TW201923675A - Information recommendation method, device and apparatus - Google Patents

Abstract

Provided in an embodiment of the specification are an information recommendation method, device and apparatus. The information recommendation method comprises: collecting user data of a target user, the user data comprising behavior data generated when the target user accesses an information provision page of a target service; determining, on the basis of the user data, an input value of a conditional prediction model corresponding to the target service, inputting the same to the conditional prediction model, and outputting an information filtering condition; and performing filtering of information sets corresponding to the target service to obtain recommendation information meeting the information filtering condition, and providing the same to the target user.

Description

Information recommendation method, device and equipment

The embodiments of the present specification relate to the field of machine learning technology, and in particular, to an information recommendation method, device, and device.

At present, websites or applications (Application, App) provide users with pages for displaying information lists, and users usually need to filter out the information they need from the information list. In related technologies, for the convenience of filtering, the page usually contains some parameters for the user to set (such as product price, product category, etc.), and the user can complete the information filtering process by manually setting the values of each parameter. It can be seen that, because the current information filtering method is more dependent on the user's own filtering operation, it is obviously not efficient and not smart enough.

In view of this, the embodiments of the present specification provide a method, an apparatus and a device for recommending information. In order to achieve the above purpose, the technical solutions provided in the embodiments of the present specification are as follows: In one aspect, an information recommendation method provided includes: collecting user data of a target user, the user data including the target user accessing a target service Behavioral data generated on the information providing page of ；; 确定 determining input values of conditional prediction models corresponding to the target business based on the user data and inputting the conditional prediction models to output information filtering conditions; from the target business The recommended information matching the information filtering condition is filtered out from the corresponding information set and provided to the target user. In another aspect, an information recommendation method provided includes: sending a request to a server for recommendation information corresponding to a target business, the request carrying a target user identification; receiving and displaying information filtering conditions returned by the server, The information screening condition is predicted and obtained based on the user data corresponding to the target user identification and a condition prediction model corresponding to the target business; receiving from the server corresponding to the target business Recommended information filtered from the information collection that meets the information filtering conditions is displayed. In another aspect, an information recommendation device provided includes: (i) a collection unit that collects user data of a target user, the user data including behavior data generated by the target user accessing an information providing page of the target business; (ii) conditional acquisition A unit that determines an input value of a conditional prediction model corresponding to the target business based on the user data and inputs the conditional prediction model into the conditional prediction model, and outputs information filtering conditions; an information recommendation unit, from the information corresponding to the target business The recommended information that meets the information filtering conditions is filtered out from the collection and provided to the target user. In another aspect, an information recommendation device provided includes: a request sending unit that sends a request to a server for recommendation information corresponding to a target service, the request carrying a target user identification; a condition display unit that receives the server The returned information filtering conditions are predicted and obtained based on the user data corresponding to the target user identification and a condition prediction model corresponding to the target business; a recommended information display unit that receives The recommendation information returned by the server and filtered from the information set corresponding to the target business and meeting the information filtering condition is displayed. In yet another aspect, an electronic device provided includes: a processor; a memory for storing processor-executable instructions; a processor configured to: a collection of user data of a target user, the user data including The target user accesses behavior data generated from the information providing page of the target business; 确定 determines an input value of a conditional prediction model corresponding to the target business based on the user data and inputs the conditional prediction model into the conditional prediction model, and outputs information filtering Conditions; 筛选 selecting recommended information that meets the information filtering conditions from the information set corresponding to the target business and providing it to the target user. In yet another aspect, an electronic device provided includes: a processor; a memory for storing processor-executable instructions; a processor configured to: a request to a server to obtain recommendation information corresponding to a target service, The request carries a target user identification; receiving and displaying information filtering conditions returned by the server, the information filtering conditions are based on user data corresponding to the target user identification and conditions corresponding to the target business The prediction model is used to predict the obtained information. (1) Receive and display the recommended information that meets the information filtering conditions and that is filtered out from the information set corresponding to the target service and returned by the server. As can be seen from the above technical solutions, a condition prediction model corresponding to the target business is obtained in advance through machine learning training. After collecting user data of the target user, based on the user data and the conditions The prediction model predicts the information filtering conditions corresponding to the target user, and finally automatically recommends the recommended information that meets the information filtering conditions and provides them to the target user. It can be seen that the above process does not require user operation, which improves Information screening efficiency.

