screen out the required information from a large amount of user data.

[0172] In step 812, the user information stored in the file system is exported to the message queue.

[0173] Exemplarily, by judging in real time whether the trigger condition of the delivery task configured by the game operation is triggered, and the trigger conditions such as delivery cycle, frequency, and time. Refer toFigure 10 , Figure 10 This is a schematic flowchart of the process for triggering the first recommendation configuration condition provided by an embodiment of the present application. The time interval for triggering the first recommendation configuration condition is set through a timer. In step S1, it is determined whether the task trigger condition is to be triggered. When it is determined that the trigger condition is satisfied, a scheduling process is initiated to export the user information of the file system to the message queue. When it is determined that the trigger condition is not satisfied, the task waits to be executed by the scheduling process again next time.

[0174] Exemplarily, the recommendation conditions include at least one of the following:

[0175] Immediate delivery: Once the current recommendation information is obtained, it can be directly delivered.

[0176] Periodic delivery: The duration between the current moment and the first moment reaches the first pre-configured duration, where the first moment is the moment when the historical recommendation information was last sent to the terminal device of the second object.

[0177] Scheduled delivery: When the current moment reaches the pre-configured sending moment, delivery can be carried out.

[0178] Within the delivery cycle: The current moment is within the pre-configured time period for sending recommendation information.

[0179] Delivery frequency: Within the pre-configured time period, the number of recommendation information received by the terminal device of the second object is less than the quantity threshold.

[0180] In step 813, the message queue is grouped.

[0181] Exemplarily, according to the delivery tasks configured for game operation, it is determined whether the user meets the delivery conditions such as delivery cycle, delivery frequency, delivery times limit, etc., so as to achieve refined delivery information on the community side. The second object is the user of the community-side APP, and the recommendation information corresponding to each second object is stored in the form of media information flow.

[0182] Exemplarily, referring to Figure 11 , Figure 11 This is a schematic diagram of splitting the media information flow into sub-media information flows provided by an embodiment of the present application. The media information flow S2 is split into multiple different sub-media information flows. Among them, each sub-media information flow includes multiple recommendation information. When the recommendation conditions are met, before sending the recommendation information to the terminal device associated with the second object, the object identifiers 1101 and 1102 of multiple third objects are obtained, f represents multiple third objects, and the object identifier of the third object is different customer service number IDs. Each sub-media information flow is respectively associated with the customer service number ID of a different customer service number to obtain an association result, where the association result represents that each customer service number is respectively associated with a different sub-media information flow.

[0183] In step 814, aggregate the message queue.

[0184] Exemplarily, at regular intervals, batch deliver different sub-media information flows. Based on the customer service number ID of different customer service numbers, send recommendation information to each target terminal device corresponding to the sub-media information flow, where the target terminal device is the terminal device of the second object corresponding to the sub-media information flow.

[0185] In step 815, send the recommendation information in the processed message queue to the user terminal device.

[0186] Exemplarily, after completing the setting by selecting the target user interface, click to enter the page for setting recommendation configuration information. Refer to Figure 6 , Figure 6 is the second interface schematic diagram of the recommendation configuration information provided by the embodiments of the present application. Figure 6 Shown in Figure 5 After the corresponding interface, the recommendation configuration information in area 601 includes the form of the delivered content, plain text, delivery period, delivery frequency, delivery push time, prize redemption validity period, delivery calendar preview, selection of employees to be notified, delivery name. Among them, the form of the delivered content is not limited to plain text, pictures, and pictures with text; the delivery period can select the start date and end date; the delivery frequency can be set to only deliver once (deliver immediately), deliver once on the day when the delivery period starts, and then deliver once every x days (x is a time value and can be customized with a specific value), deliver x times a week, etc. (x is a time value and can be customized with a specific value); the delivery push time can be customized; the prize redemption validity period can be set to the player can redeem the prize within x days after receiving the message (x is a time value and can be customized with a specific value); in the delivery calendar preview, options such as bag lifting and message push will be performed on the current day, and the valid prize redemption period of the user who receives the message can be set; in the option of selecting employees to be notified, the enterprise number can be entered for search. As Figure 6 shown on the right side, in area 602, a preview diagram of the effect of the delivered recommendation information is displayed.

