Processing method, computing device and storage medium

Abstract

The invention provides a processing method, computing equipment and a storage medium, and the processing method comprises the steps: S1, generating recommendation information corresponding to a region according to objects in an object set; and S2, carrying out pushing processing on the recommendation information corresponding to the region. According to the technical scheme, the regional object pushing process can be simplified, and the object pushing efficiency and effect are improved.

Description

Technical Field

[0001] This application relates to the field of information processing technology, specifically to a processing method, computing device, and storage medium. Background Technology

[0002] In conceiving and implementing this application, the inventors discovered at least the following problem: how to optimize the regional object push process is a technical problem that urgently needs to be solved by those skilled in the art.

[0003] The preceding description is intended to provide general background information and does not necessarily constitute prior art. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides a processing method, processing system, computing device, and storage medium that can optimize the regional object push process and improve object push efficiency and effectiveness.

[0005] This application provides a processing method, including the following steps: S1: generating recommendation information corresponding to a region based on objects in an object set; S2: pushing the recommendation information corresponding to the region.

[0006] Optionally, step S1 includes at least one of the following: Identify one or more regions where the target audience needs to be pushed to. Determine one or more primary processing models; Obtain one or more first model input instructions; Based on the first model input instruction, the first processing model, and the region, the objects in the object set are subjected to thematic clustering to obtain recommendation information corresponding to each region. Recommended information includes object clustering results and topical content; The content of the special feature includes at least one of the following: theme, promotional image information, and descriptive content.

[0007] Optionally, the processing method of this application further includes at least one of the following: Perform content verification on the recommended information to obtain recommended information that has completed content verification; In response to the completion of push notification processing, perform push notification effect analysis and / or model optimization.

[0008] Optionally, it includes at least one of the following: Content verification is performed based on the topic content in the recommendation information and the second processing model to obtain recommendation information with completed content verification; The system performs filtering based on user behavior feature database, third processing model and at least some recommendation information to obtain target recommendation information that matches the target user, and / or pushes the target recommendation information. Optionally, the second processing model is used to verify the compliance of the topic content in the recommended information based on the legal and regulatory information and / or the prohibited word database corresponding to a specific region.

[0009] Optionally, the content validation process includes at least one of the following: The second processing model is used to perform compliance verification on the topic content in the recommended information, and the verification results are output. When the verification results indicate that the topic content is compliant, the recommended information corresponding to the topic content is deemed to have completed content verification; or, when the verification results indicate that the topic content is compliant, a manual audit task is issued. When the verification results indicate that the content of a specific topic violates regulations, a manual audit task will be issued. When the audit result corresponding to the received manual audit task indicates that the audit has passed, it is determined that the recommended information corresponding to the topic content has been verified. When the audit results of a received manual audit task indicate that there is illegal content, the illegal content will be added to the prohibited word library or the illegal content already included in the prohibited word library will be given more weight by the model for identification.

[0010] Optionally, in response to the completion of push notification processing, push notification performance analysis and / or model optimization processing are performed, including at least one of the following: In response to the completion of push processing, listen for the reported information fed back after the smart terminal displays the recommended information; The effectiveness of the push notifications is analyzed based on the reported information received, in order to obtain information on the effectiveness of the push notifications from at least one dimension. Based on the push effect information, the model and / or model input instructions corresponding to the recommendation information are subjected to performance evaluation and / or optimization processing.

[0011] Optionally, the performance evaluation process includes: Based on the fourth processing model and the push effect information, the model performance of the model corresponding to the recommendation information and / or the model input instructions is evaluated to determine the execution effect information of the model corresponding to the recommendation information and / or the execution effect information of the model input instructions corresponding to the recommendation information.

[0012] This application also provides a processing system, including a smart terminal and a server; the server is used to execute the steps of the processing method described in any of the above technical solutions; the smart terminal is used to respond to the server by pushing recommendation information corresponding to a region and displaying the received recommendation information.

[0013] This application also provides a computing device, including: a memory and a processor, wherein the memory stores a processing program, and when the processing program is executed by the processor, it implements the steps of the processing method as described in any of the preceding claims.

[0014] This application also provides a storage medium storing a computer program that, when executed by a processor, implements the steps of the processing method described in any of the preceding claims.

[0015] As described above, the processing method, computing device, and storage medium of this application include the following steps: S1: generating recommendation information corresponding to different regions based on objects in the object set; S2: pushing the recommendation information corresponding to different regions. Through the technical solution of this application, different recommendation information can be generated according to different regions based on objects in the object set, and objects can be pushed according to each recommendation information and its corresponding region. Thus, the technical solution of this application simplifies the regional object push process and improves the efficiency and effectiveness of object push. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without any creative effort.

[0017] Figure 1 A schematic diagram of the hardware structure of a mobile terminal to implement the various embodiments of this application.

[0018] Figure 2 This is a communication network system architecture diagram provided for an embodiment of this application.

[0019] Figure 3 This is a flowchart illustrating the processing method according to the first embodiment.

[0020] Figure 4 This is an interface diagram of a smart terminal displaying recommended information, based on the example in this application.

[0021] Figure 5 This is a first flowchart illustrating the processing method according to the second embodiment.

[0022] Figure 6 This is a second flowchart illustrating the processing method according to the second embodiment.

[0023] Figure 7 This is a schematic diagram of the processing system according to the third embodiment.

[0024] The realization of the objectives, functional features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. The accompanying drawings have illustrated specific embodiments of this application, which will be described in more detail below. These drawings and textual descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0025] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0026] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of this application may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.

[0027] It should be understood that although the terms first, second, third, etc., may be used herein to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this document, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if," as used herein, may be interpreted as "when," "when," or "in response to determination." Furthermore, as used herein, the singular forms "a," "an," and "the" are intended to also include the plural forms unless the context indicates otherwise. It should be further understood that the terms "comprising," "including," indicate the presence of the stated feature, step, operation, element, component, item, kind, and / or group, but do not exclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, kinds, and / or groups. The terms "or," "and / or," "including at least one of the following," etc., as used in this application, may be interpreted as inclusive, or mean any one or any combination thereof. For example, "including at least one of the following: A, B, C" means "any one of the following: A; B; C; A and B; A and C; B and C; A and B and C." Similarly, "A, B, or C" or "A, B, and / or C" means "any one of the following: A; B; C; A and B; A and C; B and C; A and B and C." Exceptions to this definition only occur when the combination of elements, functions, steps, or operations is inherently mutually exclusive in some way.

[0028] It should be understood that although the steps in the flowcharts of this application's embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0029] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0030] It should be noted that step designations such as S1 and S2 are used in this document for the purpose of more clearly and concisely describing the corresponding content, and do not constitute a substantial limitation on the order. In specific implementation, those skilled in the art may execute S2 first and then S1, etc., but these should all be within the protection scope of this application.

[0031] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0032] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.

[0033] Smart terminals can be implemented in various forms. For example, the smart terminals described in this application may include smart terminals such as mobile phones, tablets, laptops, handheld computers, personal digital assistants (PDAs), portable media players (PMPs), navigation devices, wearable devices, smart bracelets, pedometers, etc., as well as fixed terminals such as digital TVs and desktop computers.

