An information delivery method, device and computer readable storage medium

Abstract

Embodiments of the present application provide an information putting method, device and computer readable storage medium; the method comprises: obtaining portrait information, exposure information and trigger information of a target putting object; the portrait information describes interests of the target putting object, the exposure information represents information shown to the target putting object, and the trigger information represents information triggered by the target putting object; based on the portrait information, the exposure information and the trigger information, a demand type of the target putting object is determined; the demand type represents an information type demanded by the target putting object; using the demand type, to-be-put information is matched from a preset information set; the to-be-put information represents information waiting to be put to the target putting object; and the to-be-put information is sent to a terminal corresponding to the target putting object. Through the present application, the precision of information putting can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to big data technology in the field of Internet, and in particular to an information putting method and device based on big data and a computer readable storage medium. BACKGROUND

[0002] The advent of the big data era makes the information on the Internet more and more, and the users to which the information is directed are not the same. If different categories of information can be targeted to the terminals of corresponding users, the user experience can be greatly improved. Information putting refers to the back end matching a category of users for information and sending the information to the terminals of the matched users so that the information can be read by the category of users.

[0003] In the related art, the back end usually directly matches users based on the tags of information and the tags of users to implement information putting. However, the accuracy of directly matching users by using tags may be deviated, so that the back end may put the content that is not interesting to the users to the users when putting information based on the tags of information and the tags of users, and the content that is really interesting to the users is not put, thereby resulting in a low precision of information putting. SUMMARY

[0004] The embodiments of the present application provide an information putting method, device and computer readable storage medium, which can improve the precision of information putting.

[0005] The technical solution of the embodiments of the present application is as follows:

[0006] The embodiments of the present application provide an information putting method, comprising:

[0007] Obtaining portrait information, exposure information and trigger information of a target putting object; the portrait information describes the interest of the target putting object, the exposure information represents the information displayed to the target putting object, and the trigger information represents the information triggered by the target putting object;

[0008] Determining the demand type of the target putting object based on the portrait information, the exposure information and the trigger information; the demand type represents the information type required by the target putting object;

[0009] Matching the to-be-put information from a preset information set by using the demand type; the to-be-put information represents the information waiting to be put to the target putting object;

[0010] Sending the to-be-put information to the terminal corresponding to the target putting object.

[0011] In some embodiments of the present application, the predicted delivery return index corresponding to the demand type comprises:

[0012] The exposure weight parameter and the trigger weight parameter are used to construct a trigger exposure proportion.

[0013] The delivery object quantity, the interest proportion, and the trigger exposure proportion are multiplied to obtain the delivery return index.

[0014] In some embodiments of the present application, before the portrait information, exposure information, and trigger information of the target delivery object are obtained, the method further comprises:

[0015] According to a preset category attribute, all objects are classified to obtain at least one delivery object.

[0016] From the at least one delivery object, any one delivery object is selected as the target delivery object.

[0017] In some embodiments of the present application, after the demand type is used to match the to-be-delivered information from the preset information set, and before the to-be-delivered information is sent to the terminal of the target delivery object, the method comprises:

[0018] Obtain the to-be-pushed information for the target delivery object.

[0019] Correspondingly, the to-be-delivered information is sent to the terminal corresponding to the target delivery object to realize information delivery, comprising:

[0020] The to-be-pushed information and the to-be-delivered information are sent to the terminal of the target delivery object.

[0021] In some embodiments of the present application, the portrait information comprises type labels of various types, and each type label corresponds to a type weight.

[0022] The type weight is obtained by integrating a plurality of temporary type weights obtained from various business platforms.

[0023] An embodiment of the present application provides an information delivery method, characterized by comprising:

[0024] Receiving the to-be-delivered information sent by the server;

[0025] The to-be-delivered information is filled into the information display sub-area of the information stream area to obtain a display information stream; wherein the information stream area is located in the first preset area of the display interface, and the information display sub-area is overlaid on the second preset area of the information stream area.

[0026] present the display information stream on the display interface, and realize information delivery.

[0027] Embodiments of the present application provide an information delivery device, comprising:

[0028] an acquisition module, configured to acquire portrait information, exposure information and trigger information of a target delivery object; the portrait information describes interests of the target delivery object, the exposure information represents information shown to the target delivery object, and the trigger information represents information triggered by the target delivery object;

[0029] a demand determination module, configured to determine a demand type of the target delivery object based on the portrait information, the exposure information and the trigger information; the demand type represents a type of information demanded by the target delivery object;

[0030] an information matching module, configured to match out to-be-delivered information from a preset information set by using the demand type; the to-be-delivered information represents information waiting to be delivered to the target delivery object;

[0031] a sending module, configured to send the to-be-delivered information to a terminal corresponding to the target delivery object.

[0032] Embodiments of the present application provide an information presentation device, comprising:

[0033] a receiving module, configured to receive to-be-delivered information sent by a server;

[0034] an information processing module, configured to fill the to-be-delivered information into an information display sub-region of an information stream region, to obtain a display information stream; wherein the information stream region is located in a first preset region of a display interface, and the information display sub-region covers a second preset region of the information stream region;

[0035] a display module, configured to present the display information stream on the display interface, and realize information delivery.

[0036] Embodiments of the present application provide a server, comprising:

[0037] a first memory, configured to store executable information delivery instructions;

[0038] a first processor, configured to execute the executable information delivery instructions stored in the first memory, to realize an information delivery method provided by the server side of embodiments of the present application.

[0039] Embodiments of the present application provide a terminal, comprising:

[0040] a second memory, configured to store executable information delivery instructions;

[0041] The second processor is configured to execute the executable information delivery instruction stored in the second memory, and implement the information delivery method provided by the terminal side of the embodiment of the present application.

[0042] The embodiment of the present application provides a computer readable storage medium, which stores an executable information delivery instruction, and is configured to cause the first processor to execute the information delivery method provided by the server side of the embodiment of the present application, or cause the second processor to execute the information delivery method provided by the terminal side of the embodiment of the present application.

[0043] The embodiment of the present application has the following beneficial effects:

[0044] In the embodiment of the present application, the server analyzes the portrait information, exposure information and trigger information of the target delivery object, determines the actual required information type of the target delivery object, and then finds the to-be-delivered information according to the actual required information type of the target delivery object and delivers the to-be-delivered information, so that the to-be-delivered information fully meets the interest and requirement of the target delivery object, and the precision of information delivery is improved. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 is a schematic diagram of an information flow;

[0046] Figure 2 is a schematic diagram of an information delivery system 100 provided by the embodiment of the present application;

[0047] Figure 3 is a schematic diagram of a structure of the server 200 in the information delivery system 100 provided by the embodiment of the present application; Figure 2

[0048] Figure 4 is a schematic diagram of a structure of the terminal 400 in the information delivery system 100 provided by the embodiment of the present application; Figure 2

[0049] Figure 5 is a schematic diagram of an optional flow of the information delivery method provided by the embodiment of the present application; Figure 1

[0050] Figure 6 is a schematic diagram of an information flow area and an information display sub-area provided by the embodiment of the present application;

[0051] Figure 7 is a schematic diagram of displaying an information flow provided by the embodiment of the present application; Figure 1

[0052] Figure 8 is a schematic diagram of an optional flow of the information delivery method provided by the embodiment of the present application; Figure 2 ​​​​​

[0053] Figure 9 is an optional flowchart of the information delivery method provided by the embodiment of the present application Figure 3 ;

[0054] Figure 10 is an optional flowchart of the information delivery method provided by the embodiment of the present application Figure 4 ;

[0055] Figure 11 is a schematic diagram of displaying information flow provided by the embodiment of the present application Figure 2 ;

[0056] Figure 12 is a schematic diagram of the income distribution of objects with different activity provided by the embodiment of the present application

[0057] Figure 13 is a schematic diagram of the income distribution of objects with different gender provided by the embodiment of the present application

[0058] Figure 14 is a schematic diagram of the income distribution of objects with different age provided by the embodiment of the present application

[0059] Figure 15 is a schematic diagram of the income distribution of objects with different city provided by the embodiment of the present application DETAILED DESCRIPTION

[0060] In order to make the objects, technical solutions and advantages of the present application clearer, the following will further describe the present application in conjunction with the accompanying drawings, and the described embodiments should not be regarded as limiting the present application, and all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0061] In the following description, "some embodiments" are described, which describe a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subset of all possible embodiments, and can be combined with each other without conflict.

[0062] In the following description, the term "first\second" is only to distinguish similar objects, and does not represent the specific order of the objects, and it can be understood that "first\second" can be interchanged with the specific order or sequence as allowed, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0063] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application, and are not intended to limit the present application.

[0064] The related data collection and processing in the embodiments of the application should strictly comply with the requirements of relevant laws and regulations, obtain the informed consent or separate consent of the personal information subject, and carry out subsequent data use and processing within the scope of authorization of laws and regulations and the personal information subject.

[0065] Before the embodiments of the application are further described in detail, the terms and phrases involved in the embodiments of the application are explained, and the terms and phrases involved in the embodiments of the application are applicable to the following explanations.

[0066] 1) Information pushing refers to inferring information that a user may like according to information read by the user in a historical time, and sending the inferred information to a terminal of the user for reading by the user.

[0067] 2) Information putting refers to putting information to potential users so that the information can be exposed to more users. It should be noted that information putting and information pushing are different exposure methods. Information pushing is generally performed for a single user, that is, from the perspective of the user, information is sought, while information putting is performed for a user group, that is, from the perspective of the information, users are matched.

[0068] 3) Information generally consists of a title and a body. The title can consist of a text title and a cover picture to guide the user to click to read the body; the body can consist of text, pictures, videos, etc. to fully display the content in the information.

[0069] 4) Information flow refers to using multiple information to form an information flow that can be scrolled and viewed. In the information flow, there are multiple information display sub-areas, which are arranged in sequence, and each information display sub-area displays a title of an information. After the user clicks the title, the user can jump to the body page.

[0070] Exemplarily, Figure 1 A schematic diagram of the information flow is shown. In the display area 1-1 of the information flow, there are information display sub-area 1-11, information display sub-area 1-12 and information display sub-area 1-13. Among them, the information display sub-area 1-11 displays the text: Emergency announcement XXX 1-111, and the cover Figures 1-11 2; the information display sub-area 1-12 displays the text: Protest XXXX 1-121, and the cover Figures 1-12 2; the information display sub-area 1-13 displays the text: Dormitory fee investigation result 1-131, and the cover Figures 1-13 2.

[0071] 5) Exposure, refers to the process of a piece of information being displayed to a user in the information stream. When a piece of information appears in the information stream once, it is recorded that the piece of information has been exposed once.

[0072] 6) Click, when a piece of information is exposed to a user in the information stream, the user clicks on the title to enter the text page to read, then it is recorded that the piece of information has been clicked once.

[0073] 7) Portrait information, is a model based on a series of real data, is a labeled model extracted according to the entity attributes, characteristics and other information of the user. The core work of building portrait information is to label the entity, and the label is a highly refined feature identifier obtained by analyzing the entity information.

[0074] 8) Target Group Index (TGI) represents the degree of attention of a user to a certain feature. TGI = [the proportion of the user group with a certain feature in the target user group / the proportion of the user group with the same feature in the total] * standard number 100. TGI index equal to 100 represents the average level, higher than 100 represents the degree of attention of the user to a certain feature.

[0075] For example, in a certain video client, the male and female ratio of users is 60% and 40% respectively, among these users, the male and female ratio of users who have watched a certain sports video is 90% and 10% respectively, then the TGI of the sports video in the male is , and the TGI in the female is ; among these users, the male and female ratio of users who have watched a certain sports video is 20% and 80% respectively, then the TGI of the sports video in the male is , and the TGI in the female is . As can be seen, men have stronger preference for sports videos, and women have stronger preference for baby videos.

[0076] 9) Tag2Vector, refers to converting words in the corpus into vectors, for example, converting the tags of information into vector form.

[0077] The advent of the big data era makes the information on the Internet more and more, these information are not the same for different users, if different categories of information can be targeted to deliver to the corresponding user's terminal, it can greatly improve the user's experience of reading information. Information delivery is to realize this kind of targeted information delivery, information delivery refers to that the back end matches a category of users for the information, and sends the information to the terminal of the matched user, so that the information can be read by this category of users.

[0078] In a general case, the backend obtains information to be pushed, and the backend can circumscribe a class of users to perform the pushing according to the labels of the information to be pushed and the labels determined by an operator for the information to be pushed, that is, directly matching the users based on the labels of the information and the labels of the users to realize the information pushing. For example, when the backend obtains an article named "Beijing Palace You Don't Know", the original labels of the article are "palace" and "courtyard", and the operator can also determine "cultural relics" and "Forbidden City" according to the content of the article, at this time, the final labels of the article are "palace", "courtyard", "Forbidden City" and "cultural relics". The backend circumscribes a batch of users with these labels from all users, and exposes the article to the batch of users.

