CN110730236A

CN110730236A - Business pushing method and device based on artificial intelligence and electronic equipment

Info

Publication number: CN110730236A
Application number: CN201910991416.7A
Authority: CN
Inventors: 李国柱; 刘金林; 陈帅; 赖凌华; 袁宜霞; 龚健飞; 纪琳琳; 钟文涛; 刘智君; 陈炎福; 徐雄威
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2019-10-18
Filing date: 2019-10-18
Publication date: 2020-01-24
Anticipated expiration: 2039-10-18
Also published as: CN110730236B

Abstract

The invention provides a service pushing method and device based on artificial intelligence, electronic equipment and a storage medium; the method comprises the following steps: responding to a trigger operation of a client scene, and acquiring a scene identifier corresponding to the client scene; acquiring an equipment identifier of a client, and determining a rule platform corresponding to the equipment identifier; determining a plurality of services corresponding to the scene identification in the rule platform; determining the style identification and the service content of each service according to the push configuration; determining the service weight of each service, and determining the pushing time of each service according to the service weight; and when the pushing opportunity is met, pushing the service to the client according to the style identification and the service content of the service corresponding to the pushing opportunity. The invention can ensure that the pushing processes of a plurality of services do not conflict with each other, and improve the ordering and rationality of service pushing.

Description

Business pushing method and device based on artificial intelligence and electronic equipment

Technical Field

The invention relates to artificial intelligence and cloud technology, in particular to a service pushing method and device based on artificial intelligence, electronic equipment and a storage medium.

Background

Artificial Intelligence (AI) is a theory, method and technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human Intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence.

The service push is an application direction of artificial intelligence, and specifically researches on pushing services to a client to prompt a user to click so as to achieve popularization or other purposes, wherein the services to be pushed generally include various types, such as information services and services for achieving specific functions (such as a function of connecting a wireless network). In the related art, services pushed to the client are often developed according to types, which causes mutual conflict during pushing, and the reasonability and effect of pushing services are poor.

Disclosure of Invention

The embodiment of the invention provides a service pushing method and device based on artificial intelligence, electronic equipment and a storage medium, which can improve the reasonability and the pushing effect of a pushing service.

The technical scheme of the embodiment of the invention is realized as follows:

the embodiment of the invention provides a service pushing method based on artificial intelligence, which comprises the following steps:

responding to a trigger operation of a client scene, and acquiring a scene identifier corresponding to the client scene;

acquiring an equipment identifier of a client, and determining a rule platform corresponding to the equipment identifier;

determining a plurality of services corresponding to the scene identification in the rule platform;

determining the style identification and the service content of each service according to the push configuration;

determining the service weight of each service, and determining the pushing time of each service according to the service weight;

and when the pushing opportunity is met, pushing the service to the client according to the style identification and the service content of the service corresponding to the pushing opportunity.

The embodiment of the invention provides a service pushing device based on artificial intelligence, which comprises:

the identification acquisition module is used for responding to the triggering operation of the client scene and acquiring a scene identification corresponding to the client scene;

the platform determination module is used for acquiring the equipment identifier of the client and determining a rule platform corresponding to the equipment identifier;

a service determining module, configured to determine multiple services corresponding to the scene identifier in the rule platform;

the content determining module is used for determining the style identification and the service content of each service according to the push configuration;

the timing determining module is used for determining the service weight of each service and determining the pushing timing of each service according to the service weight;

and the pushing module is used for pushing the service to the client according to the style identification and the service content of the service corresponding to the pushing opportunity when the pushing opportunity is met.

An embodiment of the present invention provides an electronic device, including:

a memory for storing executable instructions;

and the processor is used for realizing the artificial intelligence based service pushing method provided by the embodiment of the invention when the executable instruction stored in the memory is executed.

The embodiment of the invention provides a storage medium, which stores executable instructions and is used for causing a processor to execute so as to realize the artificial intelligence based service pushing method provided by the embodiment of the invention.

The embodiment of the invention has the following beneficial effects:

the embodiment of the invention determines the rule platform according to the equipment identifier of the client, determines a plurality of services corresponding to the triggered scene identifier in the rule platform, determines the pushing time according to the service weight of each service, and pushes the service according to the pushing configuration of the corresponding service when the pushing time is met, thereby ensuring that the pushing of different services is not conflicted with each other, and improving the orderliness and rationality of the pushing service.

Drawings

Fig. 1 is an alternative architecture diagram of a service push system based on artificial intelligence provided by an embodiment of the present invention;

FIG. 2 is an alternative architecture diagram of a server provided by an embodiment of the invention;

fig. 3A is an alternative flowchart of a service pushing method based on artificial intelligence according to an embodiment of the present invention;

fig. 3B is a schematic flow chart of another alternative artificial intelligence based service pushing method according to an embodiment of the present invention;

FIG. 3C is a schematic diagram of an alternative process for determining an optimal configuration from at least two types of configurations under test according to an embodiment of the present invention;

FIG. 4 is an alternative diagram of a client scenario and service provided by an embodiment of the present invention;

fig. 5 is a schematic flow chart of another alternative artificial intelligence based service pushing method according to an embodiment of the present invention;

FIG. 6 is an alternative flow diagram of data monitoring provided by embodiments of the present invention;

FIG. 7 is an alternative architecture diagram of a middlebox provided by an embodiment of the present invention;

fig. 8 is an alternative schematic diagram of monitored business push data according to an embodiment of the present invention;

FIG. 9 is an alternative diagram of the style privilege ratio provided by an embodiment of the present invention;

FIG. 10 is a schematic diagram of an alternative strategy for increasing the service presentation rate according to an embodiment of the present invention;

FIG. 11 is an alternative configuration diagram of a push configuration provided by embodiments of the present invention;

fig. 12 is a schematic diagram of an alternative configuration of a service push condition provided by an embodiment of the present invention;

fig. 13 is a schematic diagram of an alternative configuration of the service weight provided by the embodiment of the present invention;

FIG. 14 is a schematic diagram of an alternative configuration of a gray scale test provided by an embodiment of the present invention;

FIG. 15 is a schematic diagram of an alternative configuration of a comparative test provided by an embodiment of the present invention;

FIG. 16 is a schematic diagram of an alternative configuration of a comparative test provided by an embodiment of the present invention;

fig. 17 is an alternative diagram of the push effect provided by the embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail with reference to the accompanying drawings, the described embodiments should not be construed as limiting the present invention, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

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

In the description that follows, references to the terms "first", "second", and the like, are intended only to distinguish similar objects and not to indicate a particular ordering for the objects, it being understood that "first", "second", and the like may be interchanged under certain circumstances or sequences of events to enable embodiments of the invention described herein to be practiced in other than the order illustrated or described herein.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to be limiting of the invention.