[0187] Exemplarily, in response to receiving the login record of the second object in the game application, send additional information to the terminal device associated with the second object, where the additional information is associated with the recommendation information and matches the object data of the second object. The additional information is used to be displayed in the community session interface or personal session interface of the second object's terminal device.

[0188] Exemplarily, the types of additional information include: virtual materials in the game application; recommended content of game activities in the game application; virtual tasks in the game application, where the virtual tasks are executed by the virtual object associated with the second object. Refer to Figure 12 , Figure 12It is the fifth interface schematic diagram for recommending additional information provided by the embodiments of the present application. Recommended additional information is displayed in the conversation interface 1201. For example, the additional information is the recommended content of a game activity within a game application, and the information content is: "Dear, are you ready to embrace the new challenges this week? There is a new outfit and a brand-new skin is on the line... You can claim it. Check out more details." Figure 12 The additional information is the recommended content of a game activity.

[0189] For example, for long-term playing users, the JavaScript rule engine is used to determine the portrait to which the user belongs, and refined gift packages / tasks are pushed through the community chat interface. The rule engine includes:

[0190] The user's level within the game application reaches a pre-configured level, for example: above level 30.

[0191] The duration for which the user has not logged in to the game application reaches a pre-configured duration. For example, if the user has not logged in for 30 days, they can be marked as a lost user.

[0192] The total consumption amount of the user within the game application is within a pre-configured amount range, for example: the payment is greater than 3000 yuan, etc.

[0193] For example, for lost game users, determine the portrait to which the user belongs, and send notification messages through channels such as the community. When the received user logs in to the in-game interface of the game application, the game client will send a request to this full-link automated message delivery system, use the JavaScript rule engine to determine the portrait to which the player belongs, and push refined gift packages / tasks through the community chat interface.

[0194] For example, when the portrait to which the user belongs is a player below level 30, push an A-level gift package / task for users below level 30. Rule A: 'R1<30', where R1 is the player level indicator, generated based on the user's behavior logs within the game application. The rule engine queries the value of R1, runs this rule code through virtual machine technology and obtains the result. According to the 'true / false' judgment of the result, if the result is 'true', then push the gift package / task A configured by the game operation for 'R1<30'.

[0195] For example, the rule engine can also adopt a hard-coded method, for example:

[0196] if(r1<30)

[0197] return A

[0198] else if(r1>=30)

[0199] return B

[0200] That is, when the value of the user level indicator queried by the rule engine is less than 30, the A rule is returned, and an A-level gift package / task is pushed to the user; otherwise, when the value of the user level indicator is greater than or equal to 30, the B rule is returned, and a B-level gift package / task is pushed to the user. Among them, the advantage of hard coding is that when the rules are few and the changes are infrequent, the development efficiency is the highest and the stability is better. The compilation system ensures that syntax-level errors will not occur.

[0201] For example, refer to Figure 7 , Figure 7 FIG. is a schematic diagram of a third interface of the information recommendation progress provided by an embodiment of the present application. After sending the recommendation information to the user terminal device, the information recommendation progress can be viewed in real time. The progress interface 701 can display the delivery ID, delivery name, task target, user label, delivery cycle, delivery interval, delivery content, creation information, status, operations, and other contents.

[0202] In the above game operation scenario, the historical behaviors and interest portraits of users in the game platform are considered, and game activity information is pushed to the terminal devices where the users are located, thus ensuring the normal operation of the game platform. The community and the game account system are connected to realize the linkage between the in-game application and the out-of-game community. The out-of-game community is automatically and finely recommended with information, reducing the redundant messages sent to users, saving server resources, and improving the retention rate of game users.