[0079] However, the users circumscribed directly by using the labels of the information may not all like the information. For example, the user who likes "Forbidden City" may only be interested in "Qing Dynasty Palace Drama", and may not be interested in "palace and courtyard". Therefore, the accuracy of directly matching the users by using the labels may be deviated, so that when the backend performs the information pushing based on the labels of the information and the labels of the users, the user may be pushed the content that the user is not interested in, and the content that the user is really interested in may not be pushed, thereby causing the precision of the information pushing to be low.

[0080] In addition, before the information pushing, the backend may have pushed the content with the same or similar labels to the user, that is, the backend has over-exposed the information similar to the information to the user. For example, the backend has exposed the content with the "palace" label to the user through a pushing system, so that the user is tired of the content related to the palace, at this time, if the information with the "palace" label is continued to be pushed to the user, the user will have a feeling of disgust, thereby causing the proportion of the pushing converted to the clicking to be low.

[0081] The embodiment of the present application provides an information pushing method, device and computer readable storage medium, which can improve the precision of information pushing. The following describes an exemplary application of the information pushing device provided by the embodiment of the present application. The information pushing device provided by the embodiment of the present application can be implemented as a terminal or a server. The server can be a physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing; the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal and the server can be directly or indirectly connected through wired or wireless communication, which is not limited in the embodiment of the present application. The following will describe the exemplary application when the information pushing device is implemented as a server and a terminal respectively.

[0082] Referring to Figure 2 ,Figure 2 is an optional architecture diagram of the information delivery system 100 provided by the embodiments of the present application, for implementing a support information delivery application, the terminal 400 connects the server 200 through the network 300, the network 300 can be a wide area network or a local area network, or a combination of the two.

[0083] In the information delivery, the server 200 first acquires the portrait information, exposure information and trigger information of the target delivery object, wherein the portrait information describes the interest of the target delivery object, the exposure information represents the information displayed to the target delivery object, and the trigger information represents the information triggered by the target delivery object. Then, the server 200 determines the demand type of the target delivery object based on the portrait information, the exposure information and the trigger information, wherein the demand type represents the information type required by the target delivery object. Then, the server 200 matches the to-be-delivered information from the to-be-delivered information set by using the demand type, wherein the to-be-delivered information represents the information waiting to be delivered to the target delivery object. After that, the server 200 sends the to-be-delivered information to the terminal 400 of the target delivery object through the network 300. After receiving the to-be-delivered information sent by the server 200, the terminal 400 fills the to-be-delivered information into the information display sub-area of the information stream area to obtain a display information stream, wherein the information stream area is located in the first preset area of the display interface, and the information display sub-area covers the second preset area of the information stream area. Finally, the terminal 400 presents the display information stream on the display interface, thereby realizing information delivery.

[0084] Referring to Figure 3 , Figure 3 is a structure diagram of the server 200 in the Figure 2 provided by the embodiments of the present application, Figure 3 The server 200 shown in the figure includes at least one first processor 210, a first memory 250, at least one first network interface 220 and a first user interface 230. The various components in the server 200 are coupled together through a first bus system 240. It can be understood that the first bus system 240 is used to realize the connection communication between the components. The first bus system 240 includes not only a data bus, but also a power bus, a control bus and a status signal bus. However, for the purpose of clear illustration, all kinds of buses are marked as the bus system 240 in the figure. Figure 3

[0085] The first processor 210 can be an integrated circuit chip with signal processing capability, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., wherein the general-purpose processor can be a microprocessor or any conventional processor. ​

[0086] The first user interface 230 includes one or more first output devices 231 that enable presentation of media content, including one or more speakers and / or one or more visual display screens. The first user interface 230 also includes one or more first input devices 232 that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

[0087] The first memory 250 includes volatile or non-volatile memory, or both. The non-volatile memory can be read only memory (ROM), the volatile memory can be random access memory (RAM), and the first memory 250 described herein is intended to include any suitable type and form of memory. The first memory 250 can optionally include one or more memory devices physically located near the first processor 210.

[0088] In some embodiments, the first memory 250 is capable of storing data to support various operations, examples of such data including, without limitation, programs, modules, and data structures or subsets or superset thereof, examples of which are illustrated below.

[0089] The first operating system 251 includes systems programs for processing various basic system services and for executing hardware dependent tasks, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services as well as processing hardware dependent tasks;

[0090] The first network communication module 252 is configured to communicate to other computing devices via one or more (wired or wireless) first network interfaces 220, examples of which include Bluetooth, wireless fidelity (Wi-Fi), universal serial bus (USB), and the like;

[0091] The first display module 253 is configured to enable presentation of information (e.g., user interfaces for operating peripheral devices and displaying content and information) via one or more first output devices 231 (e.g., display screens, speakers, and the like) associated with the first user interface 230;

[0092] The first input processing module 254 is configured to detect and interpret one or more user inputs or interactions from one or more first input devices 232.

[0093] In some embodiments, the apparatus provided by the embodiments of the present application can be implemented in software, Figure 3The information delivery device 255 stored in the first memory 250 is shown, which can be software in the form of programs and plug-ins, etc., including the following software modules: an acquisition module 2551, a demand determination module 2552, an information matching module 2553, a sending module 2554, a type matching module 2555, an index prediction module 2556, and an object classification module 2557, the functions of each module will be described below.

[0094] In some embodiments, the information delivery device provided by the embodiments of the present application can be implemented in a hardware manner. For example, the information delivery device provided by the embodiments of the present application can be a processor in the form of a hardware decoding processor, which is programmed to execute the information delivery method provided by the server side of the embodiments of the present application. For example, the processor in the form of a hardware decoding processor can use 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 elements.

[0095] For example, the embodiments of the present application provide a server, characterized in that, comprising:

[0096] A first memory for storing executable information delivery instructions;

[0097] A first processor for executing the executable information delivery instructions stored in the first memory, so as to implement the information delivery method provided by the server side of the embodiments of the present application.

[0098] Referring to Figure 4 , Figure 4 is a structural schematic diagram of the terminal 400 in the Figure 2 provided by the embodiments of the present application, Figure 4 The terminal 400 shown in the figure includes at least one second processor 410, a second memory 450, at least one second network interface 420, and a second user interface 430. The various components in the terminal 400 are coupled together through a second bus system 440. It can be understood that the second bus system 440 is used to realize the connection and communication between the components. The second bus system 440 includes not only a data bus, but also a power bus, a control bus, and a status signal bus. However, for the purpose of clear illustration, all kinds of buses are marked as the second bus system 440 in the Figure 4 .

[0099] The second processor 410 can be an integrated circuit chip that has the processing capability of signals, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., wherein the general-purpose processor can be a microprocessor or any conventional processor.

[0100] The second user interface 430 includes one or more second output devices 431 that enable presentation of media content, including one or more speakers and / or one or more visual display screens. The second user interface 430 also includes one or more second input devices 432 that facilitate user input, such as a keyboard, a mouse, a microphone, a touch screen display, a camera, other input buttons and controls.

[0101] The second memory 450 includes volatile memory or non-volatile memory, and can include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), and the volatile memory can be random access memory (RAM). The second memory 450 described in the embodiments of the present application is intended to include any suitable type of memory. The second memory 450 can optionally include one or more storage devices physically removed from the second processor 410.

[0102] In some embodiments, the second memory 450 is capable of storing data to support various operations, examples of which include programs, modules, and data structures or subsets or supersets thereof, which are exemplarily illustrated below.

[0103] The second operating system 451 includes 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;

[0104] The second network communication module 452 is used to reach other computing devices via one or more (wired or wireless) second network interfaces 420, exemplary second network interfaces 420 including Bluetooth, wireless compatibility certification (Wi-Fi), and universal serial bus (USB), etc.

[0105] The second display module 453 is used to enable presentation of information (e.g., user interfaces for operating peripheral devices and displaying content and information) via one or more second output devices 431 (e.g., display screens, speakers, etc.) associated with the second user interface 430;

[0106] The second input processing module 454 is configured to detect one or more user inputs or interactions from one or more of the second input devices 432 and translate the detected inputs or interactions.

[0107] In some embodiments, the information presenting apparatus provided by the embodiments of the present application can be implemented in software, Figure 4 The information presenting apparatus 455 stored in the second memory 450 is shown, which can be software in the form of programs and plug-ins, etc., including the following software modules: a receiving module 4551, an information processing module 4552 and a display module 4553, the functions of which will be described below.

[0108] In some other embodiments, the information presenting apparatus provided by the embodiments of the present application can be implemented in hardware, for example, the information presenting apparatus provided by the embodiments of the present application can be a processor in the form of a hardware decoding processor, which is programmed to execute the information presenting method provided by the embodiments of the present application on the terminal side, for example, the processor in the form of a hardware decoding processor can be 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 elements.

[0109] For example, the embodiments of the present application provide a terminal, characterized in that, comprising:

[0110] The second memory is configured to store executable information presenting instructions;

[0111] The second processor is configured to execute the executable information presenting instructions stored in the second memory, so as to implement the information presenting method provided by the embodiments of the present application on the terminal side.

[0112] In the following, the information presenting method provided by the embodiments of the present application will be described in combination with the exemplary application and implementation of the server and the terminal provided by the embodiments of the present application.

[0113] Referring to Figure 5 , Figure 5 is an optional flowchart of the information presenting method provided by the embodiments of the present application Figure 1 will be described in combination with the steps shown in Figure 5 .

[0114] S101, the server acquires portrait information, exposure information and trigger information of a target delivery object; the portrait information describes interests of the target delivery object, the exposure information represents information shown to the target delivery object, and the trigger information represents information triggered by the target delivery object.

[0115] Embodiments of the present application are implemented in the scenario of delivering information to a target delivery object, for example, delivering an article or a song to the target delivery object. When delivering information to the target delivery object, portrait information of the target delivery object is acquired from a portrait information library, exposure information of the target delivery object and trigger information of the target delivery object are acquired from an operation information library, so as to analyze the actual demand information type of the target delivery object by the server based on the portrait information, the exposure information and the trigger information.

[0116] It should be noted that the target delivery object refers to all objects waiting for information delivery, and the objects can be users registered in the server. In embodiments of the present application, the object waiting for information delivery can be one or multiple, that is, the number of target delivery objects can be one or multiple.

[0117] In some embodiments of the present application, the target delivery object can be a type of object with certain commonality selected from all objects, for example, the target delivery object can be a female of 25-30 years old who likes food selected from all objects, or a male of 18-25 years old who likes games selected from all objects. The target delivery object can be a type of object with other characteristics, which are not enumerated herein.

[0118] It can be understood that the portrait information of the target delivery object refers to a labeled model extracted from the inherent attribute of the target delivery object and historical operation information, which can preliminarily indicate the type of information interested by the target delivery object and the degree of interest. In the portrait information, there can be a type of information interested by the target delivery object, that is, an interest type, and a degree of interest of the target delivery object to each information type, that is, an interest weight, etc.

[0119] The inherent attribute of the target delivery object can refer to the age, gender, region, education level, etc. of the target delivery object. The historical operation information of the target delivery object can refer to information clicked, commented, forwarded or liked by each object in the target delivery object in a historical period, which has its own type and weight. The portrait information is equivalent to integrating the type and weight of the trigger information to obtain a labeled model.

[0120] For example, assuming that there is only one object in the target delivery object, the type and weight of the information triggered by the object are combined to form a set, and the portrait information {“qimei”:“86800803”, [{“tag”:“life”,“w”:1.0}, {“tag”:“entertainment”,“w”:1.0}, {“tag”:“history”,“w”:1.0}, {“tag”:“constellation and fortune”,“w”:0.999}], {“tag”:“finance”,“w”:0.997}]} is obtained. Further, for the same information type, subdivision can also be performed, for example, and then the portrait information is formed by using each subdivision type and the weight of the subdivision type. For example, the portrait information can be {[{“tag”:“culture_ancient artifacts”,“w”:1.0}, {“tag”:“culture_collection”,“w”:1.0}, {“tag”:“food_food culture”,“w”:1.0}, {“tag”:“society_curious things”,“w”:0.999}, {“tag”:“society_community news”,“w”:0.998}, {“tag”:“culture_handicrafts”,“w”:0.997}, {“tag”:“sports_basketball”,“w”:0.996}, {“tag”:“culture_folk customs”,“w”:0.998}, {“tag”:“sports_chess”,“w”:0.998}]}.

[0121] In some embodiments of the present application, the exposure information can have the type of information exposed to the target delivery object, that is, the exposure type, and can also have the type weight of the exposed information, that is, the exposure weight, and the number of times the information is exposed, etc. Similarly, the trigger information also has the type of information triggered by the target delivery object, that is, the trigger type, the type weight of the triggered information, that is, the trigger weight, and the number of times the target delivery object triggers, that is, the trigger times, etc. Of course, the exposure information and the trigger information can also include other contents, which are not limited in the embodiments of the present application.