Before further detailed description of the embodiments of the present invention, terms and expressions mentioned in the embodiments of the present invention are explained, and the terms and expressions mentioned in the embodiments of the present invention are applied to the following explanations.

1) Client side scenario: the scene related to the client and used for triggering service push can be preset according to an actual application scene, for example, a scene that WiFi is available in the client, a scene that WiFi is successfully connected, or a scene that the time of the client reaches a set time.

2) A rule platform: and the rule platform can be deployed at the cloud.

3) Equipment identification: a unique Identity indicating the Identity of the client, such as an International Mobile Equipment Identity (IMEI).

4) Machine learning: the special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. Machine learning is the core of artificial intelligence, is the fundamental approach for computers to have intelligence, and is applied to all fields of artificial intelligence.

Embodiments of the present invention provide a service pushing method and apparatus, an electronic device, and a storage medium based on artificial intelligence, which can improve the rationality and pushing effect of a pushed service, and an exemplary application of the electronic device provided in the embodiments of the present invention is described below.

The embodiment of the invention can be realized by combining a Cloud technology, wherein the Cloud technology is a hosting technology for unifying series resources such as hardware, software and a network in a wide area network or a local area network to realize the calculation, storage, processing and sharing of data, and can also be understood as a general term of a network technology, an information technology, an integration technology, a management platform technology, an application technology and the like based on Cloud computing business model application. Background services of the technical network system require a large amount of computing and storage resources, such as video websites, photo-like websites and more portal websites, so cloud technology needs to be supported by cloud computing. Cloud computing is a computing model that distributes computing tasks over a resource pool of large numbers of computers, enabling various application systems to obtain computing power, storage space, and information services as needed. The network that provides the resources is referred to as the "cloud". Resources in the "cloud" appear to the user as being infinitely expandable and available at any time, available on demand, expandable at any time, and paid for on-demand. As a basic capability provider of cloud computing, a cloud computing resource pool platform, which is called an Infrastructure as a Service (IaaS) for short, is established, and multiple types of virtual resources are deployed in a resource pool and are used by external clients selectively. The cloud computing resource pool mainly comprises: a computing device (which may be a virtualized machine, including an operating system), a storage device, and a network device.

Referring to fig. 1, fig. 1 is an optional architecture diagram of an artificial intelligence based service push system 100 according to an embodiment of the present invention, in order to support an artificial intelligence based service push application, a terminal device 400 (an exemplary terminal device 400-1 and a terminal device 400-2 are shown) is connected to a server 200 located in a cloud end through a network 300, where the network 300 may be a wide area network or a local area network, or a combination of the two. It should be noted that the server 200 may be a physical device or a virtualized device.

The terminal device 400 is configured to determine a scene identifier corresponding to a client scene in response to a trigger operation of a user on the client scene, and send the device identifier and the scene identifier to the server 200; the server 200 is configured to obtain a device identifier and a scene identifier sent by the terminal device 400, and determine a rule platform corresponding to the device identifier; determining a plurality of services corresponding to the scene identifiers in the rule platform; determining the style identification and the service content of each service according to the push configuration; determining the service weight of each service, and determining the push opportunity of each service according to the service weight; when the push opportunity is met, pushing the service to the terminal device 400 according to the style identification and the service content of the service corresponding to the push opportunity; the terminal 400 device is further configured to present the service content according to the style identification. For example, business content 1, business content 2, and business content 3 are shown in graphical interface 410 of FIG. 1 (which illustratively shows graphical interface 410-1 and graphical interface 410-2).

The following continues to illustrate exemplary applications of the electronic device provided by embodiments of the present invention. The electronic device may be implemented as various types of terminal devices such as a notebook computer, a tablet computer, a desktop computer, a set-top box, a mobile device (e.g., a mobile phone, a portable music player, a personal digital assistant, a dedicated messaging device, a portable game device), and the like, and may also be implemented as a server. Next, an electronic device will be described as an example of a server.

Referring to fig. 2, fig. 2 is a schematic diagram of an architecture of a server 200 (for example, the server 200 shown in fig. 1) provided by an embodiment of the present invention, where the server 200 shown in fig. 2 includes: at least one processor 210, memory 250, at least one network interface 220, and a user interface 230. The various components in server 200 are coupled together by a bus system 240. It is understood that the bus system 240 is used to enable communications among the components. The bus system 240 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 240 in fig. 2.

The Processor 210 may be an integrated circuit chip having Signal processing capabilities, such as a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like, wherein the general purpose Processor may be a microprocessor or any conventional Processor, or the like.

The user interface 230 includes one or more output devices 231, including one or more speakers and/or one or more visual display screens, that enable the presentation of media content. The user interface 230 also includes one or more input devices 232, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

The memory 250 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid state memory, hard disk drives, optical disk drives, and the like. Memory 250 optionally includes one or more storage devices physically located remotely from processor 210.

The memory 250 includes volatile memory or nonvolatile memory, and may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read Only Memory (ROM), and the volatile Memory may be a Random Access Memory (RAM). The memory 250 described in embodiments of the invention is intended to comprise any suitable type of memory.

In some embodiments, memory 250 is capable of storing data, examples of which include programs, modules, and data structures, or a subset or superset thereof, to support various operations, as exemplified below.

An operating system 251 including system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks;

a network communication module 252 for communicating to other computing devices via one or more (wired or wireless) network interfaces 220, exemplary network interfaces 220 including: bluetooth, wireless compatibility authentication (WiFi), and Universal Serial Bus (USB), etc.;

a presentation module 253 to enable presentation of information (e.g., a user interface for operating peripherals and displaying content and information) via one or more output devices 231 (e.g., a display screen, speakers, etc.) associated with the user interface 230;

an input processing module 254 for detecting one or more user inputs or interactions from one of the one or more input devices 232 and translating the detected inputs or interactions.

In some embodiments, the artificial intelligence based service pushing apparatus provided by the embodiments of the present invention may be implemented in software, and fig. 2 illustrates an artificial intelligence based service pushing apparatus 255 stored in a storage 250, which may be software in the form of programs and plug-ins, and includes the following software modules: the identifier obtaining module 2551, the platform determining module 2552, the service determining module 2553, the content determining module 2554, the opportunity determining module 2555 and the pushing module 2556 are logical, and thus any combination or further splitting can be performed according to the implemented functions.

The functions of the respective modules will be explained below.