[0203] Next, the implementation of the information recommendation device 455 provided by the embodiment of the present application as a software module will be further described. In some embodiments, as Figure 2 shown, the software module in the information recommendation device 455 stored in the memory 450 may include: a data acquisition module 4551, configured to acquire a first object data set and recommendation configuration information in a first application, where the recommendation configuration information includes at least a first recommendation configuration condition, and the first object data set includes object data of multiple different first objects; a data extraction module 4552, configured to perform extraction processing on the first object data set according to the first recommendation configuration condition to obtain a second object data set, where the second object data set includes object data of multiple different second objects, and the second object is a first object that meets the first recommendation configuration condition; a determination module 4553, configured to determine recommendation information based on the first recommendation configuration condition, where the recommendation information is used to be displayed in a second application of the terminal device of the second object, and the second application is different from the first application; a recommendation module 4554, configured to send the recommendation information to the terminal device associated with the second object in response to meeting the recommendation condition.

[0204] In some embodiments, the data extraction module 4552 is configured to perform format conversion processing on the first recommended configuration condition to obtain the converted first recommended configuration condition, wherein the converted first recommended configuration condition is in the form of a structured query language; call the converted first recommended configuration condition to perform query processing in the first object data set to obtain a second object data set that meets the first recommended configuration condition.

[0205] In some embodiments, the recommended configuration information further includes recommended information; the determination module 4553 is configured to obtain the mapping relationship between the first recommended configuration condition and the recommended information; query the recommended information corresponding to the first recommended configuration condition in the recommended configuration information based on the mapping relationship.

[0206] In some embodiments, the determination module 4553 is configured to obtain a pre-configured recommended information template, wherein the pre-configured recommended information template includes: the maximum length of the recommended information, the type of the recommended information; based on the object data of each second object and the first recommended configuration condition, call a neural network model to perform information generation processing to obtain the content of the recommended information; fill the content of the recommended information into the pre-configured recommended information template to obtain the recommended information.

[0207] In some embodiments, the recommended information includes: historical recommended information and current recommended information; the recommended conditions include at least one of the following: obtaining the current recommended information; the duration between the current moment and the first moment reaches a first pre-configured duration, wherein the first moment is the moment when the historical recommended information was last sent to the terminal device of the second object; the current moment reaches the pre-configured sending moment; the current moment is within the pre-configured time period for sending recommended information; within the pre-configured time period, the number of recommended information received by the terminal device of the second object is less than the number threshold.

[0208] In some embodiments, the recommended information corresponding to each second object is stored in the form of a media information stream; the recommendation module 4554 is configured to, before sending the recommended information to the terminal device associated with the second object in response to meeting the recommended conditions, obtain the object identifiers of multiple third objects, wherein the third objects are different from the first object; split the media information stream into multiple different sub-media information streams, wherein each sub-media information stream includes multiple recommended information; associate each sub-media information stream with a different object identifier respectively to obtain an association result, wherein the association result represents that each third object is respectively associated with a different sub-media information stream.

[0209] In some embodiments, the recommendation module 4554 is configured to obtain the sub-media information flow associated with the object identifier of each third object; perform the following processing for each third object: based on the object identifier of the third object, send recommendation information to each target terminal device corresponding to the sub-media information flow, where the target terminal device is the terminal device of the second object corresponding to the sub-media information flow.

[0210] In some embodiments, after the recommendation module 4554 is configured to send recommendation information to the terminal device associated with the second object in response to meeting the recommendation condition, in response to receiving the login record of the second object for the first application, the recommendation module 4554 sends additional information to the terminal device associated with the second object, where the additional information is associated with the recommendation information and matches the object data of the second object.

[0211] In some embodiments, the types of the additional information include: virtual items in the first application; recommended content in the first application; virtual tasks in the first application, where the virtual tasks are executed by the virtual object associated with the second object.

[0212] In some embodiments, the recommendation information is used to be displayed in the community session interface or the personal session interface of the terminal device.

[0213] In some embodiments, the first recommendation configuration condition includes at least one of the following: the level of the first object in the first application reaches a pre-configured level; the duration that the first object has not logged in to the first application reaches a second pre-configured duration; the total consumption amount of the first object for the first application is within a pre-configured amount range.