[0122] It can be understood that in the embodiments of the present application, the trigger refers to the click operation of the target delivery object, and can also be the long press operation of the target delivery object, and can also be the double-click like operation, which is not limited in the embodiments of the present application.

[0123] S102, the server determines the demand type of the target delivery object based on the portrait information, the exposure information and the trigger information; the demand type represents the information type required by the target delivery object.

[0124] Since the target delivery object can trigger the type which is not interested in itself for various reasons at the historical time, or the target delivery object is no longer interested in the information type after a certain time point, but the information type still exists in the portrait information, therefore, the portrait information can not reflect the real demand of the target delivery object. Based on this, the server needs to comprehensively analyze the obtained portrait information, exposure information and trigger information, find the obvious trigger preference of the target delivery object, and the information type which is lack in the exposure information and the portrait information is the type which is actually interested and actually demanded by the target delivery object, that is, the demand type.

[0125] For example, when the portrait information of the target delivery object has the label of a certain TV series, and the exposure information also has the related information of the TV series, but the target delivery object rarely triggers the related information about the TV series, but more triggers the information about the star starring the TV series, which indicates that the target delivery object actually pays attention to the information about the star, that is, the information related to the star, which is the demand type of the target delivery object.

[0126] It should be noted that in some embodiments of the present application, the server can directly determine the demand type by using the interest type in the portrait information, the exposure type in the exposure information and the trigger type in the trigger information. In some other embodiments of the present application, the server can also calculate whether the target delivery object has demand for each type by using the interest weight in the portrait information, the exposure weight and the exposure times in the exposure information, and the trigger weight and the trigger times in the trigger information, that is, determine the demand information of the target delivery object for each type, so as to find the demand type according to the demand information.

[0127] It can be understood that the demand type determined by the server is not a specific information type, but a general term of all determined information types, that is, the demand type can have one or more information types.

[0128] S103, the server matches the to-be-delivered information from the preset information set by using the demand type; the to-be-delivered information represents the information waiting to be delivered to the target delivery object.

[0129] After the server analyzes the demand type, the server can match the demand type with all information in the preset information set one by one, so as to find the information related to the demand type, which is the information which is really demanded and interested by the target delivery object, therefore, the server takes these information as the to-be-delivered information, and prepares to deliver to the target delivery object.

[0130] It can be understood that the server can directly match the demand type with the tags of all information in the preset information set to obtain the information to be put; the server can also perform content analysis on all information in the information set to be put, so as to extract the key information features of all information, such as keywords, article summaries, etc., and then match the information type with the key information features, so as to avoid that the tags of the information set do not comprehensively summarize the information, and select the information that the target delivery object is not interested in as the information to be put.

[0131] It can be understood that the preset information set refers to an information set created in advance, and the preset information set can have some high-quality information, such as high-quality articles, high-quality music, etc. In this way, the quality of the information to be put matched by the server is relatively high. The preset information set can be updated, for example, the latest article of an author is added to the preset information set.

[0132] S104, the server sends the information to be put to the terminal corresponding to the target delivery object.

[0133] After obtaining the information to be put, the server sends the information to be put to the terminal corresponding to the target delivery object through the network. The terminal receives the information to be put sent by the server, so as to present the information to be put subsequently.

[0134] It can be understood that each object in the target delivery object has a corresponding terminal, and the server sends the information to be put to these terminals, so that the information to be put is exposed as much as possible.

[0135] S105, the terminal fills the information to be put into the information display sub-area of the information stream area to obtain a display information stream.

[0136] After receiving the information to be put, the terminal adds the information to be put to the information stream, so that the information to be put is displayed in the information stream, and the target delivery object can obtain the information to be put on the display interface. At this time, the terminal first selects an information display sub-area from the information stream area, then fills the information to be put into the selected information display sub-area, and then takes the information stream in which the information to be put has been filled as a display information stream to be displayed. The information stream area is located in the first preset area of the display interface, and the information display sub-area covers the second preset area of the information stream area.

[0137] It should be noted that in the embodiments of the present application, the size, position, and proportion on the display interface of the first preset area can be set according to actual conditions, for example, the width of the first preset area is directly set as the width of the display interface, the height of the first preset area is set as 4 / 5 of the height of the display interface, the first preset area is set in the middle part of the display interface, and the like, which are not limited in the embodiments of the present application.

[0138] It can be understood that the information stream is composed of multiple information, and therefore, one or more information display sub-areas can be provided in the information stream area, and each information display sub-area can be used to display the to-be-launched information. Further, the terminal can cover one or more display areas on the second preset area of the information stream area as the information display sub-area.

[0139] For example, the embodiments of the present application provide a schematic diagram of the information stream area and the information display sub-area, as shown in Figure 6 The terminal sets the information stream display area 6-11 in the display interface 6-1, which is used to display the information stream. Inside the information stream display area 6-11, there are multiple information display sub-areas, such as the information display sub-area 6-12, the information display sub-area 6-13, and the information display sub-area 6-14, which can be used to display the to-be-launched information.

[0140] S106, the terminal presents the display information stream on the display interface, and realizes information launching.

[0141] After the terminal fills the to-be-launched information into the information display sub-area to obtain the display information stream, the terminal can display the display information stream on the display interface of the terminal, so that the terminal realizes exposing the to-be-launched information to the target launching object, and realizes information launching. The target launching object can select whether to click and trigger the to-be-launched information for reading according to the interest of the target launching object.

[0142] For example, the embodiments of the present application provide a schematic diagram of the display information stream Figure 1 , as shown in Figure 7 The display information stream 7-11 is presented on the display interface 7-1, and in the display information stream 7-11, there are three to-be-launched information, which are the to-be-launched information 7-12, the to-be-launched information 7-13, and the to-be-launched information 7-14. The to-be-launched information 7-12 has a text title: reason for not returning to China 7-12a, and a cover Figures 7-12 b; the to-be-launched information 7-13 has a cover Figures 7-13a, with a text title: Thanks to the treasure netizen provided 7-13b hilarious content; to be put into information 7-14 has a small video 7-14a, and the text title: the air field is open, is to grab a bowl of rice 7-14b. The target delivery object can click the text title, cover picture or small video in the to-be-delivered information according to its own interest to enter the text page of the to-be-delivered information to obtain the detail content of the to-be-delivered information.

[0143] In the embodiment of the application, the server analyzes the portrait information, exposure information and trigger information of the target delivery object obtained, determines the information type actually required by the target delivery object, and then finds and delivers the to-be-delivered information according to the information type actually required by the target delivery object. In this way, the to-be-delivered information fully meets the interest and requirement of the target delivery object, thereby improving the precision of information delivery.

[0144] Referring to Figure 8 , Figure 8 is an optional flowchart of the information delivery method provided by the embodiment of the application Figure 2 In some embodiments of the application, the portrait information includes an interest type, the exposure information includes an exposure type, and the trigger information includes a trigger type. The server determines the requirement type of the target delivery object based on the portrait information, the exposure information and the trigger information. The specific implementation process of S102 can include S1021-S1023 as follows:

[0145] S1021, the server compares the interest type and the trigger type to obtain a first comparison result. The first comparison result represents whether the trigger type is contained in the interest type.

[0146] S1022, the server compares the exposure type and the trigger type to obtain a second comparison result. The second comparison result represents whether the trigger type is contained in the exposure type.

[0147] The server analyzes the portrait information, the exposure information and the trigger information to obtain the interest type, the exposure type and the trigger type of the target delivery object. Then, the server compares the interest type and the trigger type to determine whether the trigger type is contained in the interest type to obtain a first comparison result. Meanwhile, the server compares the exposure type and the trigger type to determine whether the trigger type is contained in the exposure type to obtain a second comparison result.

[0148] It can be understood that the server can compare each type in the trigger type with each type in the interest type, determine whether there is a type in the interest type which is the same as each type in the trigger type or similar to a certain threshold, and determine that the first comparison result is that the interest type contains the trigger type when the type exists. Conversely, when there is no type in the interest type which is the same as each type in the trigger type or similar to a certain threshold, the server determines that the first comparison result is that the interest type does not contain the trigger type. Similarly, when there is no type in the exposure type which is the same as each type in the trigger type or similar to a certain threshold, the server determines that the second comparison result is that the exposure type does not contain the trigger type.

[0149] It should be noted that in some embodiments of the present application, the interest type and the exposure type can have multiple types, and these types can overlap. Similarly, the trigger type can also have multiple types, and at this time, as long as the trigger type has a type that is not in the exposure type or the interest type, the server will determine that the interest type and the exposure type do not contain the trigger type.

[0150] S1023, when the first comparison result represents that the interest type does not contain the trigger type, or the second comparison result represents that the exposure type does not contain the trigger type, the server determines that the trigger type is the demand type of the target delivery object.

[0151] After the server obtains the first comparison result and the second comparison result, the server analyzes these comparison results. When the server learns that the first comparison result represents that the interest type does not contain the trigger type, or the second comparison result represents that the exposure type does not contain the trigger type, it means that the target delivery object has browsed more information corresponding to the trigger type. In other words, the target delivery object has obvious preference for the trigger type. At this time, the server will directly determine the trigger type as the demand type of the target delivery object, so as to subsequently deliver information corresponding to the trigger type to the target delivery object, so as to maximize the actual reading demand of the target delivery object.

[0152] For example, when the interest type is "cute pets", "TV series", and "finance", the exposure type is "TV series", "finance", and "culture", and the trigger type is "food", the server will determine "food" as the demand type.

[0153] Of course, when the first comparison result represents that the interest type does not contain the trigger type, and the second comparison result represents that the exposure type does not contain the trigger type, the server will also determine the trigger type as the demand type of the target delivery object.

[0154] In the embodiment of the present application, the server can directly determine whether the interest type and the exposure type contain the trigger type, so as to determine that the target delivery object has a trigger preference, but in the type lacking in the interest type and the exposure type, the type is taken as a demand type, so as to select the information to be delivered according to the demand type subsequently, so that the information to be delivered fully meets the interest and demand of the target delivery object, and finally the precision of information delivery is improved.

[0155] Referring to Figure 9 , Figure 9 is an optional flowchart of the information delivery method provided by the embodiment of the present application Figure 3 In some embodiments of the present application, the server determines the demand type of the target delivery object based on the portrait information, the exposure information and the trigger information, that is, the specific implementation process of S102 can include S1024-S1025, as follows:

[0156] S1024, the server determines the demand information of the target delivery object for a current type in each type based on the portrait information, the exposure information and the trigger information; the current type is any one of each type, and the demand information represents whether the target delivery object has a demand for the current type.

[0157] In addition to directly comparing the interest type, the exposure type and the trigger type to determine the demand type, the server can also analyze the portrait information, the exposure information and the trigger information to determine the demand of the target delivery object for each type, so as to select the demand type from each type. At this time, the server can select any one type from each type as the current type, and then determine whether the target delivery object has a demand for the current type by combining the portrait information, the exposure information and the trigger information, that is, determine the demand information of the target delivery object for the current type, so that the server can know the demand of the target delivery object for each type in each type.

[0158] It can be understood that in the embodiment of the present application, the portrait information has an interest weight of the target delivery object for each type, and the interest weight is used to indicate the interest degree of the target delivery object for each type, that is, when the target delivery object is not very interested in a certain type, the interest weight of the type is 0, and when the target delivery object is very interested in a certain type, the interest weight of the type is 1.

[0159] Similarly, in the embodiment of the present application, the exposure information has exposure weights of each type of exposure for the target delivery object, and the trigger information has trigger weights of each type for the target delivery object. In this way, when the server analyzes the portrait information, the exposure information and the trigger information, the interest weights, the exposure weights and the trigger weights of each type corresponding to the target delivery object can be analyzed, so as to determine the demand information of each type for the target delivery object.

[0160] S1025, when the demand information represents that the target delivery object has a demand for the current type, the server determines the current type as a demand type.

[0161] When the server reads the demand information and finds that the demand information represents that the target delivery object has a demand for the current type, the server directly determines the current type as a demand type. Otherwise, when the demand information represents that the target delivery object does not have a demand for the current type, the server does not determine the current type as a demand type, but determines the current type as a non-demand type. In this way, the server can screen the demand types from the types.

[0162] In the embodiment of the present application, the server can also screen the demand types from the types from the perspective of whether the target delivery object has a demand for each type, so as to obtain more accurate demand types and further improve the accuracy of information delivery.

[0163] In some embodiments of the present application, the target delivery object is included in the full quantity object; the server determines the demand information of the target delivery object for the current type in each type based on the portrait information, the exposure information and the trigger information, that is, the specific implementation process of S1024 can include: S401-S405, as follows:

[0164] S401, the server obtains the full quantity portrait information corresponding to the full quantity object from the portrait information library, and obtains the full quantity exposure information corresponding to the full quantity object and the full quantity trigger information corresponding to the full quantity object from the operation information library.