In other embodiments, the service pushing apparatus based on artificial intelligence provided by the embodiments of the present invention may be implemented in hardware, and as an example, the service pushing apparatus based on artificial intelligence provided by the embodiments of the present invention may be a processor in the form of a hardware decoding processor, which is programmed to execute the service pushing method based on artificial intelligence provided by the embodiments of the present invention, for example, the processor in the form of the hardware decoding processor may employ one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs), Field Programmable Gate Arrays (FPGAs), or other electronic components.

The service push method based on artificial intelligence provided by the embodiment of the present invention may be executed by the server, or may be executed by a terminal device (for example, the terminal device 400-1 and the terminal device 400-2 shown in fig. 1), or may be executed by both the server and the terminal device.

In the following, a process of implementing the artificial intelligence based service push method by an embedded artificial intelligence based service push apparatus in an electronic device will be described in conjunction with the exemplary application and structure of the electronic device described above.

Referring to fig. 3A, fig. 3A is an optional flowchart of the artificial intelligence based service pushing method according to the embodiment of the present invention, which is described with reference to the steps shown in fig. 3A by taking a client and a server 200 (hereinafter, referred to as a server) operated by the terminal device 400 shown in fig. 1 as an example.

In step 101, in response to a trigger operation on a client scene, a client determines a scene identifier corresponding to the client scene, and sends the scene identifier to a server.

Here, when a client scene is triggered, a client determines a scene identifier corresponding to the client scene, and sends the scene identifier to a server located in the cloud, where the triggering operation of the client scene may be triggered by a user, for example, the user turns on a WiFi switch in the client to enable the client to be in a client scene with WiFi connectivity; the triggering may also be automatic, for example, when the current time of the client reaches a set time, the corresponding client scenario is triggered. The scene identification is a digital identification, the mapping relation between the client scene and the scene identification can be preset, and the scene identifications corresponding to different client scenes are different. For example, a scene identifier corresponding to a client scene where WiFi is connectable is preset to be 1, and a scene identifier corresponding to a client scene where the current time reaches a set time is preset to be 2.

In step 102, the client sends a device identification to the server.

Here, the client reads the device identifier, such as the IMEI of the terminal device, and sends the device identifier to the server in the cloud.

In step 103, the server determines a rule platform corresponding to the device identifier.

The server is accessed to at least one rule platform, the rule platform stores the mapping relation of 'equipment identification-scene identification-service', and when the server acquires the scene identification and the equipment identification sent by the client, the server firstly determines the rule platform corresponding to the equipment identification.

In step 104, the server determines a plurality of services corresponding to the scene identification in the rule platform.

For the determined rule platform, the server further determines a plurality of services corresponding to the scene identifiers in the rule platform, and the determined services are services to be pushed. For example, it is preset that the mapping relationship stored in the rule platform 1 is "(device identifier 1, 2) - (scene identifier 1) - (WiFi speed measurement service, WiFi acceleration service, and credit acquisition service)", and the mapping relationship stored in the rule platform 2 is "(device identifier 3) - (scene identifier 2) - (information recommendation service, game gift service, and welfare activity service)", and when the scene identifier sent by the client is 1 and the device identifier is 1, it is first determined that the corresponding rule platform is 1, and then the service to be pushed is further determined according to the scene identifier, specifically including WiFi speed measurement service, WiFi acceleration service, and credit acquisition service.

In step 105, the server determines the style identifier and the service content of each service according to the push configuration.

The server stores preset push configuration, and the push configuration comprises style identification and service content of each service. After determining the services to be pushed in the rule platform, the server determines the style identification and the service content of each service to be pushed according to the pushing configuration so as to facilitate the subsequent pushing.

In step 106, the server determines a service weight of each service, and determines a push timing of each service according to the service weight.

Here, the server determines a service weight of each service to be pushed, the service weight indicating an importance degree of the service, the higher the importance degree is, the larger the service weight is. The service weight may be preset in the server, for example, a weight configuration is set, and the weight configuration includes a service weight corresponding to each service in the rule platform. It is worth to be noted that different service weights can be set in the weight configuration for the same service triggered by different scene identifiers.

Then, the server determines the push timing of each service to be pushed according to the sequence of the service weights from large to small, that is, the service with the larger service weight is preferentially pushed. Specifically, the push timing of each service may be determined according to a set push frequency, for example, if the push frequency is once pushed for 30 seconds, the push timing of the service with the largest service weight is determined as the current time, and then 30 seconds, 60 seconds, and … … after the current time are sequentially determined as the push timings of other services according to the order of the service weights from large to small.

In some embodiments, the above-mentioned determining a plurality of services corresponding to the scene identification in the rule platform may be implemented by: when the first rule platform comprises the equipment identifier, the server determines a plurality of services corresponding to the scene identifier in the first rule platform and the second rule platform; when the first rule platform does not comprise the equipment identification, the server determines a plurality of services corresponding to the scene identification in the second rule platform; and the second rule platform corresponds to all the equipment identifications.

The server can be accessed to a first rule platform and a second rule platform, wherein the first rule platform corresponds to a specific device identifier, and the second rule platform corresponds to all device identifiers. When the first rule platform comprises an equipment identifier sent by the client, namely the equipment identifier corresponds to the first rule platform, the server determines a plurality of services corresponding to the scene identifier sent by the client in the first rule platform and the second rule platform; when the first rule platform does not comprise the equipment identification, the server determines a plurality of services corresponding to the scene identification in the second rule platform. It is worth noting that when it is determined that there is overlap in the traffic to be pushed, only one of the overlapping traffic is reserved. Through the mode, the universal second rule platform and the exclusive first rule platform are arranged, on the basis of ensuring the universal capability, the pertinence to the specific equipment identification is improved, and the flexibility of determining the service to be pushed is improved.

In some embodiments, the determining the service weight of each service may be implemented in such a manner that: the server acquires a first platform weight of a first rule platform and acquires a second platform weight of a second rule platform, wherein the first platform weight is greater than the second platform weight; determining the service weight of each service according to the weight configuration; updating the service weight of the service corresponding to the first rule platform according to the first platform weight; and updating the service weight of the service corresponding to the second rule platform according to the second platform weight.

In the embodiment of the invention, the first rule platform has specificity, so the importance degree of the service set in the first rule platform is higher, and the weight of the first platform is specifically set to be greater than that of the second platform. For each determined service to be pushed, the service weight of each service is determined from the weight configuration of the server. When the service only corresponds to the first rule platform, updating the service weight of the service according to the first platform weight; when the service only corresponds to the second rule platform, updating the service weight of the service according to the second platform weight; and when the service corresponds to the first rule platform and the second rule platform, updating the service weight of the service according to the first platform weight. The embodiment of the present invention does not limit the update processing method, and may include: and adding or multiplying the platform weight and the service weight. By the mode, the service weight is updated according to the property of the service (corresponding to which type of rule platform), and the accuracy of subsequent pushing is improved.