FIG. 1 shows a flowchart of an information recommendation method applied on a server side according to an exemplary embodiment. As shown in FIG. 1, in an embodiment, the method includes steps 101 to 105, where: In step 101, user data of a target user is collected, where the user data includes the target user's storage. Get behavioral data from the feed page of the target business. In general, for an application App or a website, it can contain one or more businesses. For example, the business involved in an App includes: clothing business, wealth management product business, insurance business, etc. The target service may be one of the services provided by the platform. For different businesses, the platform will provide users with feed pages corresponding to each business. These feed pages can be used to display various product information. Correspondingly, the behavior data may include, but is not limited to: the user viewed those product information on the page, or the frequency of viewing a certain product information, the length of time spent on a certain product information page, or the user viewing the platform Duration of recommended information, etc. Of course, the above behavior data may be data generated within a set period of time (such as the last 3 days). In addition to behavioral data, user data can also include, but is not limited to: basic personal information of the user (such as: age, gender, work, etc.). Among them, the user data may be collected in advance and stored in a database, and the required user data is extracted from the database when needed. Of course, it can also be recorded on the terminal device used by the user, and obtained from the terminal device when needed. In step 102, an input value of a conditional prediction model corresponding to the target business is determined based on the user data and inputted into the conditional prediction model, and an information filtering condition is output. Among them, the conditional prediction model is obtained by training with a Machine Learning (ML) algorithm in advance. In an embodiment, for a specified target service, a method initially used to train the model (the model needs to be continuously optimized in the subsequent steps) includes the following steps a to e, where: step a: determining that the target service corresponds to The initial information screening condition of the user, wherein the user group matching the initial information screening condition under the target business is the largest. For example, if the target business is a wealth management product business, the initial platform will obtain the demand target of each user in the user group of the wealth management product business. The demand target is the information screening condition corresponding to each user. The information screening condition It can be composed of one or more conditions, for example: Condition 1: Low risk, Condition 2: The amount is below 100,000. Among them, in order to obtain the data used to initially train the model, the initial information filtering conditions need to be determined in advance according to the demand goals of most users under the target business (the demand goals of a small number of users are not considered). Among them, after obtaining the information filtering conditions corresponding to each user, users can be clustered according to the same information filtering conditions, so as to obtain the number of user groups after clustering corresponding to each information filtering condition, and select among them. The user group with the largest number of users finally uses the information filtering condition corresponding to the selected user group as the initial information filtering condition. Step b: Select initial recommendation information that meets the initial information filtering condition from the information set corresponding to the target service and provide it to the user group of the target service. For example, if the target business is a wealth management product business, the information collection is a collection of wealth management product information (for example, information about 100 types of wealth management products). Assuming that the initial information screening condition is "low risk + quota below 100,000", you can Automatically filter out all product information (that is, the initial recommendation information) that meets the "low risk + quota below 100,000" and display it to users in the form of a list. The purpose of the above steps a and b is to show a small number of screening results to new users of the target business, thereby reducing the operations of most users in the process of filtering information. Step c: According to each user's selection of the initial recommendation information, determine a personalized filtering condition corresponding to each user. Generally, the initial recommendation information selected by the platform according to the initial information screening conditions does not meet the needs of all users. Some users need to make further selections based on the initial recommendation information. For example, the initial recommendation information includes 10 kinds of product information. , The user picks out five of his needs. After the user chooses, the personalized filtering conditions that meet the user's real needs goals can be determined. For example: the initial information screening condition is "low risk + quota below 100,000". After a user further selects, it can be determined that the user's corresponding personal screening condition is: low risk + quota below 100,000 + investment period Within 6 months. Step d: Collect user data of each user. As mentioned above, user data includes, but is not limited to, behavioral data generated by users accessing the target business's feed page and basic personal information of the user. Step e: Based on the user data of each user and the personalized filtering conditions corresponding to each user, a machine learning algorithm is used to train a condition prediction model of the target business.实施 In the embodiment of the present application, each user may be used as a training sample, and user data and personalized filtering conditions may be used as sample data. By mathematically expressing user data and personalized filter conditions (usually vectors), the mathematical expression corresponding to the user data is used as the input of the conditional prediction model, and the mathematical expression corresponding to the personalized filter conditions is used as the conditional prediction. The expected output of the model is finally trained to obtain the conditional prediction model. Of course, the accuracy of the initially trained conditional prediction model may be less accurate, which can be continuously optimized in the subsequent use process. Machine learning algorithms are common techniques in this field, and will not be repeated here. After having the above conditional prediction model, the input value (ie, vectorized representation) of the conditional prediction model can be determined according to the user data collected in step 101 and input into the model. Finally, it can be determined according to the model output Forecasted information filters (in line with the needs of the target user). In step 103, recommendation information that meets the information filtering condition is filtered from the information set corresponding to the target service and provided to the target user. It can be seen that a conditional prediction model corresponding to the target business is obtained in advance through machine learning training. After collecting user data of the target user, the