[0165] Since the target delivery object belongs to a part of the full quantity object, if the attention degree of the target delivery object to a certain type is obviously higher than the attention degree of the full quantity object to the type, it means that the target delivery object has a preference for the type, that is, the target delivery object has a higher attention degree to the type. Therefore, the server can also analyze the attention degree of the target delivery object to the current type in combination with the full quantity portrait information of the full quantity object. At this time, the server will first obtain the full quantity portrait information corresponding to the full quantity object.

[0166] Similarly, the server can also analyze whether the current type exposure to the target delivery object is high according to the information presented to the full object, i.e., the full exposure information. At this time, the server will first obtain the full exposure information. Similarly, when the target delivery object has a significantly higher triggering tendency for a certain type than the full object has for the same type, it means that the target delivery object has a strong triggering preference for the type, and it means that the type is the type that the target delivery object really needs and is really interested in. Therefore, the server will also first obtain the triggering of the information of each type by the full object, i.e., obtain the full triggering information of the full object.

[0167] S402, the server constructs type attention information according to the portrait information and the full portrait information; the type attention information represents the attention degree of the target delivery object to the current type.

[0168] After obtaining the full portrait information, the server will calculate the attention degree of the target delivery object to the current type according to the portrait information of the target delivery object and the obtained full portrait information, and take the calculated attention degree as the type attention information.

[0169] It can be understood that, similar to the portrait information, the full portrait information has the interest degree of the full object to each type, and these interest degrees are full interest weights, so the server can use the interest weight in the portrait information and the full interest weight to construct the type attention information.

[0170] For example, when the server constructs the type attention information from the interest weight and the full interest weight, the server can compare the interest weight and the full interest weight, multiply the ratio result by 100, and then determine whether the average of the interest weight is significantly higher than the average of the full interest weight in the current type according to the final calculated value.

[0171] S403, the server generates type exposure information based on the exposure information and the full exposure information; the type exposure information represents the tendency degree of displaying the information of the current type to the target delivery object.

[0172] The server analyzes the exposure information corresponding to the target delivery object and the full exposure information to calculate the tendency degree of displaying the information belonging to the current type to the target delivery object, i.e., the possibility of exposure of the information of the current type, and takes the calculated tendency degree as the type exposure information.

[0173] It can be understood that, in some embodiments of the present application, the full exposure information has the weight of each type exposed to the full object, i.e., the full exposure weight, and the server can use the full exposure weight and the exposure weight to construct the type exposure information.

[0174] S404, the server constructs type trigger information by using the trigger information and the full-amount trigger information; the type trigger information represents a degree of tendency of the target delivery object to trigger the information of the current type.

[0175] Similarly, the server continues to analyze the trigger information and the full-amount trigger information, calculates the trigger tendency of the target delivery object to the information of the current type, and thus obtains the type trigger information corresponding to the current type.

[0176] It can be understood that in the full-amount trigger information, there is a type weight of each type of information triggered by the full-amount object, that is, a full-amount trigger weight. The server can analyze the full-amount trigger weight and the trigger weight to obtain the type trigger information of the target delivery object to the current type.

[0177] S405, the server determines the demand information of the target delivery object to the current type based on the type attention information, the type exposure information and the type trigger information.

[0178] After obtaining the type attention information, the type exposure information and the type trigger information, the server determines whether the target delivery object has a preference for the current type according to the type attention information, that is, whether the current type is a portrait preference, determines the degree of tendency of the information of the current type to be exposed to the target delivery object according to the type exposure information, and determines the degree of tendency of the target delivery object to trigger the information of the current type according to the type trigger information, so as to determine whether the current type is a type that the target delivery object has a trigger preference but lacks exposure tendency and portrait preference. When the current type is a type that the target delivery object has a trigger preference and lacks exposure tendency or portrait preference, the server obtains the demand information that the target delivery object has a demand for the current type.

[0179] In the embodiment of the application, the server can obtain the type attention information of the current type by combining the portrait information and the full-amount portrait information, obtain the type exposure information of the current type by combining the exposure information and the full-amount exposure information, obtain the type trigger information of the current type by combining the trigger information and the full-amount trigger information, and then determine whether the target delivery object has a demand for the current type according to the type attention information, the type exposure information and the type trigger information, so as to obtain the demand type, which is convenient for subsequent screening of the to-be-delivered information according to the demand type.

[0180] In some embodiments of the application, the server determines the demand information of the target delivery object to the current type based on the type attention information, the type exposure information and the type trigger information, that is, the specific implementation process of S405 can include S4051 or S4052, as follows:

[0181] S4051, when the type attention information is less than a preset degree threshold value and the type trigger information is greater than the preset degree threshold value, the server determines that the demand information is that the target delivery object has a demand for the current type.

[0182] When the type attention information is less than the preset degree threshold value, it indicates that the current type is not the portrait preference of the target delivery object, and when the type trigger information is greater than the preset degree threshold value, it indicates that the target delivery object has a trigger preference for the current type. At this time, the server considers that the target delivery object has a demand for the current type, thereby obtaining the demand information.

[0183] It should be noted that in the embodiments of the present application, the preset degree threshold value can be set according to actual conditions, for example, the preset degree threshold value can be set to 100, or the preset degree threshold value can be set to 80, and the embodiments of the present application are not limited herein.

[0184] For example, when the preset degree threshold value is 100, the type attention information is less than the preset degree threshold value, and the type trigger information is greater than the preset degree threshold value, it can be written as: type attention information < 100 && type trigger information > 100.

[0185] S4052, when the type exposure information is less than a preset degree threshold value and the type trigger information is greater than the preset degree threshold value, the server determines that the demand information is that the target delivery object has a demand for the current type.

[0186] When the type exposure information is less than the preset degree threshold value, it indicates that the current type does not have an exposure preference, and when the type trigger information is greater than the preset degree threshold value, it indicates that the target delivery object has a trigger preference for the current type. At this time, the server determines that the demand information is that the target delivery object has a demand for the current type, thereby obtaining the demand information.

[0187] For example, when the preset degree threshold value is 100, the type exposure information is less than the preset degree threshold value, and the type trigger information is greater than the preset degree threshold value, it can be written as: type exposure information < 100 && type trigger information > 100.

[0188] It should be noted that in the embodiments of the present application, the server can also simultaneously use the type attention information, the type exposure information and the type trigger information to determine the demand information of the target delivery object for the current type. At this time, when the type attention information is less than the preset degree threshold value, the type exposure information is less than the preset degree threshold value, and the type trigger information is greater than the preset degree threshold value, the server determines that the target delivery object has a demand for the current type.

[0189] Exemplarily, the above manner of judging whether the target delivery object has a demand for the current type is integrated into a judgment formula (type attention information < 100 || type exposure information < 100) && type trigger information > 100. Through the judgment formula, the server can determine whether the target delivery object has a demand for the current type.

[0190] In the embodiment of the application, the server can determine the demand situation of the target delivery object for the current type according to the relationship between the type attention information, the type exposure information and the type trigger information and the preset degree threshold, so as to determine the demand information.

[0191] In some embodiments of the application, the portrait information includes an interest weight, and the full-amount portrait information includes a full-amount interest weight; the server constructs the type attention information according to the portrait information and the full-amount portrait information. The specific implementation process of S402 can include S4021-S4023, as follows:

[0192] S4021, the server integrates, from the full-amount interest weight, a full-amount attention parameter of the full-amount object for each type and a current attention parameter of the full-amount object for the current type.

[0193] The server adds the interest weight of each object in the full-amount object for each type to obtain the full-amount attention parameter. Then, the server extracts the interest weight of each object in the full-amount object for the current type from the full-amount interest weight, and adds the interest weight of each object in the full-amount object for the current type to obtain the current attention parameter.

[0194] S4022, the server integrates, from the interest weight, a target attention parameter of the target delivery object for each type and a type attention parameter of the target delivery object for the current type.

[0195] The server extracts the interest weight of each object in the target delivery object for the current type from the interest weight of the target delivery object for each type, and adds the interest weight of each object in the target delivery object for the current type to obtain the type attention parameter. Meanwhile, the server adds the interest weight of each object in the target delivery object for each type to obtain the target attention parameter.

[0196] S4023, the server constructs the type attention information of the target delivery object by using the full-amount attention parameter, the current attention parameter, the target attention parameter and the type attention parameter.

[0197] After obtaining the full attention parameter, the current attention parameter, the target attention parameter and the type attention parameter, the server compares the current attention parameter with the full attention parameter, and compares the type attention parameter with the target attention parameter, and then performs a proportional operation by taking the ratio of the type attention parameter and the target attention parameter as the numerator and taking the current attention parameter and the full attention parameter as the denominator to obtain a proportional operation result. Finally, the server multiplies the proportional operation result by a preset value to obtain the type attention information of the target delivery object.

[0198] It can be understood that the preset value can be set to 100, or 50, or other values according to actual needs, which are not limited in the embodiments of the present application.

[0199] For example, the embodiments of the present application provide an expression for calculating the type attention information, as shown in formula (1):

[0200]

[0201] In some embodiments of the present application, the portrait information includes type labels of various types, and each type label corresponds to a type weight; wherein the type weight is obtained by integrating a plurality of temporary type weights obtained from various business platforms.

[0202] It can be understood that the type label in the portrait information is the type name of the interest type, and the type weight corresponding to each type label is the interest weight. In other embodiments of the present application, the portrait information and the full portrait information can be obtained by fusing portraits on a plurality of business platforms, for example, by adding the weights in the portraits of the target delivery object on a plurality of business platforms, so that the portrait information and the full portrait information are more accurate.

[0203] It can be understood that after the portrait fusion, the range of the interest weight and the full interest weight may no longer be between 0-1, at which time the server can normalize the interest weight and the full interest weight. Here, the normalization process is illustrated by taking the normalization of the interest weight of a certain type as an example.

[0204] When normalizing the interest weight of a certain type, the server finds the maximum interest weight and the minimum interest weight from the interest weights of various types. Then, the server subtracts the minimum interest weight from the interest weight of a certain type, and subtracts the minimum interest weight from the maximum interest weight, and then performs a proportional operation by taking the difference between the interest weight of a certain type and the minimum interest weight as the numerator and taking the difference between the maximum interest weight and the minimum interest weight as the denominator, and the result of the proportional operation is the normalized interest weight of the type.

[0205] Exemplarily, the embodiment of the present application provides a calculation manner of the normalized interest weight, refer to formula (2):

[0206]

[0207] wherein, is the interest weight of a certain type, is the minimum interest weight, is the maximum interest weight, is the normalized interest weight of a certain type. When the server obtains the specific value of the above parameters, the specific value of the above parameters can be substituted into formula (2) to calculate the normalized interest weight.

[0208] In the embodiment of the present application, the type attention information calculated by the server can reflect the portrait preference of the target delivery object. Exemplarily, refer to table 1, table 1 shows the portrait preference of different target delivery objects, which is obtained by extracting the types whose type attention information exceeds the attention threshold.

[0209] Table 1

[0210]

[0211] In Table 1, the female, male, 0-17 years old, 30-40 years old, first-tier city and second-tier city are different target delivery objects. Among them, in the female target delivery object, the types whose attention information exceeds the attention threshold value are "** Niang", "high gluten powder", "corn flour", "** Ai", "foundation brush", "pregnancy period", "mask paper", "* Tu" and "* Pian", which are mostly concentrated in cooking and beauty and skin care, which conforms to the portrait preference of women. In the male target delivery object, the types whose attention information exceeds the attention threshold value are "** Ji", "a", "* basket", "** 10", "XX car", "basketball player", "* Ning", "*** Si", "football event", which are mostly concentrated in sports, which conforms to the portrait preference of men. In the 0-17-year-old target delivery object, the types whose attention information exceeds the attention threshold value are "* Lang", "** You have you", "* Ran", "precious **", "** Luo", "** Xiu", "*** treasure", "game war order", "** fish", which are mostly cartoon characters, idols, games and other contents, which conforms to the portrait preference of 0-17-year-old teenagers. In the 30-40-year-old target delivery object, the types whose attention information exceeds the attention threshold value are "** Yi", "Dao Ming", "* vegetable", "** Tian", "** Zhen", "* Feng", "** Ming", "** cured meat" and "** Hong Kong", which are mainly concentrated in some era corresponding to idol dramas, stars, which conforms to the portrait preference of 30-40-year-old users. In the first-tier city target delivery object, the types whose attention information exceeds the attention threshold value are "** District", "** Group", "** University", "self-driving", "** Liang", "** subway", "** Society", "* Li", "temperature measuring instrument", etc., which are mainly concentrated in the urban area, urban transportation and higher education institutions in the first-tier city, which is more in line with the portrait preference of users in the first-tier city. In the second-tier city target delivery object, the types whose attention information exceeds the attention threshold value are "** Square", "** Town", "** Bureau", "** Town", "* Hua", "** District", "* Jia", "* Mi", "* Yin", which are mainly concentrated in some district and county regions, which conforms to the portrait preference of users in the second-tier city. It can be seen that the type attention information can reflect the portrait preference of the target delivery object.