In some embodiments, the determining the service weight of each service may be implemented in such a manner that the push timing of each service is determined according to the service weight: the server acquires historical trigger data of each service in the client scene; and classifying the historical trigger data through a machine learning model to obtain the service weight and the pushing time of the corresponding service.

For the service weight, in addition to a preset manner, the server may also obtain historical trigger data of each service in the client scene, for example, the server obtains the historical trigger data from a log record of the client trigger service, where the historical trigger data is, for example, the number of times of triggering the service each day in the last seven days. Then, the server classifies the historical trigger data of each service through the machine learning model to obtain the service weight and the pushing time of the corresponding service. By means of the model processing, accuracy of determining the push timing is improved from another angle.

In step 107, when the push opportunity is satisfied, the server pushes the service to the client according to the style identifier and the service content of the service corresponding to the push opportunity.

And when the current time reaches the push opportunity, the server pushes the service to the client according to the style identification and the service content of the service corresponding to the push opportunity, wherein the service content comprises a service file and/or a service icon. In addition, a service pop-up policy of each service may be configured in the server, and when the push opportunity is satisfied, the corresponding service pop-up policy, the style identifier, and the service content are sent to the client together, for example, the service pop-up policy of a certain service is configured such that the client presents the service content 1 time every 5 seconds according to the style identifier until 3 times of presentation.

In step 108, the client presents the service content according to the style corresponding to the style identifier.

The style identification corresponds to the style in the client, and the client presents the service content according to the style corresponding to the style identification after acquiring the style identification and the service content.

In some embodiments, the client may present the service content according to the style corresponding to the style identifier in such a manner that: when the client side has the floating window authority, the client side presents the floating window comprising the service content according to the style identification; when the client side does not have the floating window authority, bypassing the floating window authority according to the style identification, and presenting the floating window comprising the service content; when the client fails to bypass the floating window permission, the service content is presented in a notification bar according to the style identification; the style identification comprises a floating window identification and a notification bar identification.

When the style identifier sent to the client comprises the floating window identifier and the notification bar identifier, the client firstly detects whether the client has the floating window authority for presenting the service content. And when the client side has the floating window authority, the client side presents the floating window comprising the service content according to the style identification. And when the client does not have the floating window authority, bypassing the floating window authority according to the style identification, for example, the client bypasses the floating window authority by setting the TypeToast and presents the floating window including the business content, and when the TypeToast is set and the floating window is displayed unsuccessfully, bypassing the floating window authority by setting the Activity and presenting the floating window including the business content, wherein the TypeToast and the Activity are parameters related to the floating window in the client.

And when the client fails to bypass the floating window authority, presenting the service content in the notification bar according to the style identification. In addition, the client can synchronously present the business content in the notification bar when the presented floating window including the business content is not triggered. By the mode, the business content is ensured to be displayed in the floating window as much as possible, and the attraction effect of the business content on the user is increased.

In some embodiments, the determining the style identifier and the service content of each service according to the push configuration may be implemented in such a manner that: the server determines the style identification, the service content and the jump link of each service according to the push configuration;

the service can be pushed to the client according to the style identification and the service content of the service corresponding to the pushing opportunity in such a way that: the server sends the style identification, the service content and the jump link of the service corresponding to the pushing opportunity to the client, so that the client presents the service content according to the style identification, and initiates a data request according to the jump link when the service content is triggered; and sending jump data corresponding to the jump link to the client according to the data request of the client.

Besides the style identification and the service content, a jump link corresponding to each service can be set in the push configuration of the server in advance. And during pushing, the server sends the style identification, the service content and the jump link of the service to be pushed to the client. The client presents the service content according to the style identification, and initiates a data request to the server according to the jump link when the service content is triggered, for example, a floating window including the service content is clicked by a user. The server sends jump data corresponding to the jump link to the client according to the data request of the client, for example, when the service is an information recommendation service, a specific information text is used as the jump data and sent to the client. By the mode, the applicability of service pushing is improved, and the method is suitable for services needing page skipping.

As can be seen from the above exemplary implementation of fig. 3A, in the embodiment of the present invention, a rule platform is determined according to an equipment identifier of a client, a plurality of services corresponding to a triggered scene identifier in the rule platform are determined, a push opportunity is determined according to a service weight of each service, and when the push opportunity is satisfied, the service is pushed according to push configuration of the corresponding service, so that push processes of different services are ensured not to conflict with each other, and the ordering and rationality of the push service are improved.

In some embodiments, referring to fig. 3B, fig. 3B is another optional flowchart of the service pushing method based on artificial intelligence according to the embodiment of the present invention, after step 108, in step 109, the server determines a plurality of services corresponding to the device identifier in the rule platform, and determines historical trigger data of each service at the client.

The server determines a plurality of services corresponding to the device identifier in the rule platform, and determines historical trigger data of each service at the client, for example, the server acquires the historical trigger data of each service at the client from a log record of the service triggered by the client, where the historical trigger data is the number of times of triggering the service each day in the last seven days. It should be noted that, when determining a plurality of services corresponding to the device identifier in the rule platform, the type of the scene identifier is not limited.

In step 110, the server determines the service corresponding to the historical trigger data meeting the trigger condition as the target service.

For example, the triggering condition is set such that the triggering times of the service in the past seven days reach a time threshold, for example, the time threshold is 3 times, and for the historical triggering data meeting the triggering condition, the server determines the service corresponding to the historical triggering data as the target service, which is equivalent to the service triggered by the user at high frequency. And when the historical trigger data meeting the trigger condition are at least two, determining the service corresponding to the historical trigger data with more triggering total times as the target service.

In step 111, the server obtains a first service quantity of the services pushed to the client within a set time period and a second service quantity of the services presented by the client.

For example, a set time period is from nine am to nine pm in a day, and in the set time period, the server obtains a first service quantity of a service pushed to the client and obtains a second service quantity of a service presented by the client. The second service quantity of the client presentation service can be fed back to the server by the client.

In step 112, the server determines the service filling rate of the client in the set time period according to the first service quantity and the second service quantity.

Here, the ratio between the second traffic amount and the first traffic amount is determined as the traffic filling rate of the client in the set time period.

In step 113, when the service filling rate satisfies the filling rate condition, the server pushes the target service to the client within the set time period according to the style identifier and the service content of the target service.