[0034] The following description will use a mobile terminal as an example. Those skilled in the art will understand that, apart from elements specifically designed for mobile purposes, the construction according to the embodiments of this application can also be applied to fixed-type terminals.

[0035] Please see Figure 1 This is a schematic diagram of the hardware structure of a mobile terminal implementing various embodiments of this application. The mobile terminal 100 may include: an RF (Radio Frequency) unit 101, a WiFi module 102, an audio output unit 103, an A / V (Audio / Video) input unit 104, a sensor 105, a display unit 106, a user input unit 107, an interface unit 108, a memory 109, a processor 110, and a power supply 111, etc. Those skilled in the art will understand that... Figure 1 The mobile terminal structure shown does not constitute a limitation on the mobile terminal. The mobile terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0036] The following is combined Figure 1 A detailed introduction to each component of the mobile terminal: The radio frequency unit 101 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink information from the base station and processes it with the processor 110; additionally, it transmits uplink data to the base station. Typically, the radio frequency unit 101 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier, and a duplexer. Furthermore, the radio frequency unit 101 can also communicate wirelessly with networks and other devices. The aforementioned wireless communications may use any communication standard or protocol, including but not limited to GSM (Global System of Mobile communication), GPRS (General Packet Radio Service), CDMA2000 (Code Division Multiple Access 2000), WCDMA (Wideband Code Division Multiple Access), TD-SCDMA (Time Division-Synchronous Code Division Multiple Access), FDD-LTE (Frequency Division Duplexing-Long Term Evolution), TDD-LTE (Time Division Duplexing-Long Term Evolution), 5G, and 6G.

[0037] WiFi is a short-range wireless transmission technology. Mobile terminals, through the WiFi module 102, can help users send and receive emails, browse web pages, and access streaming media, providing users with wireless broadband internet access. Although Figure 1 WiFi module 102 is shown, but it is understood that it is not a necessary component of a mobile terminal and can be omitted as needed without changing the nature of the invention.

[0038] The audio output unit 103 can convert audio data received by the radio frequency unit 101 or the WiFi module 102 or stored in the memory 109 into audio signals and output them as sound when the mobile terminal 100 is in call signal receiving mode, call mode, recording mode, voice recognition mode, broadcast receiving mode, etc. Furthermore, the audio output unit 103 can also provide audio output related to specific functions performed by the mobile terminal 100 (e.g., call signal receiving sound, message receiving sound, etc.). The audio output unit 103 may include a speaker, a buzzer, etc.

[0039] The A / V input unit 104 is used to receive audio or video signals. The A / V input unit 104 may include a graphics processing unit (GPU) 1041 and a microphone 1042. The GPU 1041 processes image data of still images or videos acquired by an image capture device (such as a camera) in video capture mode or image capture mode. The processed image frames can be displayed on the display unit 106. The image frames processed by the GPU 1041 can be stored in the memory 109 (or other storage media) or transmitted via the radio frequency unit 101 or the WiFi module 102. The microphone 1042 can receive sound (audio data) in operating modes such as telephone call mode, recording mode, and voice recognition mode, and can process such sound into audio data. The processed audio (voice) data can be converted into a format that can be transmitted to a mobile communication base station via the radio frequency unit 101 in telephone call mode. The microphone 1042 can implement various types of noise cancellation (or suppression) algorithms to eliminate (or suppress) noise or interference generated during the reception and transmission of audio signals.

[0040] The mobile terminal 100 also includes at least one sensor 105, such as a light sensor, a motion sensor, and other sensors. Optionally, the light sensor includes an ambient light sensor and a proximity sensor. Optionally, the ambient light sensor can adjust the brightness of the display panel 1061 according to the ambient light level, and the proximity sensor can turn off the display panel 1061 and / or backlight when the mobile terminal 100 is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that recognize the phone's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc. Other sensors that may be configured in the phone, such as fingerprint sensors, pressure sensors, iris sensors, molecular sensors, gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, will not be described in detail here.

[0041] The display unit 106 is used to display information input by the user or information provided to the user. The display unit 106 may include a display panel 1061, which may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0042] User input unit 107 can be used to receive input numerical or character information, and generate key signal inputs related to user settings and function control of the mobile terminal. Optionally, user input unit 107 may include touch panel 1071 and other input devices 1072. Touch panel 1071, also known as touch screen, can collect touch operations on or near the user (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near touch panel 1071), and drive corresponding connection devices according to a pre-set program. Touch panel 1071 may include two parts: a touch detection device and a touch controller. Optionally, the touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, sends it to processor 110, and can receive and execute commands sent by processor 110. In addition, touch panel 1071 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 1071, the user input unit 107 may also include other input devices 1072. Optionally, other input devices 1072 may include, but are not limited to, one or more of the following: physical keyboard, function keys (such as volume control buttons, power buttons, etc.), trackball, mouse, joystick, etc., without being specifically limited here.

[0043] Optionally, the touch panel 1071 may cover the display panel 1061. When the touch panel 1071 detects a touch operation on or near it, it transmits the information to the processor 110 to determine the type of touch event. Subsequently, the processor 110 provides corresponding visual output on the display panel 1061 based on the type of touch event. Although in Figure 1 In this embodiment, the touch panel 1071 and the display panel 1061 are two independent components to realize the input and output functions of the mobile terminal. However, in some embodiments, the touch panel 1071 and the display panel 1061 can be integrated to realize the input and output functions of the mobile terminal. The specific implementation is not limited here.

[0044] Interface unit 108 serves as an interface through which at least one external device can connect to mobile terminal 100. For example, the external device may include a wired or wireless headset port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, an audio input / output (I / O) port, a video I / O port, a headphone port, and so on. Interface unit 108 may be used to receive input (e.g., data, power, etc.) from the external device and transmit the received input to one or more elements within mobile terminal 100, or it may be used to transmit data between mobile terminal 100 and the external device.

[0045] The memory 109 can be used to store software programs and various data. The memory 109 may primarily include a program storage area and a data storage area. Optionally, the program storage area may store the operating system, applications required for at least one function (such as sound playback, image playback, etc.), etc.; the data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). Furthermore, the memory 109 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0046] The processor 110 is the control center of the mobile terminal. It connects various parts of the mobile terminal via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 109, and by calling data stored in the memory 109, it performs various functions and processes data of the mobile terminal, thereby providing overall monitoring of the mobile terminal. The processor 110 may include one or more processing units; preferably, the processor 110 may integrate an application processor and a modem processor. Optionally, the application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 110.

[0047] The mobile terminal 100 may also include a power supply 111 (such as a battery) that supplies power to various components. Preferably, the power supply 111 can be logically connected to the processor 110 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system.

[0048] although Figure 1 As not shown, the mobile terminal 100 may also include a Bluetooth module, etc., which will not be described in detail here.

[0049] To facilitate understanding of the embodiments of this application, the communication network system on which the mobile terminal of this application is based is described below.