[0212] In the embodiment of the application, the server can construct type attention information capable of representing the target delivery object's attention to the current type according to the interest weight in the portrait information and the total interest weight in the total portrait information, so as to facilitate the server to judge whether the current type is the portrait preference of the target delivery object, so as to facilitate subsequent determination of demand information.

[0213] In some embodiments of the present application, the exposure information includes an exposure weight and an exposure frequency, and the full-amount exposure information includes a full-amount exposure weight and a full-amount exposure frequency; the server generates type exposure information based on the exposure information and the full-amount exposure information, i.e., the specific implementation process of S403 can include: S4031-S4035, as follows:

[0214] S4031, the server multiplies the exposure frequency and the exposure weight to obtain an exposure incremental weight of each type for the target delivery object; wherein the exposure weight represents the weight of the information type exposed to the target delivery object.

[0215] The server extracts the frequency of exposing each type of information to the target delivery object from the exposure information, i.e., extracts the exposure frequency, and then multiplies the exposure frequency and the exposure weight, and the multiplication result is the exposure incremental weight of each type for the target delivery object.

[0216] It should be noted that in the embodiments of the present application, the exposure frequency can refer to the deduplicated exposure frequency, i.e., the same information is exposed to the same object multiple times, but only counts as one exposure. The server can use the deduplicated exposure frequency to calculate the exposure incremental weight.

[0217] For example, when the information of the uterus type is deduplicated and exposed to the target delivery object 3 times, and the weight of the uterus in the information is 0.5, the exposure incremental weight of the uterus type is 1.5.

[0218] S4032, the server integrates the target exposure parameters of each type for the target delivery object and the type exposure parameters of the current type for the target delivery object from the exposure incremental weight.

[0219] Then, the server extracts the exposure weight of each object in the target delivery object for the current type from the exposure incremental weight, and adds the extracted exposure incremental weight of each object in the target delivery object for the current type to obtain the type exposure parameters. At the same time, the server adds the exposure incremental weight of each type for each object in the target delivery object to obtain the target exposure parameters.

[0220] S4033, the server multiplies the full-amount exposure weight and the full-amount exposure frequency to obtain a full-amount exposure incremental weight of each type for the full-amount object; wherein the full-amount exposure weight represents the weight of the information type exposed to the full-amount object.

[0221] Similarly, the server also obtains the exposure times of the information exposed to the full-amount object in each type, i.e., the full-amount exposure times, and the type weight of the information exposed to the full-amount object in each type, i.e., the full-amount exposure weight, from the full-amount exposure information, and then multiplies the full-amount exposure times and the full-amount exposure weight to obtain the full-amount exposure incremental weight.

[0222] The full-amount exposure times can also refer to the deduplicated full-amount exposure times in the incremental weight type, and the server can calculate the full-amount exposure incremental weight by using the deduplicated full-amount exposure times.

[0223] For example, when the information of the palace type is exposed to the target delivery object for 3 times and exposed to other types of objects for 10 times, and the weight of the palace in the information is 0.5, the full-amount exposure incremental weight of the palace type is 0.5(10+3)=6.5.

[0224] S4034, the server integrates the full-amount exposure parameters of the full-amount object for each type and the current exposure parameters of the full-amount object for the current type from the full-amount exposure incremental weight.

[0225] After obtaining the full-amount exposure incremental weight, the server extracts the incremental exposure weight of each object in the full-amount object for the current type, adds the extracted exposure weight of each object for the current type, and obtains the current exposure parameter. Meanwhile, the server adds the exposure incremental weight of each object for each type, and obtains the full-amount exposure parameter.

[0226] S4035, the server constructs the type exposure information of the target delivery object by using the target exposure parameter, the type exposure parameter, the full-amount exposure parameter and the current exposure parameter.

[0227] The server compares the type exposure parameter with the target exposure parameter, compares the current exposure parameter with the full-amount exposure parameter, then takes the ratio of the type exposure parameter to the target exposure parameter as the numerator, takes the ratio of the current exposure parameter to the full-amount exposure parameter as the denominator, and performs proportional operation, and the obtained result is the type exposure information.

[0228] In the embodiment of the application, the server can calculate the exposure incremental weight according to the exposure weight and the exposure times, integrate the target exposure parameter and the type exposure parameter from the exposure incremental weight, calculate the full-amount exposure incremental weight according to the full-amount exposure weight and the full-amount exposure times, integrate the full-amount exposure parameter and the current exposure parameter from the full-amount exposure incremental weight, and finally construct the type exposure information by using the target exposure parameter, the type exposure parameter, the full-amount exposure parameter and the current exposure parameter, so as to facilitate subsequent determination of the demand information by using the type exposure information.

[0229] In some embodiments of the present application, the trigger information includes a trigger weight and a trigger number, and the full trigger information includes a full trigger weight and a full trigger number; the server uses the trigger information and the full trigger information to construct type trigger information, i.e., the specific implementation process of S404 can include S4041-S4045, as follows:

[0230] S4041, the server multiplies the trigger number and the trigger weight to obtain a trigger increment weight of each type for the target delivery object; wherein the trigger weight represents the weight of the information type triggered by the target delivery object.

[0231] S4042, the server integrates a target trigger parameter of each type for the target delivery object and a type trigger parameter of the current type for the target delivery object from the trigger increment weight.

[0232] S4043, the server multiplies the full trigger weight and the full trigger number to obtain a full trigger increment weight of each type for the full object; wherein the full trigger weight represents the weight of the information type triggered by the full object.

[0233] S4044, the server integrates a full trigger parameter of each type for the full object and a current trigger parameter of the current type for the full object from the full trigger increment weight.

[0234] S3035, the server uses the target trigger parameter, the type trigger parameter, the full trigger parameter, and the current trigger parameter to construct a type trigger parameter of the target delivery object.

[0235] Similar to the calculation of the type exposure information, the server first extracts the number of times that the target delivery object triggers information of each type from the trigger information, i.e., extracts the trigger number, and then multiplies the trigger number and the trigger weight to obtain the trigger increment weight. The server also obtains the number of times that the full object triggers information of each type from the full trigger information, i.e., the full trigger number, and the type weight of the information of each type triggered by the full object, i.e., the full trigger weight, and then multiplies the full trigger number and the full trigger weight to obtain the full trigger increment weight. Then, the server obtains the target trigger parameter and the type trigger parameter from the trigger increment weight, obtains the full trigger parameter and the current trigger parameter from the full trigger increment weight, and finally uses the ratio of the type trigger parameter to the target trigger parameter as the numerator and the ratio of the full trigger parameter to the current trigger parameter as the denominator to obtain the type trigger parameter that can describe whether the target delivery object has a trigger preference for the current type.

[0236] It can be understood that the triggering times can be deduplicated triggering times, that is, one object triggers the same information multiple times, and only one triggering is counted, and correspondingly, the full quantity triggering times can also be deduplicated full quantity triggering times.

[0237] In the embodiment of the application, the server can calculate the triggering increment weight according to the triggering weight and the triggering times, count the target triggering parameter and the type triggering parameter from the triggering increment weight, then calculate the full quantity triggering increment weight according to the full quantity triggering weight and the full quantity triggering times, count the full quantity triggering parameter and the current triggering parameter from the full quantity increment weight, and finally construct the type triggering information by using the target triggering parameter, the type triggering parameter, the full quantity triggering parameter and the current triggering parameter, so as to facilitate subsequent determination of the demand information by using the type triggering information.

[0238] Referring to Figure 10 , Figure 10 is an optional flowchart of the information delivery method provided by the embodiment of the application Figure 4 In some embodiments of the application, after the server determines the demand type of the target delivery object based on the portrait information, the exposure information and the triggering information, before the server sends the information to be delivered to the terminal corresponding to the target delivery object, that is, after S102 and before S104, the method can further include: S107-S109, as follows.

[0239] S107, the server acquires the historical push type for the target delivery object; the historical push type represents the type of information pushed to the target delivery object at a historical time.

[0240] S108, the server matches the historical push type and the demand type to obtain a matching result; the matching result represents whether the historical push type and the demand type match.

[0241] The server can acquire the historical push record for the target delivery object from the database, and the historical push record records the type of information pushed to the target delivery object, that is, the historical push type. The server extracts the historical push type, and then matches the historical push type with the determined demand type to judge whether the historical push type and the demand type are the same or whether the similarity degree reaches a certain threshold. When the historical push type and the demand type are the same or the similarity degree reaches a certain threshold, it is indicated that the historical push type and the demand type are matched. Conversely, when the historical push type and the demand type are not the same or the similarity degree is lower than a certain threshold, it is indicated that the historical push type and the demand type are not matched.

[0242] It can be understood that the server can convert the historical push type and the demand type into vectors, and then calculate the similarity degree of the vectors to judge whether the historical push type and the demand type are matched.

[0243] For example, for the two types of "*gong" and "**yuan", the server can convert both to 200-dimensional vectors using the tag2vector algorithm, e.g., converting "*gong" to [-0.056396, -0.090522, 0.935096, 0.065242, 0.843557, -0.254964, 0.359682, 0.037870, 0.296060, 0.276016, -0.026777, 0.066378, 0.182684, 0.095527, -0.010487, -0.080757, 0.200389, -0.047565, -0.521742, 0.287354, -0.358958, -0.164368, 0.034278, -0.453018, -0.270229, -0.340655, -0.016789, 0.147458, -0.271454, -0.319662, -0.396275, 0.128608, -0.072506, 0.591916, 0.396722, 0.151030, 0.687118, -0.207247, -0.172028, 0.047510, -0.091599, -0.069702, 0.480043, -0.060705, -0.023457, -0.308404, -0.042078, -0.570606, -0.148631, -0.030760, -0.687672, 0.082423, -0.787128, 0.227140, -0.062624, -0.217884, 0.026550, 0.369715, -0.024367, 0.744774, 0.366842, 0.599170, 0.516692, 0.203593, 0.047066, -0.248923, -0.293685, 0.528148, 0.284010, 0.423223, 0.040066, -0.210593, -0.015255, 0.777359, 0.334364, 0.179796, 0.156300, -0.311745, 0.018399, 0.036197, -0.830084, 0.085114, -0.271454, 0.439693, 0.513554, 0.357657, -0.814202, 0.089058, -0.104654, -0.464062, 0.240746, -0.113030, 0.183249, -0.121620, -0.334511, -0.327671, 0.134638, -0.301083,-0.316633,0.191562,0.114542,-0.123954,0.470130,0.342641,0.281651,0.376080,-0.037122,-0.457659,0.153041,0.091499,0.226399,0.478591,0.189378,-0.224102,0.006822,0.421877,0.131060,-0.230536,0.326092,-0.317272,0.183482,-0.352424,0.191719,0.595564,0.081384,-0.431508,-0.262803,0.342979,-0.077924,-0.292611,0.238173,0.189595,0.181602,0.179831,-0.506251,-0.975739,-0.061049,-0.253532,0.220305,-0.093731,-0.344974,0.167344,-0.252789,-0.272433,0.039740,-0.018445,-0.139393,-0.204477,-0.461104,0.129840,-0.262299,-0.268836,0.098430,0.165803,-0.235626,-0.514308,0.271131,0.376837,-0.138041,0.310985,0.334784,-0.341090,-0.465053,0.711370,0.023144,-0.584616,-0.296981,0.045378,0.509104,-0.489406,-0.254868,0.240608,0.419868,0.089674,-0.152399,0.420049,-0.077940,-0.146168,-0.225541,0.013036,-0.199241,-0.134627,0.410482,0.053290,0.584829,-0.060490,-0.350765,0.580098,-0.076310,-0.226178,0.381528,0.480653,0.080260,0.435836,0.590955,1.164203,0.038419,-0.566581,0.343651,0.063802]。.

[0244] The server can use the cosine value of the included angle between the vector corresponding to the historical push type and the vector corresponding to the demand type as the similarity between the two vectors. At this time, the server first calculates the inner product of the two vectors, and then respectively takes the modulus of the two vectors, takes the product of the modulus of the two vectors as the denominator, and takes the inner product as the numerator to calculate the cosine value of the included angle between the two vectors.

[0245] For example, the embodiment of the present application provides a formula for calculating the similarity between the vector corresponding to the historical push type and the vector corresponding to the demand type, as shown in formula (3):

[0246]

[0247] Where b and c are two vectors, and A is the included angle between the two vectors. After the server obtains the specific values of the above parameters, the specific values of the above parameters can be substituted into formula (3) to calculate the similarity between the vector corresponding to the historical push type and the vector corresponding to the demand type.

[0248] In the embodiment of the present application, after the server obtains the cosine value of the included angle between the vector corresponding to the historical push type and the vector corresponding to the demand type, the cosine value can be compared with a preset cosine value. When the cosine value is greater than the preset cosine value, it indicates that the historical push type and the demand type match.

[0249] It can be understood that in the embodiment of the present application, the preset cosine value can be set to 0.5, or 0.7, or other values, which are not limited in the embodiment of the present application.