Here, the fill rate condition may be that the traffic fill rate is lower than a set fill rate threshold, such as 30%. When the service filling rate meets the filling rate condition, the server determines the style identification and the service content of the target service according to the push configuration, for example, in the case that the target service is a self-contained function of the client, the service content may include a functional main title and a functional sub-title of the target service in the client. Then, the server pushes the target service to the client within a set time period according to the style identifier and the service content, and a specific pushing opportunity may be set according to an actual application scenario, for example, the target service is pushed at eight nights in a day.

In step 114, the client presents the service content of the target service according to the style corresponding to the style identifier of the target service.

And in a similar way, the client determines the corresponding style according to the style identifier of the target service and presents the service content of the target service according to the style.

As can be seen from the above exemplary implementation of fig. 3B, in the embodiment of the present invention, when the service filling rate is low, the target service frequently triggered is pushed within a set time period, so that the pushing effect is improved.

In some embodiments, referring to fig. 3C, fig. 3C is an optional flowchart of determining an optimal configuration from at least two types of configurations to be tested, which is provided by the embodiment of the present invention, so as to be executed by the testing client and the server 200 of the terminal device 400, and the steps shown in fig. 3C are described in conjunction with the flowchart.

In step 115, the server obtains at least two types of configurations to be tested, and determines a test client corresponding to each type of configuration to be tested.

In the embodiment of the invention, different configurations can be tested, so that the service push is carried out according to the configuration with the best effect. Specifically, the server obtains at least two types of configurations to be tested, and determines at least one test client for each type of configuration to be tested. The type of configuration to be tested comprises push configuration and/or mapping configuration included by a rule platform, and the mapping configuration is determined according to an actual test purpose and is used for indicating a mapping relation between equipment identification, scene identification and service. The test clients corresponding to different types of configurations to be tested are isolated from each other, and the client environments of the test clients corresponding to different types of configurations to be tested are the same, and the client environments comprise software/hardware configurations of the clients and client users (for example, the client users are all young).

In step 116, the server pushes the service to the test client according to the various types of configurations to be tested.

Here, the server performs service pushing to the corresponding test clients respectively according to various configurations to be tested, and the process of service pushing is not described herein again.

In step 117, the testing client determines the push efficiency rate for the acquired service.

Here, after obtaining the style identifier and the service content sent by the server, the testing client presents the service content according to the style identifier, and at the same time, determines a pushing effective rate of the service, which may be at least one of a service filling rate and a service triggering rate, and is determined according to an actual application scenario, where the service triggering rate is a ratio between the number of services triggered in the testing client and the number of services presented by the testing client.

In step 118, the server obtains the push efficiency of the test client, and determines the configuration to be tested corresponding to the push efficiency with the highest value as the configuration for pushing the service.

Here, the server obtains the push effective rates fed back by the test clients corresponding to the various types of configurations to be tested, wherein when the number of the test clients corresponding to the one type of configurations to be tested is at least two, the server averages the push effective rates fed back by the at least two test clients, and takes the averaged result as the push effective rate finally corresponding to the type of configurations to be tested. And the server determines the type of configuration to be tested corresponding to the pushing effective rate with the highest value as the configuration for subsequently pushing the service.

It should be noted that, when the effective push rate includes both the service fill rate and the service trigger rate, weights may be set for the service fill rate and the service trigger rate according to an actual application scenario, and a result of weighted summation is used as a final value of the effective push rate.

As can be seen from the above exemplary implementation of fig. 3C, in the embodiment of the present invention, through performing a comparison test, a type of configuration to be tested with the best push efficiency is determined, so that subsequent service push is performed according to the type of configuration to be tested, and the push effect of service push is further improved.

In the following, an exemplary application of the embodiment of the present invention in some practical application scenarios will be described, and for convenience of understanding, an application related service is exemplified, and the application is used for being installed to a client to implement the functions of connecting and managing WiFi.

Referring to fig. 4, fig. 4 is a schematic diagram of a client scene and services provided in the embodiment of the present invention, in fig. 4, the client scene is divided into a strong scene and a weak scene, and for the strong scene, corresponding services including WiFi guidance, physical examination speed measurement, WiFi acceleration and software download are set in a rule platform; for weak scenes, setting corresponding services including information recommendation, point acquisition, game gift bags and welfare activities. Fig. 4 further exemplarily shows five client scenes, including that WiFi is connectable, WiFi is connected, the current time reaches the customary time of the client, the identified current geographic location is the frequent residence of the client, and the user opens the reading page, in practical applications, a part of the client scenes may be determined as a strong scene, and the rest of the client scenes may be determined as a weak scene, for example, the client scenes having WiFi is connectable and WiFi is connected are determined as a strong scene.

Fig. 4 also shows the style of service presentation in the client and the service content, where the style presented by service 41 is the notification bar and the styles presented by services 42, 43 and 44 are the floating windows. When the business is pushed, the configuration related to the business can be adjusted according to the intention of the user to the business, so that the pushing effect of the business pushing is better. For example, when it is detected that the trigger rate of the user actively triggering the WiFi acceleration service and the point pickup service in the client is high, the WiFi acceleration service and the point pickup service are added to the mapping configuration of the rule platform, so that the WiFi acceleration service and the point pickup service are pushed to the client, and the trigger rate of the user is further increased. For another example, through a comparison test, if it is detected that the triggering rate of the user actively triggering the service at two places of home and the company is higher than that at other places, the adding client scenario is as follows: the identified current geographic location belongs to a home or a business. For another example, through a comparison test, if it is detected that the trigger rate of the service content presented by the user in the floating window style is higher than the notification bar style, the style identifier of each service in the push configuration is modified to include the floating window identifier. For another example, for a certain service, if it is detected through the comparison test that the trigger rate of the user to the service content including the first document is higher than that of the second document, the service content is set as the first document in the push configuration.

Referring to fig. 5, fig. 5 is a schematic flow chart of another alternative artificial intelligence based service pushing method according to an embodiment of the present invention. In fig. 5, the trigger point is the above client scene, and after the trigger point is triggered, the client determines a digital scene identifier corresponding to the client scene, and uploads the scene identifier and the device identifier to the middlebox, where the middlebox is a cloud platform and can deploy a server, thereby managing and controlling service push to the client. When the middle station receives the scene identification and the equipment identification, the first rule platform and the second rule platform are pulled, whether the equipment identification is matched with the first rule platform or not is judged, when the matching is successful, the equipment identification is determined to be a specific equipment identification, the scene identification is sent to the first rule platform and the second rule platform, and further matching is carried out; and when the matching fails, determining that the equipment identifier is a universal equipment identifier, and issuing the scene identifier to a second rule platform.