[0050] Please see Figure 2 , Figure 2 This application provides a communication network system architecture diagram. The communication network system is an LTE system based on the universal mobile communication technology. The LTE system includes a UE (User Equipment) 201, an E-UTRAN (Evolved UMTS Terrestrial Radio Access Network) 202, an EPC (Evolved Packet Core) 203, and the operator's IP services 204, which are connected in sequence.

[0051] Optionally, UE201 can be the aforementioned terminal 100, which will not be described in detail here.

[0052] E-UTRAN202 includes eNodeB2021 and other eNodeB2022s. Optionally, eNodeB2021 can connect to other eNodeB2022s via backhaul (e.g., X2 interface). eNodeB2021 connects to EPC203 and can provide UE201 with access to EPC203.

[0053] EPC203 may include an MME (Mobility Management Entity) 2031, an HSS (Home Subscriber Server) 2032, other MMEs 2033, an SGW (Serving Gateway) 2034, a PGW (Packet Data Network Gateway) 2035, and a PCRF (Policy and Charging Rules Function) 2036, etc. Optionally, MME2031 is the control node that handles signaling between UE201 and EPC203, providing bearer and connection management. HSS2032 is used to provide registers to manage functions such as the Home Location Register (not shown in the figure) and stores user-specific information such as service characteristics and data rates. All user data can be sent through SGW2034. PGW2035 can provide UE 201 IP address allocation and other functions. PCRF2036 is the policy and charging control decision point for service data flow and IP bearer resources. It selects and provides available policy and charging control decisions for the policy and charging enforcement function unit (not shown in the figure).

[0054] IP services 204 may include the Internet, intranet, IMS (IP Multimedia Subsystem), or other IP services.

[0055] Although the above description uses the LTE system as an example, those skilled in the art should know that this application is not only applicable to the LTE system, but also to other wireless communication systems, such as GSM, CDMA2000, WCDMA, TD-SCDMA, 5G and future new network systems (such as 6G), etc., without limitation.

[0056] Based on the above-described mobile terminal hardware structure and communication network system, various embodiments of this application are proposed.

[0057] First Embodiment Reference Figure 3 , Figure 3 This is a flowchart illustrating the processing method according to the first embodiment (hereinafter referred to as "this embodiment"). The processing method of this embodiment can be applied to computing devices (such as servers) and includes the following steps: S1: Generate recommendation information corresponding to the region based on the objects in the object collection.

[0058] Optionally, the object can represent a resource that can be pushed or distributed to a smart terminal. Optionally, after the object is pushed or distributed to a smart terminal, it can interact with the user or the usage scenario.

[0059] Optionally, the objects include, but are not limited to, applications, multimedia content, goods, services, etc.

[0060] Optionally, the collection of objects may include one or more objects.

[0061] Alternatively, the methods for generating the object collection include, but are not limited to, at least one of the following: Receives a selection operation on an object to add the selected object to the object collection; Based on preset selection criteria, objects that meet the selection criteria are added to the object collection.

[0062] Optionally, selection criteria can represent arbitrary filtering conditions for selecting objects that meet specific requirements from a large number of objects.

[0063] Optionally, objects that meet the selection criteria include, but are not limited to, at least one of the following: Newly developed or generated objects; There are objects whose content is being updated; Objects that are related to the characteristics of the current environment.

[0064] Optionally, the current environmental characteristics include at least one of the following: current time, current location, etc.

[0065] Optionally, the recommendation information corresponding to a region can be represented as any information involved when pushing a specific object from a set of objects in a specific region.

[0066] Optionally, when the recommended information includes promotional content targeting one or more specific targets, the promotional content must comply with the language, laws and regulations, or cultural customs of the specific region.

[0067] Optionally, the method of generating recommendation information corresponding to a region based on objects in the object set can be, but is not limited to, generating recommendation information corresponding to a region through a processing model. Thus, the technical solution in this example can automatically generate recommendation information corresponding to a region based on objects in the object set through a processing model, avoiding manual intervention and improving the efficiency of recommendation information generation.

[0068] Optionally, step S1 may include: performing thematic clustering on the objects in the object set based on the characteristic information corresponding to the objects in the object set, so as to obtain recommendation information corresponding to the region.

[0069] Optionally, the characteristic information corresponding to the object represents information describing or defining the key features of the object, and / or information used to support clustering through a clustering algorithm.

[0070] Optionally, key features include, but are not limited to, at least one of the following dimensions: object name or theme, logo, technical identifier, functional category, target market, target audience, developer, object category, and usage scenario. Taking an application as an example, the application's feature information includes the application name, application type, target audience, country of development or launch, and usage scenario.

[0071] Optionally, the recommendation information may include object clustering results and topical content. Optionally, object clustering results may represent one or more target objects with the same or similar characteristics obtained after clustering based on the characteristic information corresponding to objects in the object set. Topical content may represent promotional content obtained based on the same or similar characteristics of multiple target objects in the clustering results.

[0072] Optionally, the content of the special feature may include, but is not limited to, at least one of the following: theme, promotional image information, and descriptive content.

[0073] For example, when a smart terminal displays recommendation information corresponding to an application, it may display at least one of the following: object clustering results and their corresponding themes, promotional images, and descriptive content, to attract the user of the smart terminal to select or interact with target objects in the object clustering results. Figure 4 As shown, the object clustering results displayed on the smart terminal include applications A1, A2, and A3, with the theme "Enjoy Wonderful Applications". Figure 4 The entire background image in the image is the promotional image information.

[0074] Optionally, thematic clustering processing may include: clustering objects in the object set according to the characteristic information corresponding to the objects in the object set to obtain one or more object clustering results; generating thematic content corresponding to a region based on the characteristic information of the target objects in the object clustering results; and obtaining recommendation information corresponding to the region based on the object clustering results and their corresponding thematic content. Thus, the technical solution of this embodiment can treat multiple objects with similar characteristics as a whole and attach promotional content corresponding to its characteristics as recommendation information. This recommendation information can support the display of promotional content on smart terminals to attract the attention of smart terminal users, thereby attracting users to operate on and display multiple objects with similar characteristics corresponding to the promotional content, thus improving the conversion rate of the pushed content.

[0075] S2: Push recommendation information corresponding to the region.

[0076] Optionally, push processing can represent pushing recommendation information to smart terminals in their corresponding regions to support the smart terminals in displaying the acquired recommendation information.

[0077] The processing method provided in this embodiment includes the following steps: S1: generating recommendation information corresponding to a region based on the objects in the object set; S2: pushing the recommendation information corresponding to the region. Through the technical solution of this embodiment, different recommendation information can be generated according to different regions based on the objects in the object set, and objects can be pushed according to each recommendation information and its corresponding region. Thus, the technical solution of this application simplifies the regional object push process and improves the efficiency and effectiveness of object push.

[0078] Second Embodiment Based on the technical solution of the first embodiment, a second embodiment of this application is proposed. Contents that are the same as or similar to those of the first embodiment can be referred to the above description and will not be repeated hereafter. This embodiment provides a processing method, including: S1: Generate recommendation information corresponding to the region based on the objects in the object set; S2: Push recommendation information corresponding to the region.