[0250] S109, when the matching result indicates that the historical push type and the demand type do not match, the server uses the demand type to match the to-be-launched information from the information set.

[0251] Since the historical push type is the type of information that has been pushed to the target launching object, if the server finds the to-be-launched information according to the demand type similar to the historical push type and launches the to-be-launched information to the target launching object, it may cause the target launching object to have an aversion to the information of the demand type that has been excessively exposed. Therefore, in the embodiment of the present application, when the server finds that the historical push type and the demand type do not match, the to-be-launched information matching the demand type is searched from the information set. In this way, the to-be-launched information is different from the type of the information that has been pushed, thereby avoiding launching the information of the type that has been excessively exposed to the target launching object.

[0252] For example, when the server is based on the judgment formula (type attention information < 100 || type exposure information < 100) && type trigger information > 100 to find the demand type, in the embodiment of the application, the judgment formula can be changed to (type attention information < 100 || type exposure information < 100) && type trigger information > 100 && the demand type is not overexposed.

[0253] In the embodiment of the application, the server can match the demand type and the historical push type to determine whether the demand type is overexposed, and only when the demand type is not overexposed, the server finds the information to be pushed according to the demand type, thereby avoiding pushing the information of the overexposed type to the target push object, and further improving the accuracy of information pushing.

[0254] In some embodiments of the application, the portrait information includes an interest weight, the exposure information includes an exposure weight and an exposure frequency, and the trigger information includes a trigger weight and a trigger frequency; after the server determines the demand type of the target push object based on the portrait information, the exposure information, and the trigger information, and before the server sends the information to be pushed to the terminal corresponding to the target push object, that is, after S102 and before S104, the method can further include S110-S114 as follows:

[0255] S110, the server calculates the interest proportion of the demand type in the target push object according to the interest weight.

[0256] After obtaining the demand type, the server also needs to evaluate the push return index corresponding to the demand type to determine whether the information pushing effect is good. At this time, the server will calculate the sum of the weights corresponding to the demand type and the sum of the weights of each type according to the interest weight of the target push object for each type, and then compare the sum of the weights corresponding to the demand type with the sum of the weights of each type to obtain the interest proportion.

[0257] S111, the server multiplies the exposure frequency and the exposure weight to obtain the exposure weight parameter of the demand type, and multiplies the trigger frequency and the trigger weight to obtain the trigger weight parameter of the demand type.

[0258] Next, the server selects the demand exposure frequency and the demand exposure weight corresponding to the demand type from the exposure frequency and the exposure weight, and then multiplies the demand exposure frequency and the demand exposure weight to obtain the exposure weight parameter corresponding to the demand type for the target push object. Similarly, the server determines the demand trigger frequency and the demand trigger weight from the trigger frequency and the trigger weight, and then multiplies the demand trigger frequency and the demand trigger weight to obtain the trigger weight parameter corresponding to the demand type for the target push object.

[0259] S112, the server counts the number of objects of the target delivery object, and obtains a delivery object number.

[0260] S113, the server predicts a delivery return index corresponding to the demand type by using the delivery object number, the interest proportion, an exposure weight parameter, and a trigger weight parameter.

[0261] The server counts the total number of objects contained in the target delivery object, and obtains a delivery object number. Then, the server constructs a delivery return index corresponding to the demand type by using the delivery object number, the interest proportion, an exposure weight, and a trigger weight parameter. In this way, the server can judge the delivery effect of the demand type.

[0262] S114, when the delivery return index exceeds a preset index threshold, the server matches to-be-delivered information from a preset information set according to the demand type.

[0263] The server compares the delivery return index with the preset index threshold. When the delivery return index exceeds the preset index threshold, it indicates that the delivery return index is high enough. At this time, the server finds to-be-delivered information matched with the demand type from the preset information set, and delivers the to-be-delivered information to the terminal of the target delivery object. In this way, the delivery effect of information delivery can be ensured to be at a high level when the information is delivered.

[0264] Further, in order to prevent the delivery return index of the target delivery object in the demand type from being affected by the number of objects when compared with the delivery return index corresponding to other types of other delivery objects, the server can also unitize the delivery return index, and obtain a unit return index.

[0265] For example, the embodiment of the present application provides a delivery return index and a unit return index when five different target delivery objects are delivered with corresponding demand types, as shown in Table 2.

[0266] Table 2

[0267]

[0268] Assuming the preset index threshold is 50, in Table 2, for the target delivery object of medium activity, located in a new-line city, male, aged 18-29 years old, the number of delivery objects is 26743, and the demand type is all stamp; in the target delivery object, the type attention parameter of the stamp is 103, the type exposure parameter is 0.02, the type trigger parameter is 294, the number of to-be-delivered information related to the stamp is 120, the calculated delivery return index is 159, the calculated unit return index is 0.60%, the delivery return index is higher, and the delivery effect is better. For the target delivery object of low activity, located in a new-line city, female, aged 30-40 years old, the number of delivery objects is 18712, and the demand type is all small *; the type attention parameter of the type is 129, the type exposure parameter is 0.5, the type trigger parameter is 373, the number of to-be-delivered information related to the small * is 53, the delivery return index is 104, the unit return index is 0.56%, and the delivery effect of the small * type is better. For the target delivery object of low activity, located in a first-line city, male, aged 18-29 years old, the number of delivery objects is 13059, and the demand type is all college life; the type attention parameter of the type is 139, the type exposure parameter is 1, the type trigger parameter is 166, the number of to-be-delivered information related to college life is 82, the delivery return index is 68, the unit return index is 0.52%, and the delivery effect of the college life type is also better. For the target delivery object of low activity, located in an unknown city, male, aged 18-29 years old, the number of delivery objects is 16631, and the demand type is all back to the past; the type attention parameter of the type is 115, the type exposure parameter is 2, the type trigger parameter is 286, the number of to-be-delivered information related to back to the past is 32, the delivery return index is 60, the unit return index is 0.36%, and it is indicated that the delivery effect of the back to the past type is also better. For the target delivery object of low activity, located in a second-line city, male, aged 30-40 years old, the number of delivery objects is 19142, and the demand type is all small *; the type attention parameter of the type is 59, the type exposure parameter is 1, the type trigger parameter is 5362, the number of to-be-delivered information related to small * is 32, the delivery return index is 24, the unit return index is 0.12%, and it is indicated that the delivery effect of small * is not very ideal. In summary, the server can preferentially deliver the demand type with a higher delivery return index during information delivery, so as to save information delivery resources.

[0269] In the embodiment of the application, the server can predict the delivery return index of the demand type, and then preferentially deliver the demand type with a higher delivery return index during information delivery, so that the effect of information delivery always remains at a high level.

[0270] In some embodiments of the present application, the server predicts the delivery return index corresponding to the demand type by using the number of delivery objects, the interest proportion, the exposure weight parameter and the trigger weight parameter, and the specific implementation process of S113 can include: S1131-S1132, as follows:

[0271] In S1131, the server constructs the trigger exposure proportion by using the exposure weight parameter and the trigger weight parameter.

[0272] In S1132, the server multiplies the number of delivery objects, the interest proportion and the trigger exposure proportion to obtain the delivery return index.

[0273] The server first performs a ratio operation on the trigger weight parameter and the exposure weight parameter, and takes the ratio operation result as the trigger exposure proportion, and then multiplies the number of delivery objects, the interest proportion and the trigger exposure proportion to construct the delivery return index corresponding to the demand type for the target delivery object.

[0274] For example, the present embodiment provides a formula for calculating the delivery return index, as shown in formula (4):

[0275]

[0276] Wherein, N is the number of delivery objects, A is the sum of weights corresponding to the demand type, B is the sum of weights of each type, C is the trigger weight parameter, E is the exposure weight parameter, and I is the delivery return index. After obtaining the specific values of the above parameters, the server can substitute the specific values of the above parameters into formula (4) to calculate the delivery return index.

[0277] At this time, the server divides the delivery return index by the number of delivery objects to obtain the unit return index.

[0278] For example, the present embodiment provides a method for calculating the unit return index, as shown in formula (5):

[0279]

[0280] Wherein, I is the delivery return index, N is the number of delivery objects, and ROI is the unitized return index. After obtaining the specific values of the above parameters, the server can substitute the specific values of the above parameters into formula (5) to calculate the unit return index.

[0281] In the present embodiment, the server can calculate the trigger exposure proportion by using the exposure weight parameter and the trigger weight parameter, and then calculate the delivery return index by using the number of delivery objects, the interest proportion and the trigger exposure proportion. In this way, the server can calculate the delivery return index, so as to evaluate the effect of information delivery.

[0282] In some embodiments of the present application, before the server acquires the portrait information, exposure information and trigger information of the target delivery object, i.e., before S101, the method can further include: S201-S202, as follows:

[0283] S201, the server classifies all objects according to a preset category attribute to obtain at least one delivery object.

[0284] S202, the server selects any one of the at least one delivery object as the target delivery object.

[0285] Before the server starts information delivery for the target delivery object, the target delivery object needs to be selected first. At this time, the server will first acquire all objects stored in the database, and then divide the all objects into at least one delivery object according to a preset category attribute. Then, the server selects any one of the at least one delivery object as the target delivery object. In this way, the server can know which of the all objects is the target delivery object, which facilitates the subsequent information delivery process for the target delivery object.

[0286] It can be understood that the preset category attribute includes entity attributes used for classifying objects, such as gender, age, city level, activity, etc. Of course, the preset category attribute can also include other entity attributes, which are not limited in the embodiments of the present application.

[0287] In the embodiments of the present application, the server can classify all objects, so as to extract a type of objects with commonality from the all objects as the target delivery object, so as to facilitate the subsequent information delivery for the target delivery object.

[0288] In some embodiments of the present application, after the server matches the to-be-delivered information from the preset information set by using the demand type, before the server sends the to-be-delivered information to the terminal of the target delivery object, i.e., after S103 and before S104, the method can further include: S203, as follows:

[0289] S203, the server acquires the to-be-pushed information for the target delivery object.

[0290] The server can further obtain the to-be-pushed information determined by the pushing system for the target push object after obtaining the to-be-placed information. Then, the process of the server sending the to-be-placed information to the terminal corresponding to the target push object, i.e., the process of S104, will be changed to S1041: the server sends the to-be-pushed information and the to-be-placed information to the terminal corresponding to the target push object. Correspondingly, the terminal receives the to-be-placed information and the to-be-pushed information sent by the server, fills the to-be-placed information and the to-be-pushed information into at least one information display sub-region included in the information stream region according to a preset order, obtains a display information stream, and then presents the display information stream on the display interface, thereby realizing information placement. In this way, the to-be-placed information can be placed between the to-be-pushed information, so as to increase the diversity of information placement modes.

[0291] Exemplarily, the embodiment of the present application provides a display information stream Figure 2 , refer to Figure 11 , a display information stream 11-11 is presented on the display interface 11-1. In the display information stream 11-11, there are three information, which are information 11-12, information 11-13 and information 11-14. Among them, the information 11-13 is the to-be-placed information determined by the server, and the information 11-12 and the information 11-14 are both to-be-pushed information.

[0292] In the embodiment of the present application, the to-be-placed information can be inserted in the to-be-pushed information to realize information placement, thereby increasing the diversity of information placement modes.

[0293] In some embodiments of the present application, after the terminal presents the display information stream on the display interface to realize information placement, i.e., after S106, the method can further include: S204, as follows:

[0294] S204, when the terminal obtains an information viewing instruction on the information display sub-region, the display interface is covered by an information detail page corresponding to the to-be-placed information; the information detail page is used to show the detail content of the to-be-placed information.

[0295] After the to-be-placed information is placed, if the target push object has an information viewing demand for the to-be-placed information, the target push object will trigger an information viewing instruction on the information display sub-region by clicking or the like. At this time, the terminal will obtain the information viewing instruction on the information display sub-region, then generate and render an information detail page corresponding to the to-be-placed information, and cover the display interface with the information detail page, so as to realize jumping from the display information stream to the detail content of the to-be-placed information.

[0296] In the embodiment of the present application, after the information is put, the terminal can also jump to the information detail page according to the operation of the target object, so that the target object can obtain the detail content corresponding to the to-be-put information from the information detail page.

[0297] In the following, an exemplary application of the embodiment of the present application in an actual application scenario will be described.

[0298] The embodiment of the present application is implemented in the scenario of information putting to a specified group in the highlight function of social software. In a rational state, the preferences of a specified group (target object) in user portrait (portrait information), content exposure (exposure information) and click exposure (trigger information) should be consistent. For example, 00s prefer "animation" type, so 00s should have a stronger preference for "animation" than all users in user portrait, for example, have a higher TGI value, etc. At the same time, the content label distribution exposed to 00s by the information stream should be more biased towards "animation", and the content label distribution clicked by 00s should also be more biased towards "animation". However, in reality, a specified group has obvious click preference (click type) on some content labels, but the corresponding user portrait lacks content labels (interest type does not have click type), and content exposure also lacks content labels (exposure type does not have click type). At this time, the server can find the content labels that have strong click preference but lack user portrait and content exposure (i.e. find the demand type), and then find the corresponding content for targeted putting to a specified group.