[0214] An embodiment of the present application provides a computer program product, which includes computer-executable instructions or a computer program. The computer-executable instructions or the computer program are stored in a computer-readable storage medium. The processor of the electronic device reads the computer-executable instructions or the computer program from the computer-readable storage medium, and the processor executes the computer-executable instructions or the computer program, so that the electronic device executes the information recommendation method described above in the embodiments of the present application.

[0215] An embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions or a computer program, where the computer-executable instructions or the computer program are stored. When the computer-executable instructions or the computer program are executed by a processor, it will cause the processor to execute the information recommendation method provided in the embodiments of the present application. For example, Figure 3A the information recommendation method shown.

[0216] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disc, or CD-ROM; or it may be various devices including one or any combination of the above memories.

[0217] In some embodiments, the computer-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 being deployed as an independent program or being deployed as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0218] As an example, the computer-executable instructions may or may not correspond to files in the file system, and may be stored as part of a file that stores other programs or data. For example, they may be stored in one or more scripts in a HyperText Markup Language (HTML) document, stored in a single file dedicated to the program in question, or stored in multiple cooperating files (e.g., files that store one or more modules, subroutines, or portions of code).

[0219] As an example, the computer-executable instructions may be deployed to execute on one electronic device, or on multiple electronic devices located at one location, or on multiple electronic devices distributed at multiple locations and interconnected by a communication network.

[0220] In summary, by performing extraction processing on the first object data set based on the first recommendation configuration condition and screening to obtain the second object data set, it is possible to perform information recommendation directed to specific objects; based on the first recommendation configuration condition, determine the corresponding recommendation information for the second object, so that the recommendation information matches the information of the second object, enhancing the relevance between the recommendation information and the second object; and push the recommendation information to the terminal device of the second object, so that the recommendation information is displayed in the second application, realizing cross-application of the recommendation information, expanding the recommendation channels, and improving the recommendation efficiency.

[0221] The above is only for the embodiments of the present application and is not intended to limit the protection scope of the present application. Any modifications, equivalent replacements, and improvements made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims

1. An information recommendation method, characterized in that, The method includes: Obtaining a first object data set and recommendation configuration information in a first application, where the recommendation configuration information includes at least a first recommendation configuration condition, and the first object data set includes object data of multiple different first objects; Performing extraction processing on the first object data set according to the first recommendation configuration condition to obtain a second object data set, where the second object data set includes object data of multiple different second objects, and the second objects are first objects that meet the first recommendation configuration condition; Determining recommendation information based on the first recommendation configuration condition, where the recommendation information is used to be displayed in a second application of a terminal device associated with the second object, and the second application is different from the first application; In response to meeting the recommendation condition, sending the recommendation information to the terminal device associated with the second object.

2. The method according to claim 1, wherein The performing extraction processing on the first object data set according to the first recommendation configuration condition to obtain a second object data set includes: Performing format conversion processing on the first recommendation configuration condition to obtain a converted first recommendation configuration condition, where the converted first recommendation configuration condition is in the form of a structured query language; Invoking the converted first recommendation configuration condition to perform query processing in the first object data set to obtain a second object data set that meets the first recommendation configuration condition.

3. The method according to claim 1, wherein The recommendation configuration information further includes the recommendation information; The determining recommendation information based on the first recommendation configuration condition includes: Obtaining the mapping relationship between the first recommendation configuration condition and the recommendation information; Querying the recommendation information corresponding to the first recommendation configuration condition in the recommendation configuration information based on the mapping relationship.

4. The method according to claim 1, wherein The determining recommendation information based on the first recommendation configuration condition includes: Obtaining a pre-configured recommendation information template, where the pre-configured recommendation information template includes: maximum length of the recommendation information, type of the recommendation information; Based on the object data of each second object and the first recommendation configuration condition, invoking a neural network model to perform information generation processing to obtain recommendation information content; Filling the recommendation information content into the pre-configured recommendation information template to obtain the recommendation information.