[0079] Optionally, the recommendation information corresponding to a region can be represented as any information involved when pushing a specific object from a set of objects in a specific region.

[0080] Optionally, the recommended information includes object clustering results and topical content.

[0081] Optionally, the topic content may include at least one of the following: theme, promotional image information, and descriptive content.

[0082] Optionally, refer to Figure 6Step S1 may include: Step S101: Based on the characteristic information corresponding to the objects in the object set and at least one first processing model, perform thematic clustering processing on the objects in the object set to obtain recommendation information corresponding to at least one region.

[0083] Optionally, the first processing model can be a pre-built dedicated model or a mature general model.

[0084] Optionally, the first processing model can be used to cluster objects in an object set based on their characteristic information, and generate promotional content based on the common or similar characteristics of each object in the clustering results to obtain thematic content. Alternatively, it can be used to generate promotional content based on the characteristic information of each object in the object set to obtain thematic content corresponding to the object set. Thus, the technical solution of this embodiment can conveniently and efficiently obtain or generate recommendation information corresponding to one or more regions through the first processing model.

[0085] Optionally, the first processing model may include a generative model.

[0086] Optionally, the first processing model can be custom-developed or trained based on a mature generative model framework. In this way, the clustering ability and / or promotional content generation ability of the first processing model can be improved in terms of professionalism through iteration, and it has the advantages of low cost and trainability.

[0087] Optionally, the clustering capability and / or promotional content generation capability of the first processing model can be implemented by its constituent sub-models. Optionally, the first processing model may include a clustering model and a promotional content generation model. Thus, the first processing model consists of multiple sub-models with different functions, enabling the generation of recommendation information by leveraging the functions of different models, and balancing the generation effect and cost of recommendation information. Furthermore, clustering and promotional content generation employ different sub-models, and by utilizing the characteristics of different sub-models, both effectiveness and cost can be considered.

[0088] Optionally, step S1, or the step of performing thematic clustering on the objects in the object set based on the characteristic information corresponding to the objects in the object set and at least one first processing model, to obtain recommendation information corresponding to at least one region, includes at least one of the following: Identify one or more regions where the target audience needs to be pushed to. Determine one or more primary processing models; Obtain one or more first model input instructions; Based on the input instructions of the first model, the first processing model, and the region, the objects in the object set are subjected to thematic clustering to obtain recommendation information corresponding to each region.

[0089] Optionally, the first model input instruction can represent information that guides the first processing model to perform clustering and / or promotional content generation according to specific requirements.

[0090] Optionally, the first processing model can be associated with a region. Optionally, a region can be associated with one or more first processing models.

[0091] For example, when each region is associated with multiple first processing models (at least some of the model parameters in the multiple first processing models are different), each first processing model corresponding to a specific region can first cluster the objects in the object set to obtain one or more object clustering results, and then generate one or more thematic content corresponding to the specific region based on the same or similar characteristics of each object in each object clustering result (at least some of the thematic content contains different specific content), and determine one thematic content to form recommendation information corresponding to the specific region with its corresponding specific object clustering result, and perform subsequent steps (such as step S2) to realize the push processing of the specific region according to the recommendation information corresponding to each of the at least some object clustering results, or, form multiple recommendation information including the same object clustering result based on the object clustering result and its corresponding multiple thematic content, and perform subsequent steps (such as step S2) on at least some of the recommendation information, thereby realizing the push processing of the specific region according to the one or more recommendation information corresponding to each of the at least some object clustering results.

[0092] For example, based on the characteristic information corresponding to objects in the object set and multiple first processing models corresponding to a specific region, performing thematic clustering processing on the objects in the object set to obtain multiple recommendation information corresponding to a specific region may include: determining a first model input instruction, and clustering and generating promotional content for the objects in the object set according to the first model input instruction and multiple first processing models corresponding to a specific region to obtain multiple recommendation information; or, determining multiple first model input instructions, and clustering and generating promotional content for the objects in the object set according to the multiple model input instructions and multiple first processing models corresponding to a specific region to obtain multiple recommendation information corresponding to a specific region.

[0093] For example, if each region is associated with a first processing model, the objects in the object set can be clustered and promotional content generated according to the input instructions of the first model and the first processing model corresponding to the specific region, so as to obtain a recommendation information corresponding to the specific region. Then, subsequent steps (such as step S2) are performed on the aforementioned recommendation information, thereby realizing the push processing of the specific region according to the recommendation information. Alternatively, multiple first model input instructions (the multiple first model input instructions are different from each other) can be determined, and the objects in the object set can be clustered and promotional content generated according to the multiple first model input instructions and the first processing model corresponding to the specific region, so as to obtain multiple clustering results and one or more recommendation information corresponding to them (the topic content in the multiple recommendation information corresponding to the clustering result of the same object is different), and subsequent steps (such as step S2) can be performed on at least some of the recommendation information, thereby realizing the push processing of the specific region according to one or more recommendation information corresponding to each object clustering result.

[0094] Optionally, in this embodiment, the number of push notifications obtained based on the same object set can be adjusted by adjusting the number of first processing models and / or the number of first model input instructions for each region. Thus, this embodiment can conveniently adjust the number of recommendation notifications corresponding to the same object set by adjusting the number of first processing models and / or the number of first model input instructions for each region. This allows for the generation of multiple differentiated recommendation notifications using different first processing models and / or different first model input instructions. These differentiated recommendation notifications can then be pushed to specific regions. This embodiment achieves better matching of the characteristics of specific regions and improves the click-through rate or view rate of objects in the object set after being pushed.

[0095] Optionally, after determining multiple regions with object push needs, the technical solution of this embodiment can generate different recommendation information for the same object set through multiple first processing models and first model input instructions corresponding to the voice and / or cultural customs of different regions (i.e., generating different recommendation information for the same object set with different first model input instructions and different first processing models), so as to obtain more object clustering results and topic content corresponding to each clustering result that is more in line with the cultural preferences and / or user preferences of multiple regions. After pushing multiple different recommendation information obtained in this way, the goal of improving the click conversion rate or view rate of objects in the object set after being pushed can be achieved.

[0096] Optionally, refer to Figure 5 The processing method in this embodiment also includes, but is not limited to, at least one of the following: S11: Perform content verification on the recommended information to obtain recommended information that has completed content verification; S22: In response to the completion of push processing, perform push effect analysis and / or model optimization.

[0097] Optionally, content verification processing can characterize any compliance verification of the recommended information or the patent content in the recommended information, to ensure that the recommended information can be pushed normally and / or to ensure that the topic content in the recommended information complies with the corresponding cultural customs and laws and regulations of the region.

[0098] Optionally, refer to Figure 6 The processing method in this embodiment (such as step S11: performing content verification processing on the recommendation information to obtain recommendation information with completed content verification) may include: step S102: performing content verification processing based on the topic content in the recommendation information and the second processing model to obtain recommendation information with completed content verification.

[0099] Optionally, the second processing model is used to verify the compliance of the topic content in the recommended information based on the legal and regulatory information and / or the prohibited word database corresponding to a specific region.