[0299] Before putting, the users (full amount objects) can be divided into multiple groups (at least one target object) according to four dimensions (preset category attributes) of gender, age, city level and activity. Among them, gender has three categories: male, female and unknown; age has six categories: 0-17 years old, 18-29 years old, 30-40 years old, 41-50 years old, 51+ years old and unknown; city level has six categories: new first-tier city, first-tier city, second-tier city, third-tier city, fourth-tier city and fifth-tier city; activity has four categories: not active (access 0 days within a week), low active (access 1 day within a week), medium active (access 2-4 days within a week) and high active (access 5-7 days within a week). According to the above categories, the server can divide the users into 1119 groups.

[0300] The server fuses (fuses the image information of multiple business platforms) the images of multiple businesses such as highlight image, highlight video image, browser information flow image and flash report image for a specified group of people, so that the user image data is more accurate. The server normalizes the label weight (interest weight) in the user image to 0-1, then associates according to the content label, and takes the average value of the label weight. Then, the server aggregates the content label and label weight of the user according to the people, obtains the comprehensive image (image information) of a specified group of people, and then can calculate the comprehensive image TGI (type attention parameter) of a specified group of people, and the calculation method is as formula (6):

[0301]

[0302] All people are full objects.

[0303] The server calculates the exposure image TGI (type exposure parameter) of the exposed content of a user according to the principle that a user exposes a piece of content multiple times and only counts once according to the people. For example, the label of a piece of content is (content label=* palace, label weight=0.5; content label=** hospital, label weight=0.2), and the article is exposed to a specified group of people, such as A group, 3 times (exposure times) without duplication, and to other groups, such as B group, 10 times (the total exposure times of A group and B group are the full exposure times) without duplication, then the exposure image of A group increases (content label=* palace, label weight=1.5; content label=** hospital, label weight=0.6) (exposure increment weight), and the exposure image of B group increases (content label=* palace, label weight=5; content label=** hospital, label weight=2) (the exposure image increase of A group is integrated with the exposure image increase of B group, that is, the full exposure increment weight). In this way, the server can obtain the total exposure image of each group, and then calculate the exposure TGI according to formula (6).

[0304] Similarly, the server calculates the click TGI (type trigger parameter) of the clicked content of a user according to the principle that a user clicks a piece of content multiple times and only counts once according to the people, and the calculation method is similar to the exposure TGI.

[0305] The server determines the delivery strategy (demand type) for a specified group of people according to the judgment formula < (comprehensive image TGI <100|| exposure TGI <100) && click TGI >100 && similar label is not overexposed >, for example, for a group of 40481638 users with click preferences: two, reply, children, strange stories, interesting stories, and connotation clips, and a group of inactive users, the server delivers “funny” content.

[0306] When the server determines that the similar label is not overexposed, the similarity of the two content labels is used to determine that the two content labels with a similarity greater than a certain degree are regarded as one content label, so as to not give a certain group of people the content of the overexposed label. For example, for a group of people consisting of 44204 males with low activity in a fifth-tier city, the server can analyze that the click preference is the content label "XX mother ship", that is, for the "XX ship" label, the integrated portrait TGI = 49, the exposure TGI = 44, and the click TGI = 418. At this time, the server should push the content of the "XX ship" type (demand type) to the group of people, but similar content labels such as "XX ship" (historical push type) have been pushed to the group of people. Therefore, when information is pushed to the group of people, the content of the "XX ship" type is excluded.

[0307] The server also calculates the revenue for information pushing, and the calculation method is as shown in formula (7):

[0308]

[0309] Next, the revenue distribution of different types of objects in the information pushing method provided by the embodiment of the application will be introduced.

[0310] Figure 12 The revenue distribution of objects with different activity levels provided by the embodiment of the application is shown in the schematic diagram. The revenue proportion of low-activity objects is 2.7%, the revenue proportion of medium-activity objects is 2.1%, and the revenue proportion of inactive objects is 94.3%. It is shown that the information pushing method provided by the embodiment of the application can significantly improve the information pushing effect for inactive objects. Figure 13 The revenue distribution of objects with different genders provided by the embodiment of the application is shown in the schematic diagram. The revenue distribution of male objects is 48.4%, the revenue distribution of female objects is 35.6%, and the revenue distribution of unknown gender objects is 16.0%. It is shown that the information pushing method provided by the embodiment of the application can make the revenue distribution of male objects and female objects more uniform, that is, the male objects and the female objects can both bring better pushing effect. Figure 14 The revenue distribution of objects with different ages provided by the embodiment of the application is shown in the schematic diagram. The revenue proportion of objects aged 0-17 is 8.6%, the revenue proportion of objects aged 18-29 is 30.2%, the revenue proportion of objects aged 30-40 is 29.1%, the revenue proportion of objects aged 41-50 is 9.1%, the revenue proportion of objects aged 51+ is 1.8%, and the revenue proportion of objects with unknown age is 21.2%. It is shown that the information pushing method provided by the embodiment of the application has better pushing effect in each age group, especially in the age groups of 18-29 and 30-40. Figure 15The income distribution diagram of objects in different cities provided by the embodiment of the present application is shown in the figure. The income proportion of a new first-tier city is 16.1%, the income proportion of a first-tier city is 11.8%, the income proportion of a second-tier city is 16.4%, the income proportion of a third-tier city is 16.8%, the income proportion of a fourth-tier city is 19.1%, and the income proportion of a fifth-tier city is 19.8%. It is shown that the information delivery method provided by the embodiment of the present application can bring good delivery effect for users in cities of various levels.

[0311] As known from the above, when delivering information, the server can first analyze the unmet needs of the crowd from the inconsistency of the user portrait, exposure content and click preference, then find content for delivery according to the needs, and prevent overexposure of the needs content when delivering, to realize accurate delivery.

[0312] The following continues to illustrate the exemplary structure of the information delivery device 255 provided by the embodiment of the present application as an example of a software module. In some embodiments, as shown in Figure 3 The software module stored in the information delivery device 255 of the first memory 250 can include:

[0313] The acquisition module 2551 is configured to acquire portrait information, exposure information and trigger information of a target delivery object. The portrait information describes the interest of the target delivery object, the exposure information represents information displayed to the target delivery object, and the trigger information represents information triggered by the target delivery object.

[0314] The demand determination module 2552 is configured to determine the demand type of the target delivery object based on the portrait information, the exposure information and the trigger information. The demand type represents the information type required by the target delivery object.

[0315] The information matching module 2553 is configured to match the to-be-delivered information from a preset information set by using the demand type. The to-be-delivered information represents information waiting to be delivered to the target delivery object.

[0316] The sending module 2554 is configured to send the to-be-delivered information to a terminal corresponding to the target delivery object.

[0317] In some embodiments of the present application, the portrait information includes an interest type, the exposure information includes an exposure type, and the trigger information includes a trigger type; the demand determining module 2552 is specifically configured to compare the interest type with the trigger type to obtain a first comparison result, wherein the first comparison result represents whether the trigger type is contained in the interest type; compare the exposure type with the trigger type to obtain a second comparison result, wherein the second comparison result represents whether the trigger type is contained in the exposure type; and determine the trigger type as the demand type of the target delivery object when the first comparison result represents that the trigger type is not contained in the interest type or the second comparison result represents that the trigger type is not contained in the exposure type.

[0318] In some embodiments of the present application, the demand determining module 2552 is specifically configured to determine demand information of the target delivery object for a current type in each type based on the portrait information, the exposure information and the trigger information, wherein the current type is any one of the each type, the demand information represents whether the target delivery object has demand for the current type, and the current type is determined as the demand type when the demand information represents that the target delivery object has demand for the current type.

[0319] In some embodiments of the present application, the target delivery object is contained in a full amount object; the demand determining module 2552 is specifically configured to obtain full amount portrait information corresponding to the full amount object from a portrait information library, obtain full amount exposure information corresponding to the full amount object and full amount trigger information corresponding to the full amount object from an operation information library, construct the type attention information according to the portrait information and the full amount portrait information, wherein the type attention information represents a degree of attention of the target delivery object to the current type, generate the type exposure information based on the exposure information and the full amount exposure information, wherein the type exposure information represents a degree of tendency of displaying information of the current type to the target delivery object, construct the type trigger information using the trigger information and the full amount trigger information, wherein the type trigger information represents a degree of tendency of triggering information of the current type by the target delivery object, and determine the demand information of the target delivery object to the current type based on the type attention information, the type exposure information and the type trigger information.

[0320] In some embodiments of the present application, the demand determining module 2552 is specifically configured to determine that the demand information represents that the target delivery object has demand for the current type when the type attention information is less than a preset degree threshold and the type trigger information is greater than the preset degree threshold; or,

[0321] When the type exposure information is less than the preset degree threshold, and the type trigger information is greater than the preset degree threshold, it is determined that the demand information is that the target delivery object has a demand for the current type.

[0322] In some embodiments of the present application, the demand determining module 2552, the portrait information includes an interest weight, and the full-amount portrait information includes a full-amount interest weight; specifically used for integrating a full-amount attention parameter of the full-amount object for each type and a current attention parameter of the full-amount object for the current type from the full-amount interest weight; integrating a target attention parameter of the target delivery object for each type and a type attention parameter of the target delivery object for the current type from the interest weight; and constructing the type attention information of the target delivery object by using the full-amount attention parameter, the current attention parameter, the target attention parameter, and the type attention parameter.

[0323] In some embodiments of the present application, the exposure information includes an exposure weight and an exposure frequency, and the full-amount exposure information includes a full-amount exposure weight and a full-amount exposure frequency; the demand determining module 2552 is specifically used for multiplying the exposure frequency and the exposure weight to obtain an exposure incremental weight of the target delivery object for each type; wherein the exposure weight represents a weight of an information type exposed to the target delivery object; integrating a target exposure parameter of the target delivery object for each type and a type exposure parameter of the target delivery object for the current type from the exposure incremental weight; multiplying the full-amount exposure weight and the full-amount exposure frequency to obtain a full-amount exposure incremental weight of the full-amount object for each type; wherein the full-amount exposure weight represents a weight of an information type exposed to the full-amount object; integrating a full-amount exposure parameter of the full-amount object for each type and a current exposure parameter of the full-amount object for the current type from the full-amount exposure incremental weight; and constructing the type exposure information of the target delivery object by using the target exposure parameter, the type exposure parameter, the full-amount exposure parameter, and the current exposure parameter.

[0324] In some embodiments of the application, the trigger information includes the trigger weight and the trigger times, and the full-amount trigger information includes full-amount trigger weight and full-amount trigger times; the demand determination module 2552 is specifically configured to multiply the trigger times and the trigger weight to obtain the target triggering parameter of the target delivery object for each type of trigger; wherein the trigger weight represents the weight of the information type triggered by the target delivery object; from the trigger increment weight, the target triggering parameter of the target delivery object for each type of target is integrated, and the type trigger parameter of the target delivery object for the current type; the full-amount trigger weight and the full-amount trigger times are multiplied to obtain the full-amount trigger increment weight of the full-amount object for each type; wherein the full-amount trigger weight represents the weight of the information type triggered by the full-amount object; from the full-amount trigger increment weight, the full-amount trigger parameter of the full-amount object for each type is integrated, and the current trigger parameter of the full-amount object for the current type; the target trigger parameter, the type trigger parameter, the full-amount trigger parameter and the current trigger parameter are used to construct the type trigger parameter of the target delivery object.

[0325] In some embodiments of the application, the information delivery device 255 further comprises a type matching module 2555.

[0326] The type matching module 2555 is configured to obtain a historical push type for the target delivery object; the historical push type represents the type of information pushed to the target delivery object at a historical time; the historical push type and the demand type are matched to obtain a matching result; the matching result represents whether the historical push type and the demand type match.

[0327] The information matching module 2553 is further configured to match the demand type from the to-be-delivered information set when the matching result represents that the historical push type and the demand type do not match.

[0328] In some embodiments of the application, the portrait information includes interest weight, the exposure information includes exposure weight and exposure times, and the trigger information includes trigger weight and trigger times; the information delivery device 255 further comprises an index prediction module 2556.

[0329] The index prediction module 2556 is configured to: according to the interest weight, count an interest proportion of the demand type in the target delivery object; multiply the exposure times and the exposure weight to obtain an exposure weight parameter of the demand type, and multiply the trigger times and the trigger weight to obtain a trigger weight parameter of the demand type; count a number of the target delivery object to obtain a delivery object number; and according to the delivery object number, the interest proportion, the exposure weight parameter and the trigger weight parameter, predict a delivery return index corresponding to the demand type.

[0330] The information matching module 2553 is further configured to: when the delivery return index exceeds a preset index threshold, match the to-be-delivered information from the preset information set according to the demand type.