5. The method according to claim 1, characterized in that, The recommendation information includes: historical recommendation information and current recommendation information; the recommendation condition includes at least one of the following: Obtaining the current recommendation information; The duration between the current moment and the first moment reaches a first pre-configured duration, where the first moment is the moment when the historical recommendation information was last sent to the terminal device of the second object; The current moment reaches a pre-configured sending moment; The current moment is within a pre-configured time period for sending the recommendation information; Within the pre-configured time period, the number of recommendation information received by the terminal device of the second object is less than a quantity threshold.

6. The method according to claim 1, characterized in that, The recommendation information corresponding to each second object is stored in the form of a media information stream; Before the sending the recommendation information to the terminal device associated with the second object in response to meeting the recommendation condition, the method further includes: Obtain the object identifiers of multiple third objects, where the third objects are different from the first object; Split the media information flow into multiple different sub-media information flows, where each sub-media information flow includes multiple pieces of the recommendation information; Associate each sub-media information flow with a different object identifier respectively to obtain an association result, where the association result indicates that each third object is respectively associated with a different sub-media information flow.

7. The method according to claim 6, wherein The sending the recommendation information to the terminal device associated with the second object includes: Obtain the sub-media information flow associated with the object identifier of each third object; Perform the following processing for each third object: Based on the object identifier of the third object, send the recommendation information to each target terminal device corresponding to the sub-media information flow respectively, where the target terminal device is the terminal device of the second object corresponding to the sub-media information flow.

8. The method according to any one of claims 1 to 7, characterized in that, After sending the recommendation information to the terminal device associated with the second object in response to meeting the recommendation condition, the method further includes: In response to receiving the login record of the second object for the first application, send additional information to the terminal device associated with the second object, where the additional information is associated with the recommendation information and the additional information matches the object data of the second object.

9. The method according to claim 8, characterized in that, The types of the additional information include: Virtual items in the first application; Recommended content in the first application; Virtual tasks in the first application, where the virtual tasks are executed by the virtual object associated with the second object.

10. The method according to any one of claims 1 to 7, characterized in that, The recommendation information is used to be displayed in the community session interface or personal session interface of the terminal device.

11. The method according to any one of claims 1 to 4, characterized in that, The first recommendation configuration condition includes at least one of the following: The level of the first object in the first application reaches a pre-configured level; The duration that the first object has not logged in to the first application reaches a second pre-configured duration; The total consumption amount of the first object for the first application is within a pre-configured amount range.

12. An information recommendation device, characterized in that, The device includes: A data acquisition module, configured to acquire a first object data set and recommendation configuration information in a first application, where the recommendation configuration information includes at least a first recommendation configuration condition, and the first object data set includes object data of multiple different first objects; A data extraction module, configured to perform an extraction process on the first object data set according to the first recommendation configuration condition to obtain a second object data set, where the second object data set includes object data of multiple different second objects, and the second objects are first objects that meet the first recommendation configuration condition; A determination module, configured to determine recommendation information based on the first recommendation configuration condition, where the recommendation information is used to be displayed in a second application on the terminal device of the second object, and the second application is different from the first application; A recommendation module, configured to send the recommendation information to the terminal device associated with the second object in response to meeting the recommendation condition.

13. An electronic device, characterized in that, The electronic device includes: A memory, configured to store computer-executable instructions or computer programs; A processor, when executing computer-executable instructions or a computer program stored in the memory, implements the information recommendation method according to any one of claims 1 to 11.

14. A computer-readable storage medium storing computer-executable instructions or a computer program, characterized in that, When the computer-executable instructions or the computer program are executed by the processor, the information recommendation method according to any one of claims 1 to 11 is implemented.

15. A computer program product, comprising computer-executable instructions or a computer program, characterized in that, When the computer-executable instructions or the computer program are executed by the processor, the information recommendation method according to any one of claims 1 to 11 is implemented.

Images