[0100] Optionally, the second processing model can be a pre-built dedicated model or a mature general-purpose model. Optionally, a mature general-purpose model is a large model such as OpenAI or DeepSeek that is designed for a wide range of users.

[0101] Optionally, the prohibited word list can represent a set of culturally advanced words and / or taboo words in a specific region.

[0102] Optionally, content validation processing includes, but is not limited to, at least one of the following: The second processing model is used to perform compliance verification on the topic content in the recommended information, and the verification results are output. When the verification results indicate that the topic content is compliant, the recommended information corresponding to the topic content is deemed to have completed content verification; or, when the verification results indicate that the topic content is compliant, a manual audit task is issued. When the verification results indicate that the content of a specific topic violates regulations, a manual audit task will be issued. When the audit result corresponding to the received manual audit task indicates that the audit has passed, it is determined that the recommended information corresponding to the topic content has been verified. When the audit results of a received manual audit task indicate that there is illegal content, the illegal content will be added to the prohibited word library or the illegal content already included in the prohibited word library will be given more weight by the model for identification.

[0103] Optionally, the technical solution of this embodiment can directly perform subsequent push processing based on the recommendation information when the second processing model verifies the compliance of the topic content in the recommendation information and determines that the topic content in the recommendation information is compliant; or, when the second processing model verifies the compliance of the topic content in the recommendation information and determines that the topic content in the recommendation information is compliant, a manual audit task can be issued for review to further ensure the compliance and / or accuracy of the topic content in the recommendation information. Subsequent push processing can be performed based on the manually reviewed recommendation information to ensure that the obtained push information is more compliant and reliable; or, when the second processing model verifies the compliance of the topic content in the recommendation information and determines that the topic content in the recommendation information is illegal, a manual audit task can be issued for review and / or correction. This can improve the efficiency of manual auditing and ensure the compliance and / or accuracy of the recommendation information used for push processing.

[0104] Optionally, when the verification result indicates that the topic content in the recommended information violates regulations, the violating content in the topic content of the recommended information can be marked, and then a manual audit task can be issued based on the marked topic content in the recommended information, which can improve the efficiency of completing the manual audit task.

[0105] Optionally, in the technical solution of this embodiment, when the audit result corresponding to the received manual audit task indicates that there is illegal content, the illegal content is added to the prohibited word library or the illegal content already included in the prohibited word library is given a higher weight for model recognition. This allows the prohibited word library to continuously learn and iterate, thereby making the second processing model more accurate in recognizing illegal content.

[0106] For example, taking the topic content as including a theme, promotional image information, and descriptive content as an example, the second processing module can perform compliance verification on the theme, promotional image information, and descriptive content to prevent situations where the promotional language does not comply with the legal or cultural restrictions of a specific region. When it is determined that any one of the theme, promotional image information, or descriptive content contains illegal content, the illegal content is marked to obtain the marked topic content. Based on the marked topic content, a manual audit task can be issued, which can improve the efficiency of completing the manual audit task. In addition, when the audit result corresponding to the received manual audit task indicates that there is illegal content, the illegal content is synchronized to the prohibited word library or the illegal content already included in the prohibited word library is weighted for model recognition, which can enable the prohibited word library to continuously learn and iterate.

[0107] Optionally, in this embodiment, the content verification process combines a second processing model with manual auditing, significantly improving the efficiency and accuracy of content verification. Specifically, this combination can quickly filter out non-compliant content, reduce the workload of initial manual screening, and speed up processing; through dual verification by the second processing model and manual auditing, the false judgment rate is reduced, ensuring content compliance; this combination makes the entire content verification process highly automated, reducing manual intervention and improving stability; at the same time, through standardized processes, the risks caused by content issues are reduced.

[0108] Optionally, refer to Figure 6 The processing method of this embodiment (such as step S12) may include: step S103: performing filtering processing based on the user behavior feature library, the third processing model and at least part of the recommendation information to obtain target recommendation information matching the target user, and / or performing push processing on the target recommendation information. Optionally, the user behavior feature database is used to support user behavior analysis and user profile construction, to help determine the habits or preferences of specific users or groups of people in operating objects pushed to their smart terminals. Thus, when the technical solution of this embodiment receives an object acquisition request (associated with or including the user's identifier) ​​sent by the smart terminal, the third processing model can call the user behavior feature database to determine the historical behavioral characteristics of the target user corresponding to the object acquisition request and determine its corresponding preference information. Based on the preference information, it can then filter at least one target recommendation from multiple recommendation information sources whose object clustering results match the aforementioned preference information, and send it to the aforementioned smart terminal to achieve personalized object or object list pushes. Specifically, by calling the user behavior feature database to determine at least one target recommendation matching the object acquisition request, the third processing model can increase the probability that the user corresponding to the object acquisition request clicks or operates on the displayed target recommendation information on the smart terminal, thereby effectively reaching the target user or target group with objects from the object set.

[0109] For example, taking an application as an example, the server initially selects 1000 applications to form an application set (i.e., an object set). A first processing model clusters the objects in the object set and generates promotional content to obtain 300 recommendation messages (300 application clustering results and corresponding topic content for each application clustering result). A third processing model, based on the application request corresponding to user A and the user behavior feature database, filters out 30 recommendation messages matching user A's preferences and sends these 30 recommendation messages to user A's mobile phone. User A's mobile phone or the app store on the phone displays the received recommendation messages. Optionally, the user behavior feature database can be a mature behavior-recommendation system. Optionally, a behavior-recommendation system is a system that predicts user interests and supports personalized recommendations based on user behavior data. Optionally, a mature behavior-recommendation system is, for example, the intelligent recommendation system based on user behavior data disclosed in patent CN119807546A. This system analyzes user behavior data on the platform, such as clicks, browsing, searching, and purchasing, generates user interest tags, and makes real-time recommendations based on this data to improve user experience and satisfaction.

[0110] Optionally, the third processing model is used to call the user behavior feature library and analyze the preference information of a specific user, and to filter out target recommendation information that matches the preference information from multiple recommendation information or to filter out target clustering results that match the preference information and their corresponding target recommendation information from the object clustering results corresponding to multiple recommendation information respectively.

[0111] Optionally, the third processing model can be a dedicated model. Optionally, the third processing model can be trimmed and optimized to obtain a dedicated model, which can significantly improve computational efficiency to ensure the response efficiency to object retrieval requests sent by smart terminals.

[0112] Optionally, when performing push processing, the technical solution of this implementation can not only send the recommendation information to smart terminals in specific regions, but also send the associated information of the aforementioned recommendation information to the smart terminals so that the smart terminals can perform data tracking, thereby facilitating the smart terminals to report the corresponding information based on the data tracking and realize the effect analysis on the server side.

[0113] Optionally, the associated information includes, but is not limited to, at least one of the following: model identifiers of each model corresponding to the recommendation information (such as the model identifier of the first processing model, the model identifier of the second processing model, the model identifier of the third processing model, etc.) and instruction identifiers of the model input instructions corresponding to the recommendation information.