[0331] In some embodiments of the present application, the index prediction module 2556 is specifically configured to: construct a trigger exposure proportion according to the exposure weight parameter and the trigger weight parameter; and multiply the delivery object number, the interest proportion and the trigger exposure proportion to obtain the delivery return index.

[0332] In some embodiments of the present application, the information delivery device 255 further comprises an object classification module 2557.

[0333] The object classification module 2557 is configured to: classify all objects according to a preset category attribute to obtain at least one delivery object; and select any one of the at least one delivery object as the target delivery object.

[0334] In some embodiments of the present application, the obtaining module 2551 is further configured to obtain to-be-pushed information for the target delivery object.

[0335] Correspondingly, the sending module 2554 is further configured to send the to-be-pushed information and the to-be-delivered information to the terminal of the target delivery object.

[0336] The following continues to explain an exemplary structure of the information presentation device 455 provided by the embodiments of the present application as a software module. In some embodiments, as shown in Figure 4 The software module stored in the information presentation device 455 of the second memory 450 can include:

[0337] The receiving module 4551 is configured to receive the to-be-delivered information sent by the server.

[0338] The information processing module 4552 is configured to fill the to-be-launched information into an information display sub-area of an information flow area to obtain a display information flow, wherein the information flow area is located in a first preset area of a display interface, and the information display sub-area covers a second preset area of the information flow area.

[0339] The display module 4553 is configured to present the display information flow on the display interface to realize information launching.

[0340] In some embodiments of the present application, the display module 4553 is further configured to cover the display interface with an information detail page corresponding to the to-be-launched information when an information viewing instruction is acquired on the information display sub-area, and the information detail page is used to display detailed content of the to-be-launched information.

[0341] The embodiments of the present application provide a computer readable storage medium storing executable instructions, wherein the executable information launching instructions, when executed by a first processor, will cause the processor to execute the information launching method provided by the server side of the embodiments of the present application, or when executed by a second processor, will cause the processor to execute the information launching method provided by the terminal side of the embodiments of the present application. For example, the method shown in Figure 5 、 Figure 8 、 Figure 9 and Figure 10 .

[0342] In some embodiments, the computer readable storage medium can be FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disc, or CD-ROM, etc. memory; or can be various devices including one or any combination of the above-mentioned memories.

[0343] In some embodiments, the executable information launching instructions can be in the form of programs, software, software modules, scripts or codes, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and can be deployed in any form, including being deployed as independent programs or as modules, components, subroutines or other units suitable for use in a computing environment.

[0344] As an example, the executable information launching instructions can but not necessarily correspond to a file in a file system, can be stored in part of a file storing other programs or data, for example, stored in one or more scripts in a HyperText Markup Language (HTML) document, stored in a single file dedicated to the program in question, or stored in multiple cooperative files (for example, files storing one or more modules, subroutines or code portions).

[0345] As an example, the executable information placement instructions can be deployed to execute on one computing device, or on multiple computing devices located at one site, or on multiple computing devices distributed across multiple sites and interconnected through a communications network.

[0346] The above merely provides an example of the embodiments of the present application, but is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, and improvement within the spirit and scope of the present application shall be included in the protection scope of the present application.

Claims

1. An information delivery method, characterized by, The method comprises: obtaining portrait information, exposure information and trigger information of a target delivery object; the portrait information describes interests of the target delivery object, the exposure information represents information that has been shown to the target delivery object, and the trigger information represents information that has been triggered by the target delivery object; wherein the portrait information comprises an interest type, the exposure information comprises an exposure type, and the trigger information comprises a trigger type; comparing the interest type and the trigger type to obtain a first comparison result; the first comparison result represents whether the trigger type is contained in the interest type; comparing the exposure type and the trigger type to obtain a second comparison result; the second comparison result represents whether the trigger type is contained in the exposure type; when the first comparison result represents that the trigger type is not contained in the interest type, or the second comparison result represents that the trigger type is not contained in the exposure type, determining that the trigger type is a demand type of the target delivery object; the demand type represents a type of information that is demanded by the target delivery object; using the demand type, matching out to-be-delivered information from a preset information set; the to-be-delivered information represents information that is waiting to be delivered to the target delivery object; sending the to-be-delivered information to a terminal corresponding to the target delivery object.

2. The method of claim 1, wherein, The method further comprises: based on the portrait information, the exposure information and the trigger information, determining demand information of the target delivery object for a current type in each type; the current type is any one of the each type, and the demand information represents whether the target delivery object has a demand for the current type; when the demand information represents that the target delivery object has a demand for the current type, determining the current type as the demand type.

3. The method of claim 2, wherein, The target delivery object is included in a full-amount object; based on the portrait information, the exposure information and the trigger information, determining the demand information of the target delivery object for a current type in each type comprises: obtaining full-amount portrait information corresponding to the full-amount object from a portrait information library, and obtaining full-amount exposure information corresponding to the full-amount object and full-amount trigger information corresponding to the full-amount object from an operation information library; constructing type attention information according to the portrait information and the full-amount portrait information; the type attention information represents a degree of attention of the target delivery object to the current type; generating type exposure information based on the exposure information and the full-amount exposure information; the type exposure information represents a degree of tendency of showing information of the current type to the target delivery object; constructing type trigger information using the trigger information and the full-amount trigger information; the type trigger information represents a degree of tendency of the target delivery object triggering information of the current type; based on the type attention information, the type exposure information and the type trigger information, determining the demand information of the target delivery object for the current type.

4. The method of claim 3, wherein, The demand information of the target delivery object for the current type is determined based on the type attention information, the type exposure information and the type trigger information, and the demand information includes: When the type attention information is less than a preset degree threshold and the type trigger information is greater than the preset degree threshold, it is determined that the demand information is that the target delivery object has a demand for the current type; or When the type exposure information is less than the preset degree threshold and the type trigger information is greater than the preset degree threshold, it is determined that the demand information is that the target delivery object has a demand for the current type.

5. The method according to claim 3 or 4, characterized in that, The portrait information includes an interest weight, and the full-amount portrait information includes a full-amount interest weight; the type attention information is constructed according to the portrait information and the full-amount portrait information, and the construction includes: The full-amount attention parameters of the full-amount object for the types and the current attention parameter of the full-amount object for the current type are integrated from the full-amount interest weight; The target attention parameters of the target delivery object for the types and the type attention parameter of the target delivery object for the current type are integrated from the interest weight; The type attention information of the target delivery object is constructed by using the full-amount attention parameters, the current attention parameter, the target attention parameter and the type attention parameter.

6. The method according to claim 3 or 4, characterized in that, The exposure information includes an exposure weight and an exposure frequency, and the full-amount exposure information includes a full-amount exposure weight and a full-amount exposure frequency; The type exposure information is generated based on the exposure information and the full-amount exposure information, and the generation includes: The exposure increment weight of the target delivery object for the types is obtained by multiplying the exposure frequency and the exposure weight; wherein the exposure weight represents the weight of the information type exposed to the target delivery object; The target exposure parameters of the target delivery object for the types and the type exposure parameter of the target delivery object for the current type are integrated from the exposure increment weight; The full-amount exposure increment weight of the full-amount object for the types is obtained by multiplying the full-amount exposure weight and the full-amount exposure frequency; wherein the full-amount exposure weight represents the weight of the information type exposed to the full-amount object; The full-amount exposure parameters of the full-amount object for the types and the current exposure parameter of the full-amount object for the current type are integrated from the full-amount exposure increment weight; The type exposure information of the target delivery object is constructed by using the target exposure parameter, the type exposure parameter, the full-amount exposure parameter and the current exposure parameter.

7. The method according to claim 3 or 4, characterized in that, The trigger information includes a trigger weight and a trigger frequency, and the full-amount trigger information includes a full-amount trigger weight and a full-amount trigger frequency; The type trigger information is constructed by using the trigger information and the full-amount trigger information, and the construction includes: The trigger number and the trigger weight are multiplied to obtain a trigger incremental weight of the target delivery object for each type of trigger; wherein the trigger weight represents a weight of an information type triggered by the target delivery object; From the trigger incremental weight, a target trigger parameter of the target delivery object for each type of target trigger and a type trigger parameter of the target delivery object for the current type of target trigger are integrated; The total trigger weight and the total trigger number are multiplied to obtain a total trigger incremental weight of the total object for each type of trigger; wherein the total trigger weight represents a weight of an information type triggered by the total object; From the total trigger incremental weight, a total trigger parameter of the total object for each type of target trigger and a current trigger parameter of the total object for the current type of target trigger are integrated; The target trigger parameter, the type trigger parameter, the total trigger parameter and the current trigger parameter are used to construct the type trigger parameter of the target delivery object.

8. The method of claim 1, wherein, After determining that the trigger type is the demand type of the target delivery object, before sending the to-be-delivered information to the terminal corresponding to the target delivery object, the method further comprises: For the target delivery object, a historical push type is obtained; the historical push type represents a type of information pushed to the target delivery object at a historical time; The historical push type and the demand type are matched to obtain a matching result; the matching result represents whether the historical push type and the demand type match; When the matching result represents that the historical push type and the demand type do not match, the demand type is used to match the to-be-delivered information from the set of to-be-delivered information.

9. The method of claim 1, wherein, The portrait information includes an interest weight, the exposure information includes an exposure weight and an exposure number, and the trigger information includes a trigger weight and a trigger number; After determining that the trigger type is the demand type of the target delivery object, before sending the to-be-delivered information to the terminal corresponding to the target delivery object, the method further comprises: According to the interest weight, an interest proportion of the demand type in the target delivery object is counted; The exposure number and the exposure weight are multiplied to obtain an exposure weight parameter of the demand type, and the trigger number and the trigger weight are multiplied to obtain a trigger weight parameter of the demand type; The number of target delivery objects is counted to obtain a delivery object number; The delivery object number, the interest proportion, the exposure weight parameter and the trigger weight parameter are used to predict a delivery return index corresponding to the demand type; When the delivery return index exceeds a preset index threshold, the to-be-delivered information is matched from the preset information set according to the demand type.

10. An information delivery method characterized by comprising: Comprise: Receiving a to-be-delivered information sent by a server; wherein the to-be-delivered information is determined by the method of any one of claims 1 to 9. Fill the information to be put into the information display sub-area of the information flow area, and obtain a display information flow; wherein, the information flow area is located in a first preset area of a display interface, and the information display sub-area covers a second preset area of the information flow area; Present the display information flow on the display interface, and realize information putting.

11. The method of claim 10, wherein, After the display information flow is presented on the display interface to realize information putting, the method further comprises: When an information viewing instruction is acquired on the information display sub-area, cover the display interface with an information detail page corresponding to the information to be put; the information detail page is used to show the detail content of the information to be put.

12. An information delivery apparatus, characterized by comprising: Comprise: An acquisition module is configured to acquire portrait information, exposure information, and trigger information of a target putting object; The portrait information describes interests of the target putting object, the exposure information represents information shown to the target putting object, and the trigger information represents information triggered by the target putting object; wherein, the portrait information includes an interest type, the exposure information includes an exposure type, and the trigger information includes a trigger type; A demand determination module is configured to compare the interest type and the trigger type to obtain a first comparison result; the first comparison result represents whether the interest type contains the trigger type; compare the exposure type and the trigger type to obtain a second comparison result; the second comparison result represents whether the exposure type contains the trigger type; when the first comparison result represents that the interest type does not contain the trigger type, or the second comparison result represents that the exposure type does not contain the trigger type, determine that the trigger type is a demand type of the target putting object; the demand type represents an information type required by the target putting object; An information matching module is configured to match, by using the demand type, a to-be-put information from a preset information set; the to-be-put information represents information to be put to the target putting object; A sending module is configured to send the to-be-put information to a terminal corresponding to the target putting object.

13. An information presenting apparatus characterized by comprising: Comprise: A receiving module is configured to receive to-be-put information sent by a server; wherein, the to-be-put information is determined by the method of any one of claims 1 to 9; An information processing module is configured to fill the to-be-put information into an information display sub-area of an information flow area, and obtain a display information flow; wherein, the information flow area is located in a first preset area of a display interface, and the information display sub-area covers a second preset area of the information flow area; A display module is configured to present the display information flow on the display interface, and realize information putting.

14. A server, characterized by Comprise: A first memory is configured to store executable information putting instructions; A first processor is configured to execute the executable information putting instructions stored in the first memory, and realize the information putting method of any one of claims 1 to 9.

15. A terminal, characterized by Comprise: A second memory is configured to store executable information putting instructions; A second processor, configured to implement the information delivery method of any one of claims 10 to 11 when executing the executable information delivery instructions stored in the second memory.

16. A computer-readable storage medium, characterized in that, The executable information delivery instructions stored in the memory are configured to cause the first processor to implement the information delivery method of any one of claims 1 to 9 when executed, or to cause the second processor to implement the information delivery method of claim 10 or 11 when executed.

Images