The rule platform is configured with a mapping relation of 'equipment identifier-scene identifier-service', and when the scene identifier is issued to the corresponding rule platform, the service corresponding to the scene identifier is determined in the rule platform according to the mapping relation and is used as the service to be pushed. In the service pushing process, the middle station can also configure whether to access a machine learning model, when not, the pattern identification, the service content, the jump link and the pushing opportunity of each service are determined according to the digitalized pushing configuration and the weight configuration stored in the middle station, and the pushing of each service to be pushed is controlled according to the total control of the middle station; when accessing the machine learning model, the style identifier, the service content, and the skip link (not shown in fig. 5) of each service are determined, and meanwhile, the machine learning model classifies the historical trigger data of each service to obtain the push opportunity of the corresponding service, and the machine learning model controls the push of each service. And controlling the pushing of each service, namely pushing the service to the client according to the style identification, the service content and the jump link of the service corresponding to the pushing opportunity when the pushing opportunity is met.

Referring to fig. 6, fig. 6 is an optional schematic flow chart of data monitoring provided in the embodiment of the present invention, in fig. 6, a central station may access a data monitoring platform, and detect, through the data monitoring platform, from the product layer, the code layer, the server layer, and the like, whether an on-line configuration of the central station is correct, that is, whether the on-line configuration of the central station is consistent with an expectation. In addition, whether the configuration related to the service is digitized or not, such as whether the scene identifier, the equipment identifier, the style identifier and the like are digitized or not, can be detected through the data monitoring platform. When the online configuration is incorrect or the configuration related to the service is not digitized, the data monitoring platform generates an error prompt, thereby prompting related personnel to check the configuration again. In addition, the central station can also be accessed with a contrast test system (ABtest system), the contrast test system supports flow distribution, namely, according to different types of configurations to be tested of the central station, isolated contrast tests are carried out on corresponding test clients, and test results of the contrast test system can be determined through the data monitoring platform. For digital configuration, a corresponding data report can be constructed, thereby facilitating the viewing and understanding of related personnel.

Referring to fig. 7, fig. 7 is an optional architecture diagram of a middle station according to an embodiment of the present invention, in fig. 7, the middle station is configured with a first rule platform and a second rule platform, where the first rule platform corresponds to a specific device identifier, and the second rule platform corresponds to a general device identifier. The rule platform stores mapping configuration of 'device identifier-scene identifier-service', specific contents of the mapping configuration can be adjusted according to actual application scenes, for example, setting a client scene includes unlocking a screen, returning to a desktop, connecting with WiFi successfully and the like, and setting a scene identifier corresponding to the client scene in the mapping configuration, and in addition, relationship logic including AND, OR and NOT, for example, setting mapping configuration as 'device identifier 1-scene identifier 1 or 2-service 1', and existence or relationship between scene identifier 1 and scene identifier 2 in the mapping configuration can be set in the mapping configuration of the rule platform.

The middle station also stores push configuration, the push configuration comprises style identification, service content and jump link of each service, wherein the style identification indicates the style presented by the client, such as a floating window or a notification bar; the service content comprises a service file and/or a service icon, and can be dynamically configured according to the actual application scene; the jump link is used for requesting corresponding jump data from the middle station by the client after the service is triggered by the user of the client, and the jump data can also be pre-configured in a mode of a file and/or an icon.

After the services to be pushed are determined, the pushing time of each service to be pushed is determined through the central station master control, specifically, the pushing time of each service is determined according to the service weight of each service configured by the central station, and the pushing time indicates the priority of different services. In addition, a service pop-up policy may also be configured in the middle station, for example, the service pop-up policy for configuring a certain service is: and when the push opportunity is met, enabling the client to present the service content for 1 time at intervals of 5 seconds according to the style identification until the service content is presented for 3 times. Besides determining the pushing time according to the pre-configured service weight, the middle station can also access the machine learning model, and the historical trigger data of the service is recovered through the machine learning model, so that the historical trigger data is classified, and the pushing time of each service is determined. And when the determined push opportunity is met, the middle station pushes the corresponding service to the client through the push channel.

In addition, the data monitoring platform accessed by the middle station can check the data related to the service of the middle station to generate a data report, so that related personnel can check and verify the data conveniently, such as checking the general service and the newly added dynamic service of the middle station. Through the contrast test system accessed by the middle platform, the configuration to be tested of the middle platform can be tested, and therefore service pushing is carried out according to the configuration with a good effect.

Referring to fig. 8, fig. 8 is an alternative schematic diagram of service push data monitored and obtained by a data monitoring platform according to an embodiment of the present invention, where the data shown in fig. 8 is obtained by a service push scheme provided by a central station using related technology. In fig. 8, when the middle station pushes the traffic to the client, the client may retry due to a transmission failure, and the like, so that the number of the received traffic of the client is greater than the number of the pushed traffic of the background. Specifically, the number of services received by the client is 1052 thousands, the number of services pushed by the middling station is 1044 thousands, for the received services, the number of rights of the notification bar owned by the client is 558 thousands, the number of services presented by the client is 557 thousands, and the number of triggered services presented by the client is 3.5 thousands. The service presentation rate in fig. 8 is a ratio between the number of services presented by the client and the number of services received by the client, specifically 52.95%, and the service trigger rate is a ratio between the number of services triggered (clicked) by the user of the client and the number of services presented by the client, specifically 0.63%. Based on fig. 8, the purpose of pushing the service according to the embodiment of the present invention is to improve the service presentation rate and the service triggering rate.

Referring to fig. 9, fig. 9 is an alternative diagram of the style privilege ratio provided by the embodiment of the present invention. In fig. 9, the permission ratio of the floating window is 26.9%, and the notification column permission ratio is lower than 57.1%. Since the floating window pattern is more attractive to the user, one aspect of improving the service presentation rate and the service trigger rate is to use the floating window pattern as much as possible to present the service content.

Referring to fig. 10, fig. 10 is a schematic diagram of an alternative strategy for increasing a service presentation rate according to an embodiment of the present invention. In fig. 10, for a client that does not have the floating window authority, the style identifier of the middle station configurable service includes the floating window identifier and the notification bar identifier, and the style identifier and the service content are sent to the client. The client side displays the floating window comprising the business content by setting the TypeToast to bypass the floating window authority, and when the TypeToast is set to display that the floating window fails, the floating window comprising the business content can be displayed by setting the Activity to bypass the floating window authority, wherein the TypeToast and the Activity are parameters related to the floating window in the client side. On the basis, when the presented floating window comprising the business content is not triggered, the business content can be synchronously presented in the notification bar, so that the multiple presentation of the business content is realized. In addition, when the client fails to bypass the floating window authority, the service content is presented in the notification bar according to the style identification. Meanwhile, for silent users with no or less triggered services, a manufacturer push channel can be constructed, the channel coverage rate is improved, and the services are pushed to the client of the silent users through the manufacturer push channel.