[0114] Optionally, after receiving and displaying the recommendation information, the smart terminal reports the first information based on the tracking data and associated information; and / or, after obtaining and displaying the recommendation information, and after obtaining the click time for the recommendation information, the smart terminal reports the second information based on the tracking data and associated information. Optionally, the first and second reporting information can support effect analysis on the server side.

[0115] Optionally, the push effect analysis and processing can characterize the evaluation of the conversion effect of the recommended information and the analysis of at least one dimension based on the reported information received after the push processing is completed, quantifying the specific process or rules of the conversion effect of the recommended information. Optionally, at least one dimension includes, but is not limited to, factors affecting the implementation effect such as push region, model, and model input instructions corresponding to the model.

[0116] Optionally, model optimization processing can characterize the specific process or rules for performance evaluation and / or optimization adjustment of the model and model input instructions corresponding to the recommendation information based on the push effect analysis and / or the audit results of the manual audit task.

[0117] The technical solution of this embodiment performs push effect analysis after push processing to achieve a closed loop of content push and push effect evaluation; in addition, push effect analysis and model optimization are performed after push processing to maintain and optimize at least some of the multiple models based on the analysis results.

[0118] Optionally, step S22: In response to the completion of push processing, perform push effect analysis and / or model optimization processing, including at least one of the following: In response to the completion of push processing, listen for the reported information fed back after the smart terminal displays the recommended information; The effectiveness of the push notifications is analyzed based on the reported information received, in order to obtain information on the effectiveness of the push notifications from at least one dimension. Based on the push effect information, the model and / or model input instructions corresponding to the recommendation information are subjected to performance evaluation and / or optimization processing.

[0119] Optionally, effect analysis can be performed based on the monitored reported information to obtain push effect information in at least one dimension, which can be achieved through a pre-built effect analysis model (i.e., a dedicated model).

[0120] Optionally, in the technical solution of this embodiment, in response to completing the push processing, the system listens to the reported information fed back after the smart terminal displays the recommended information, and performs effect analysis based on the listened reported information to obtain push effect information in at least one dimension. Thus, the technical solution of this embodiment can analyze the conversion rate corresponding to the recommended information by analyzing the reported information, and / or, based on the associated information corresponding to the reported information (such as the model identifier of each model corresponding to the recommended information, the instruction identifier of each model input instruction corresponding to the recommended information, the push region, etc.), it can deeply explore the impact on the conversion rate from dimensions such as region, model, and model input instructions.

[0121] Optionally, obtaining push effect information from multiple dimensions can effectively ensure the completeness of the analysis.

[0122] For example, when displaying recommended information on a smart terminal, pre-set tracking points are used to collect behavioral data such as display and clicks, and the data is fed back to the server, including recommended information, model identifier, instruction identifier, and push region. After receiving the reported information, the server can perform multi-dimensional statistical analysis and calculate key indicators such as conversion rate.

[0123] Optionally, the performance evaluation process includes: performing model performance evaluation on the model corresponding to the recommendation information and / or the model input instructions based on the fourth processing model and the push effect information, so as to determine the execution effect information of the model corresponding to the recommendation information and / or the execution effect information of the model input instructions corresponding to the recommendation information.

[0124] Optionally, the fourth processing model can quantify or evaluate the performance of the model and / or model input instructions corresponding to the recommendation information (i.e., execution effect information) based on the push effect information, and / or output key performance indicators of the model and / or model input instructions corresponding to the recommendation information. Optionally, key performance indicators include, but are not limited to, execution efficiency, the contribution of the recommendation information to the conversion rate, etc.

[0125] Optionally, the aforementioned key performance indicators can pinpoint problems with the model and / or model input instructions corresponding to the recommendation information, so as to optimize the model and / or model input instructions based on the identified problems. Optionally, the optimization process can be to issue an optimization task to trigger manual optimization of the model and / or model input instructions corresponding to the recommendation information, or to automatically optimize the model and / or model input instructions corresponding to the recommendation information through mechanized or procedural methods.

[0126] The processing method provided in this embodiment may include the following steps: S101: Based on the characteristic information corresponding to the objects in the object set and at least one first processing model, perform thematic clustering processing on the objects in the object set to obtain recommendation information corresponding to at least one region; S102: Perform content verification processing based on the thematic content in the recommendation information and the second processing model to obtain recommendation information that has completed content verification; S103: Perform filtering processing based on the user behavior feature library, the third processing model and at least part of the recommendation information to obtain target recommendation information that matches the target user, and / or perform push processing on the target recommendation information; S22: In response to the completion of the push processing, perform push effect analysis processing and / or model optimization processing. Through the technical solution of this embodiment, one or more first processing models can be used to perform thematic clustering processing based on the characteristic information of objects in the object set, which can generate recommendation information (including object clustering results and thematic content) corresponding to one or more regions respectively. The thematic content (at least one of theme, promotional image information, and descriptive content) in each recommendation information can match the language and / or cultural customs of the corresponding region. Furthermore, the thematic content in the recommendation information can be processed by a second processing model to efficiently obtain the recommendation information that has completed content verification. Therefore, the technical solution of this embodiment can process the object set through multiple models to obtain recommendation information that accurately matches the language and / or cultural customs of the corresponding region, reducing or avoiding manual intervention in the formulation of recommendation information for each region for the object set, effectively improving the generation efficiency of recommendation information, thereby improving the push efficiency of the corresponding content. Moreover, after the push processing is completed, push effect analysis processing and / or model optimization processing can be performed. Therefore, the technical solution of this embodiment can realize a closed loop of push information push and push effect evaluation, and / or can realize the maintenance and optimization of at least some of the multiple models based on the analysis results. Thus, the technical solution of this embodiment improves the push efficiency of the regional object push process and forms a closed-loop workflow for the object push process. Furthermore, it can continuously optimize the object push process by optimizing the model based on the push effect analysis results.

[0127] Through the technical solution of this embodiment, the collaborative processing of the first processing model, the second processing model, and the third processing model can optimize the push effect of object clustering results and improve the overall efficiency of the object push process. Furthermore, the technical solution of this embodiment has the ability to generate more recommendation information conveniently and quickly. In addition, the technical solution of this embodiment can automatically generate push effect information and draw optimization analysis conclusions based on the push effect information, thereby enabling rapid and continuous optimization of the model and model input instructions used for generating recommendation information.

[0128] The technical solution of this embodiment can generate different recommendation information (different object clustering results, themes, promotional image information, descriptive content, etc.) for the same object set by multiple first model input instructions corresponding to different regional languages ​​and / or cultural customs and multiple first processing models. It can well balance the generation effect and cost, and the generated recommendation information can better match the cultural customs of different regions. Furthermore, the generated recommendation information can be filtered by a third processing model to obtain target recommendation information that matches the preferences of specific users or users and then push it, which can realize automated push of personalized recommendation information, thereby improving the conversion rate of push information. In addition, after the push processing is completed, the first model input instructions corresponding to the recommendation information can be quickly iterated by push effect analysis and / or model optimization, and the model parameters of the first processing model corresponding to the recommendation information can be optimized or the selection priority of each first processing model can be adjusted (for example, when processing a new object set, the first processing model with higher priority is selected first).

[0129] The technical solution in this embodiment can utilize a dedicated model to statistically analyze data from multiple dimensions, obtaining multi-dimensional push effect information, effectively ensuring the completeness and real-time nature of the analysis. Furthermore, by employing a performance evaluation model, it can analyze various model input commands and model effects in real time, enabling rapid iteration of the content push process.

[0130] Third Embodiment Based on the two embodiments described above, a third embodiment of this application is proposed. (Refer to...) Figure 7 , Figure 7 This is a schematic diagram of the processing system according to the third embodiment. The processing system of this embodiment can be configured on a server to push recommendation information containing a list of applications to a smart terminal or other applications installed on the smart terminal. The processing system of this embodiment includes: a list item generation module, a content verification module, a recommendation list filtering module, and an effect statistics module.

[0131] The list item generation module is used to perform thematic clustering processing on the applications in the application set based on the characteristic information corresponding to the applications in the application set and at least one first processing model, so as to obtain recommendation list information corresponding to at least one region.

[0132] Optionally, the characteristic information corresponding to the application (or APP) includes screenshot style, APP type, icon style, APP description, data package size, business association information (whether there is a strong business relationship between PPT, Excel, and Office), etc.

[0133] Optionally, the applications in the application collection can be pre-selected or uploaded.

[0134] Optionally, the recommendation list information (i.e., the aforementioned recommendation information) includes an application recommendation list (i.e., object clustering results) and its corresponding topic content. The topic content includes at least one of the following: theme, promotional image, and descriptive content.

[0135] Optionally, the first processing model can cluster the applications in the application set by combining the first model input instruction prompt, so as to obtain an application recommendation list based on the N applications obtained from the clustering.

[0136] Optionally, to ensure clustering effectiveness, this system can employ either a single first processing model plus multiple first model input prompts or multiple first processing models plus multiple first model input prompts to perform various clustering methods, thereby generating multiple application recommendation lists. After each application recommendation list is generated, the first processing model or the promotional content generation model (i.e., sub-model) included in the first processing model will generate promotional content based on the application recommendation list, obtaining at least one of the following three elements: theme, promotional image, and descriptive content, thus acquiring the recommendation list information.

[0137] Optionally, each of the multiple first processing models is subjected to different optimization processes.

[0138] Optionally, this system can generate multiple recommendation lists for the same application set using the same first processing model and multiple first model input prompts, or multiple first processing models and multiple first model input prompts. Optionally, generating multiple recommendation lists using the same first processing model and multiple first model input prompts can balance model efficiency and cost, and iterative optimization of clustering can be achieved by changing the first model input prompts. The first model input prompts are typically generated by operations personnel, and multiple first model input prompts can be tagged in a single operational activity. When deployed to the first clustering model, the first model input prompt with the best convergence test results can be selected.

[0139] Optionally, when the first processing model includes multiple sub-models, the first model input instructions may include multiple sub-input instructions that cooperate with each sub-model.

[0140] The content verification module is used to perform content verification based on the topic content in the recommendation list information and the second processing model in order to obtain the recommendation list information after content verification.

[0141] Optionally, content verification processing is used to prevent any element in the recommended list information, such as the theme, promotional image, or description, from violating the legal or cultural restrictions on promotional language or prohibited words in a specific region.

[0142] Optionally, the second processing model uses MCP to call the corresponding legal and regulatory information and / or prohibited word database for a specific region to perform preliminary content verification. Based on the legal and regulatory information and / or prohibited word database, it determines whether the material content is compliant. Non-compliant content is marked. After being marked by the second processing model, it is then manually audited. The results of the manual audit will be synchronized to the legal and regulatory information and / or prohibited word database, supporting the iteration of the legal and regulatory information and / or prohibited word database.

[0143] The recommendation list filtering module is used to filter based on the user behavior feature library, the third processing model and at least part of the recommendation list information, to obtain the target recommendation list information that matches the target user, and / or to push the target recommendation list information.

[0144] Optionally, the recommendation list filtering module is used to filter target recommendation list information that matches the user's behavioral preferences from multiple recommendation list information based on the user's application usage behavior on the smart terminal (such as a mobile phone), and then send it to the smart terminal. Optionally, when a target user requests data, the third processing model calls the behavior-recommendation system through MCP to obtain the target user's preference information and / or current usage behavior information, and then filters at least one target recommendation list information that matches it from multiple recommendation list information, and sends the target recommendation list information to the target user's smart terminal, thereby realizing personalized recommendation list information push.

[0145] The effect statistics module is used to perform push effect analysis and / or model optimization in response to the completion of push processing.

[0146] Optionally, the performance statistics module can use a dedicated AI model to support push performance analysis and / or model optimization.

[0147] Optionally, the performance statistics module can analyze the conversion rate and generation effect of content push from different dimensions, including region / country, and the corresponding model ID and prompt ID on the link. The performance statistics module can call the AI-dedicated model for performance evaluation to obtain the matching execution efficiency of the model corresponding to the model ID and the prompt corresponding to the prompt ID on the link, thereby quickly locating the problems of the model and prompt, and providing support for model optimization and prompt iteration.

[0148] The aforementioned processing system can improve the efficiency of the application list push process and form a closed-loop workflow. Its main workflow is as follows: Select / upload applications to obtain an application set, call the first processing model to perform clustering, cluster the applications according to the application screenshot style, APP type, icon style, data package size, and business association information in the application set, and aggregate them into multiple application groups (i.e., the aforementioned object clustering combination or application recommendation list). Clustering is completed by multiple first sub-input prompts + the clustering model in the first processing model. For the clustered application groups, multiple second-word input instructions (prompt) are invoked, along with the promotional content generation model in the first processing model. Based on the application names and descriptions, icon styles, and application screenshot styles in the application groups, different promotional images and / or themes are generated for different languages ​​in different regions. Thus, recommendation list information is obtained based on each application group and its corresponding promotional images and / or themes. The generated promotional images and / or themes are verified using a second processing model to ensure compliance. After verification by the second processing model, they are then manually verified to improve manual efficiency. This process continuously accumulates the model input prompts, verification rules, and the second processing model itself (such as a dedicated large model) used for verification. The third processing model is invoked to filter the obtained recommendation list information, so as to achieve personalized recommendation list information push based on user behavior type. Specifically: The third processing model calls the recommendation list effect statistics system and the behavior-recommendation system through MCP to extract reference base data (user behavior of installing, using, and searching applications on mobile phones) of the target user's preference information; among them, the recommendation list effect statistics system can represent the system that stores the association information of user operation records with the displayed recommendation list information; When a target user requests data from the server via a smart terminal, the third processing model can obtain the target user's preference information based on region and behavioral characteristics and filter out the corresponding target recommendation list information. When the third processing model can obtain the target user's preference information and the corresponding target recommendation list information, it can directly cache and / or send it to the smart terminal. When the third processing model cannot obtain the target user's preference information and the corresponding target recommendation list information, it can use the recommendation list information with the best push effect in the current region as the target recommendation list information and send it to the smart terminal to ensure push effect and response efficiency. The smart terminal uses Athena to upload information about applications in the recommended list, including exposure, clicks, downloads, and installations. It calls a dedicated model to evaluate the effectiveness of the model input instructions prompt, model, promotional images, application groups, themes, etc., corresponding to the recommended list information, and then generates a push report.