Referring to fig. 11, fig. 11 is an alternative configuration diagram of a push configuration provided by the embodiment of the present invention. In fig. 11, for each type of push configuration, a unique push configuration identifier is set, and similarly, for different services, a corresponding service identifier is set. For a service identifier, the push configuration includes a style identifier and service content corresponding to the service identifier, and in fig. 11, the service content including data 1, data 2, data 3, and data 4 is exemplarily shown, where data 1 is a service icon, and data 2, data 3, and data 4 are service documents. Relevant personnel can add, edit, delete and the like to the push configuration according to the actual application scene, and the push configuration with the best push effect can be determined through a comparison test.

Referring to fig. 12, fig. 12 is a schematic diagram of an alternative configuration of a service push condition according to an embodiment of the present invention. Fig. 12 shows a device identifier, a scene identifier, a service identifier, and a rule platform, where related personnel may pre-configure a mapping relationship between the device identifier, the scene identifier, and the service identifier, a mapping relationship between the device identifier and the rule platform, and the like. Wherein, for the configuration possibly comprising at least two identifications, the array form can be applied for storage.

Referring to fig. 13, fig. 13 is a schematic diagram of an alternative configuration of the traffic weight provided in the embodiment of the present invention. Fig. 13 shows the service weight identifiers and the specific weight configuration, and it should be noted that the weight configuration shown is an array including 10 items, different values in the array correspond to different scene identifiers, and related personnel can set the weight configuration according to an actual application scene.

Referring to fig. 14, fig. 14 is a schematic diagram of an alternative configuration of the gray scale test provided by the embodiment of the present invention. A Globally Unique IDentifier (GUID) is shown in fig. 14, which matches the GUID of the testing client. Fig. 14 also shows that the first service displayed in the configuration is a credit-check-in service, and it should be noted that the chinese name of the service shown in fig. 14 is only for easy understanding, and in the actual processing, the service is still converted into the corresponding digital service identifier for processing.

Referring to fig. 15, fig. 15 is an alternative configuration diagram of a comparative test provided by an embodiment of the present invention. Fig. 15 shows an environment as a formal environment, and when performing a contrast test, a contrast rule may be configured, where the contrast rule includes an experimental group Identifier (ID), a corresponding list of directory IDs, a push switch (whether to start pushing or not), and a product ID, where the directory ID is equivalent to one use case of the test. For example, in the information lab group, the cases for performing the comparison test can be set to include "99000101-number of single pictures" and "99000102-picture height". It is worth mentioning that when pushing the service, the pushing can be performed for the service related to different applications (i.e. the product in fig. 15), for example, for the service related to product a or for the service related to product B. The trigger points in fig. 15 are client scenarios. And related personnel can perform operations such as adding, editing, deleting and the like on the experimental group according to the actual application scene.

Referring to fig. 16, fig. 16 is a schematic diagram of another alternative configuration of the comparative test provided by the embodiment of the present invention. Fig. 16 shows experiment ID, catalog ID, priority, experiment name, start time, end time, flow distribution rule, comparison test experiment parameters, and push effect, and for the experiment group, after the configuration shown in fig. 16 is performed, a multi-dimensional equal test can be performed, specifically, a test client is directionally or randomly extracted, the experiment group is divided into a plurality of experiments, and a corresponding experiment test is performed, thereby further improving the test effect of the comparison test.

Referring to fig. 17, fig. 17 is an optional schematic diagram of a push effect provided in the embodiment of the present invention, where before optimization, the service push scheme provided by the related technology is applied, and after optimization, the service push method provided in the embodiment of the present invention is applied. Through experimental verification of the inventor, after the service push method of the embodiment of the invention is applied to the services related to the application program for connecting and managing the WiFi, the service presentation rate, the service trigger rate, the notification bar permission ratio, the active networking ratio brought by push, the number of the presented services and the active users brought by external push of the client are increased to different degrees. The floating window presentation rate refers to the occupation ratio of the service content presented by the client in all the presentation modes through the floating window mode, the active networking occupation ratio refers to the occupation ratio of users (clients) connected with WiFi through the application program in all the WiFi connection modes, and the active users brought by external pushing refer to the number of the users (clients) installing and using the application program after the external pushing service. After the service pushing method provided by the embodiment of the invention is optimized, the pushing effect of the service is improved.

Continuing with the exemplary structure of the artificial intelligence based service push device 255 implemented as a software module provided by the embodiment of the present invention, in some embodiments, as shown in fig. 2, the software module stored in the artificial intelligence based service push device 255 of the storage 250 may include: an identifier obtaining module 2551, configured to, in response to a trigger operation on a client scene, obtain a scene identifier corresponding to the client scene; a platform determining module 2552, configured to obtain a device identifier of the client, and determine a rule platform corresponding to the device identifier; a service determining module 2553, configured to determine a plurality of services corresponding to the scene identifier in the rule platform; a content determining module 2554, configured to determine, according to the push configuration, a style identifier and service content of each service; a timing determining module 2555, configured to determine a service weight of each service, and determine a push timing of each service according to the service weight; and a pushing module 2556, configured to, when the pushing opportunity is met, push the service to the client according to the service style identifier and the service content corresponding to the pushing opportunity.

In some embodiments, the artificial intelligence based service push device 255 further comprises: a historical data acquisition module, configured to determine multiple services corresponding to the device identifier in the rule platform, and determine historical trigger data of each service at the client; the target service determining module is used for determining the service corresponding to the historical trigger data meeting the trigger condition as the target service; the service quantity acquisition module is used for acquiring a first service quantity of services pushed to the client in a set time period and a second service quantity of services presented by the client; a filling rate determining module, configured to determine, according to the first service quantity and the second service quantity, a service filling rate of the client in the set time period; and the target service pushing module is used for pushing the target service to the client within the set time period according to the style identification and the service content of the target service when the service filling rate meets the filling rate condition.

In some embodiments, the traffic determination module 2553 is further configured to: when the first rule platform comprises the equipment identifier, determining a plurality of services corresponding to the scene identifier in the first rule platform and the second rule platform; when the first rule platform does not comprise the equipment identifier, determining a plurality of services corresponding to the scene identifier in the second rule platform; and the second rule platform corresponds to all the equipment identifications.

In some embodiments, the opportunity determination module 2555 is further configured to: acquiring a first platform weight of the first rule platform and a second platform weight of the second rule platform, wherein the first platform weight is greater than the second platform weight; determining the service weight of each service according to weight configuration; updating the service weight of the service corresponding to the first rule platform according to the first platform weight; and updating the service weight of the service corresponding to the second rule platform according to the second platform weight.