[0149] Some implementations of the recommendation list push process are lengthy, requiring significant manpower to generate information such as application groups, themes, promotional images, and descriptions. Furthermore, some implementations lack performance statistics after the recommendation list push process is completed, or require manual performance analysis. For example, some implementations' recommendation list push processes involve: (1) operations personnel selecting applications from a product selection manual and submitting design requirements; (2) designers creating promotional images, design themes, and descriptions based on these requirements; (3) operations personnel processing the selected applications and the promotional images, themes, and descriptions designed by the designers to obtain the push list information and push it out; and (4) operations personnel then performing performance analysis. Thus, some implementations of the recommendation list push process are constrained by manpower and become inefficient when dealing with different languages ​​and cultures in multiple countries and regions.

[0150] To address the aforementioned shortcomings, this example's processing system includes the aforementioned list item generation module, content verification module, recommendation list filtering module, and performance statistics module. The entire system employs multiple AI models working together to form a closed-loop recommendation list push process, reducing manpower investment and significantly improving the scale and efficiency of recommendation list information generation, push, and performance statistics. Furthermore, the list item generation module in this example uses a multi-model + multi-model input instruction prompt approach, enhancing the scale and efficiency of recommendation list information generation. During push processing, the system can send model IDs and model input instruction IDs to the smart terminal and receive reports from the smart terminal after exposure and click events, including model IDs and model input instruction IDs. Based on these reports, the system evaluates the conversion efficiency of different models and model input instructions, supporting subsequent model tuning and model input instruction optimization. This example's processing system, employing multiple AI models working together to form a closed-loop recommendation list push process, enables real-time statistics on model input instructions and model performance, allowing for rapid iterative operation.

[0151] This application also provides a processing system, including a smart terminal and a server; the server is used to execute the steps of the processing method described in any of the above embodiments; the smart terminal is used to respond to the server in pushing recommendation information corresponding to a region and display the received recommendation information.

[0152] This application also provides a computing device (such as a server) including a memory and a processor. The memory stores a processing program, and when the processing program is executed by the processor, it implements the steps of the processing method in any of the above embodiments.

[0153] This application also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the processing method in any of the above embodiments.

[0154] In the embodiments of the smart terminal and storage medium provided in this application, all the technical features of any of the above-described processing method embodiments may be included. The extended and explained contents of the specification are basically the same as the embodiments of the above methods, and will not be repeated here.

[0155] This application also provides a computer program product, which includes computer program code. When the computer program code is run on a computer, it causes the computer to perform the methods described in the various possible implementations above.

[0156] This application also provides a chip, including a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that a device with the chip installed performs the methods described in the various possible implementations above.

[0157] It is understood that the above scenarios are merely examples and do not constitute a limitation on the application scenarios of the technical solutions provided in the embodiments of this application. The technical solutions of this application can also be applied to other scenarios. For example, as those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0158] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0159] The steps in the method of this application embodiment can be adjusted, combined, or deleted according to actual needs.

[0160] The units in the device of this application embodiment can be merged, divided, and deleted according to actual needs.

[0161] In this application, the same or similar terms, concepts, technical solutions and / or application scenario descriptions are generally described in detail only when they appear for the first time. When they appear again, they are generally not repeated for the sake of brevity. When understanding the technical solutions and other contents of this application, the same or similar terms, concepts, technical solutions and / or application scenario descriptions that are not described in detail later can be referred to their previous relevant detailed descriptions.

[0162] In this application, the descriptions of the various embodiments have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0163] The technical features of the present application can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the present application.

[0164] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, controlled terminal, or network device, etc.) to execute the methods of each embodiment of this application.

[0165] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a storage medium or transmitted from one storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, storage disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)).

[0166] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A processing method, characterized in that, Including the following steps: S1: Generate recommendation information corresponding to the region based on the objects in the object set; S2: Push the recommended information corresponding to the region.

2. The processing method as described in claim 1, characterized in that, Step S1 includes at least one of the following: Identify one or more regions where the target audience needs to be pushed to. Determine one or more primary processing models; Obtain one or more first model input instructions; Based on the first model input instruction, the first processing model, and the region, the objects in the object set are subjected to thematic clustering to obtain recommendation information corresponding to each region. The recommendation information includes object clustering results and topic content; The topic content includes at least one of the following: theme, promotional image information, and descriptive content.

3. The processing method as described in claim 1, characterized in that, It also includes at least one of the following: The recommended information is subjected to content verification processing to obtain the recommended information after content verification is completed; In response to the completion of push notification processing, perform push notification effect analysis and / or model optimization.

4. The processing method as described in claim 3, characterized in that, Includes at least one of the following: Content verification is performed based on the topic content in the recommendation information and the second processing model to obtain the recommendation information after content verification. The system performs filtering based on the user behavior feature database, the third processing model, and at least a portion of the recommended information to obtain target recommended information that matches the target user, and / or pushes the target recommended information.

5. The processing method as described in claim 4, characterized in that, The second processing model is used to perform compliance verification on the topic content in the recommended information based on the legal and regulatory information and / or prohibited word database corresponding to a specific region.

6. The processing method as described in claim 5, characterized in that, The content verification process includes at least one of the following: The second processing model is used to perform compliance verification on the topic content in the recommended information, and the verification results are output. When the verification result indicates that the topic content is compliant, the recommended information corresponding to the topic content is determined to have completed content verification; or, when the verification result indicates that the topic content is compliant, a manual audit task is issued. When the verification result indicates that the content of the topic violates the rules, a manual audit task is issued. When the audit result corresponding to the received manual audit task indicates that the audit has passed, it is determined that the recommendation information corresponding to the topic content has been verified. When the audit result corresponding to the received manual audit task indicates that there is illegal content, the illegal content is added to the prohibited word library or the illegal content already included in the prohibited word library is given a higher weight for model recognition.

7. The processing method as described in claim 3, characterized in that, In response to the completion of push notification processing, perform push notification performance analysis and / or model optimization, including at least one of the following: In response to the completion of push processing, listen for the reported information fed back by the smart terminal after the recommended information is displayed; Based on the reported information that has been monitored, an effect analysis is performed to obtain push effect information from at least one dimension; Based on the push effect information, the model and / or model input instructions corresponding to the recommendation information are subjected to performance evaluation and / or optimization processing.

8. The processing method as described in claim 7, characterized in that, The performance evaluation process includes: Based on the fourth processing model and the push effect information, the model corresponding to the recommendation information and / or the model input instruction are evaluated to determine the execution effect information of the model corresponding to the recommendation information and / or the execution effect information of the model input instruction corresponding to the recommendation information.

9. A computing device, characterized in that, include: A memory and a processor, wherein the memory stores a processing program, and the processing program, when executed by the processor, implements the steps of the processing method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the processing method as described in any one of claims 1 to 7.

Images