In some embodiments, the pushing module 2556 is further configured to: when the style identification of the service corresponding to the push opportunity comprises a floating window identification and a notification bar identification, the style identification and the service content of the service are sent to the client, so that the client executes the following processing: when the client side has the floating window right, the floating window comprising the service content is presented according to the style identification; when the client does not have the floating window authority, bypassing the floating window authority according to the style identification, and presenting the floating window comprising the service content; and when the client fails to bypass the floating window permission, presenting the service content in a notification bar according to the style identification.

In some embodiments, the opportunity determination module 2555 is further configured to: acquiring historical trigger data of each service in the client scene; and classifying the historical trigger data through a machine learning model to obtain the service weight and the pushing time of the corresponding service.

In some embodiments, the artificial intelligence based service push device 255 further comprises: the system comprises a to-be-tested configuration acquisition module, a test client and a test data acquisition module, wherein the to-be-tested configuration acquisition module is used for acquiring at least two types of to-be-tested configurations and determining the test client corresponding to each type of to-be-tested configuration; the configuration to be tested comprises the push configuration and/or the mapping configuration included by the rule platform, the mapping configuration is used for indicating the mapping relation among the equipment identifier, the scene identifier and the service, and the test clients corresponding to the different types of configurations to be tested are isolated from each other; the effective rate obtaining module is used for carrying out service pushing on the test client according to various types of configurations to be tested and obtaining the pushing effective rate of the test client; and the configuration determining module is used for determining the configuration to be tested corresponding to the pushing efficiency with the highest numerical value as the configuration for pushing the service.

In some embodiments, the content determination module 2554 is further configured to: determining the style identification, the service content and the jump link of each service according to the push configuration;

the push module 2556 is further configured to: sending the style identification, the service content and the jump link of the service corresponding to the pushing opportunity to the client so that the client presents the service content according to the style identification, and initiating a data request according to the jump link when the service content is triggered; and sending jump data corresponding to the jump link to the client according to the data request of the client.

The embodiment of the present invention provides a storage medium storing executable instructions, where the executable instructions are stored, and when being executed by a processor, will cause the processor to execute the artificial intelligence based service push method provided by the embodiment of the present invention, for example, the artificial intelligence based service push method as shown in fig. 3A or 3B.

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

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

By way of example, executable instructions may correspond, but do not necessarily have to correspond, to files in a file system, and may be stored in a portion of a file that holds other programs or data, such as in one or more scripts in a hypertext markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).

By way of example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.

In summary, the embodiment of the present invention effectively ensures that the push of different services does not conflict with each other, improves the ordering and rationality of the push services, and improves the user experience, so that the probability of the user triggering the push service is improved, and the purpose of promoting the service is better achieved.

The above description is only an example of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and scope of the present invention are included in the protection scope of the present invention.

Claims

1. A service pushing method based on artificial intelligence is characterized by comprising the following steps:

2. The service pushing method according to claim 1, further comprising:

determining a plurality of services corresponding to the equipment identification in the rule platform, and determining historical trigger data of each service at the client;

determining the service corresponding to the historical trigger data meeting the trigger condition as a target service;

acquiring a first service quantity of services pushed to the client and a second service quantity of services presented by the client within a set time period;

determining the service filling rate of the client in the set time period according to the first service quantity and the second service quantity;

and when the service filling rate meets a filling rate condition, pushing the target service to the client within the set time period according to the style identification and the service content of the target service.

3. The method of claim 1, wherein the determining the plurality of services corresponding to the scene identifier in the rule platform comprises:

when the first rule platform comprises the equipment identifier, determining a plurality of services corresponding to the scene identifier in the first rule platform and the second rule platform;

when the first rule platform does not comprise the equipment identifier, determining a plurality of services corresponding to the scene identifier in the second rule platform;

and the second rule platform corresponds to all the equipment identifications.

4. The method according to claim 3, wherein the determining the traffic weight of each of the services comprises:

acquiring a first platform weight of the first rule platform and a second platform weight of the second rule platform, wherein the first platform weight is greater than the second platform weight;

determining the service weight of each service according to weight configuration;

updating the service weight of the service corresponding to the first rule platform according to the first platform weight;

and updating the service weight of the service corresponding to the second rule platform according to the second platform weight.

5. The method according to claim 1, wherein the pushing the service to the client according to the service style identifier and the service content corresponding to the push opportunity comprises:

when the style identification of the service corresponding to the push opportunity comprises a floating window identification and a notification bar identification, the style identification and the service content of the service are sent to the client, so that the client executes the following processing:

when the client side has the floating window right, the floating window comprising the service content is presented according to the style identification;

when the client does not have the floating window authority, bypassing the floating window authority according to the style identification, and presenting the floating window comprising the service content;

and when the client fails to bypass the floating window permission, presenting the service content in a notification bar according to the style identification.

6. The method according to claim 1, wherein the determining the service weight of each service and the determining the pushing timing of each service according to the service weight comprise:

acquiring historical trigger data of each service in the client scene;

and classifying the historical trigger data through a machine learning model to obtain the service weight and the pushing time of the corresponding service.

7. The traffic pushing method according to any one of claims 1 to 6, further comprising:

acquiring at least two types of configurations to be tested, and determining test clients corresponding to the various types of configurations to be tested;

the configuration to be tested comprises the push configuration and/or the mapping configuration included by the rule platform, the mapping configuration is used for indicating the mapping relation among the equipment identifier, the scene identifier and the service, and the test clients corresponding to the different types of configurations to be tested are isolated from each other;

carrying out service push on the test client according to various types of configurations to be tested, and obtaining the push effective rate of the test client;

and determining the configuration to be tested corresponding to the pushing effective rate with the highest numerical value as the configuration for pushing the service.

8. Traffic pushing method according to any of the claims 1 to 6,

the determining the style identifier and the service content of each service according to the push configuration includes:

determining the style identification, the service content and the jump link of each service according to the push configuration;

the pushing the service to the client according to the style identification and the service content of the service corresponding to the pushing opportunity comprises:

sending the style identification, the service content and the skip link of the service corresponding to the pushing opportunity to the client so as to enable the client to push the service

The client presents the service content according to the style identification, and initiates a data request according to the jump link when the service content is triggered;

and sending jump data corresponding to the jump link to the client according to the data request of the client.

9. A service pushing device based on artificial intelligence is characterized by comprising:

10. An electronic device, comprising:

a memory for storing executable instructions;

a processor, configured to execute the executable instructions stored in the memory, and implement the artificial intelligence based service push method according to any one of claims 1 to 8.