conditional prediction model is predicted based on the user data and the conditional prediction model. The information filtering conditions corresponding to the target user, and finally automatically recommend the recommended information that meets the information filtering conditions and provide it to the target user. It can be seen that the above process improves the efficiency of information filtering because no user action is required, and Be smarter. In step 104, the information filtering conditions corresponding to the target user are updated according to the selection operation of the recommended information by the target user. In the embodiment of the present application, since the accuracy of the trained conditional prediction model needs to be continuously optimized, the information screening conditions predicted by the model may not meet the real needs of the target user. For this reason, some users can perform selective operations on the recommended information displayed, such as further selecting the information that is really interesting based on the recommended information, and adding other interesting information to the same based on the recommended information. In the page, or completely discard the information recommended by the platform, re-enter the filter conditions and obtain the corresponding information, and so on. The above operations are consistent with the actual needs of the target user, so the user's preferred information filtering conditions can be updated according to the operations performed by the user. In step 105, based on the user data of the target user and the information filtering conditions updated by the target user, a machine learning algorithm is used to optimize the condition prediction model. As described above, the user data may be generated by the target user within a certain collection period. By processing the collected user data and the updated information filtering conditions into mathematical expressions, the user data may be It is further used to train the conditional prediction model, so that the accuracy of the model is continuously optimized.该 After this step 105, the subsequent prediction process of the information screening conditions can be performed based on the latest optimized model. Through continuous precipitation of the data, the accuracy of the model can be continuously improved. Of course, in an implementable embodiment, the above steps 104 and 105 may be omitted.一 In an embodiment of the present application, the method may further include: 展示 displaying the information filtering conditions output by the condition prediction model to the target user. If the target user confirms the displayed information filtering conditions, the recommended information that meets the information filtering conditions is selected from the information set corresponding to the target business and provided to the target user. FIG. 2 shows a schematic diagram of a user interface provided by an exemplary embodiment. In conjunction with FIG. 2, after a user enters an information recommendation page, the back end (server side) can be based on the user data and conditions of the user. The prediction model predicts the information filtering conditions corresponding to the user and feeds back to the client device used by the user. After receiving the information filtering conditions, the client device will be displayed to the user. The advantage of this is that the user clearly knows what kind of conditions the platform's information filtering process is based on. After the user sees the information filtering conditions, Can intuitively understand whether it is consistent with itself, which can increase user trust. Thereafter, the interface can also provide a confirmation button for the user to click. When the user clicks, it indicates that he has no objection to the predicted information filtering conditions, and then the recommended information filtered based on these conditions is displayed to the user. Among them, the user interface also provides users with the function of further adjusting the recommendation information, such as providing many dimensions (such as: quota, cycle, etc.), the user can choose based on the dimensions, so as to filter the more consistent with their needs Information to view. Of course, the form of the user interface is not limited to this. FIG. 3 shows a flowchart of an information recommendation method applied to a user terminal (ie, a client device) provided by an exemplary embodiment. As shown in FIG. 3, in an embodiment, the method includes steps 201 to 203, where: In step 201, a request for obtaining recommendation information corresponding to a target service is sent to a server, wherein the request carries a target User ID (such as the ID of the user registered in the App). For example, the target business is a financial management business under an app. When a user clicks into a page used to display recommendation information, the terminal device that installs the app sends a request to the server. In step 202, information screening conditions returned by the server are received and displayed, wherein the information screening conditions are based on user data corresponding to the target user identification and condition prediction models corresponding to the target business. To predict the gain. In step 203, receiving and displaying recommended information that meets the information filtering condition and is filtered out from the information set corresponding to the target service and returned by the server. For this method, reference may be made to the content of the method shown in FIG. 1 above, and details are not described herein.对应 Corresponding to the above method, this article also provides an information recommendation device, which can be implemented by software code. As shown in FIG. 4, in an embodiment, an information recommendation device 300 is applied to a server. The device 300 includes: a collection unit 301 configured to collect user data of a target user, the user data Including the behavior data generated by the target user accessing the information service page of the target business; (i) the condition obtaining unit 303 is configured to determine the input value of the condition prediction model corresponding to the target business based on the user data and input the In the condition prediction model, an information screening condition is output; an information recommendation unit 305 is configured to: select recommended information that meets the information screening condition from the information set corresponding to the target business and provide it to the target for use By. In an embodiment, the device 300 further includes: a condition update unit that updates an information filtering condition corresponding to the target user according to the target user's selection operation of the recommended information; a model optimization unit based on the The user data of the target user and the information filtering conditions updated by the target user are optimized by using a machine learning algorithm. In one embodiment, the device 300 further includes: A condition display unit, which displays the information filtering conditions output by the condition prediction model to the target user. In an embodiment, the information recommendation unit 305 may be configured as follows: If the target user confirms the displayed information filtering conditions, select the information matching the information from the information set corresponding to the target business. Filter recommendation information and provide it to the target user. As shown in FIG. 5, in one embodiment, an information recommendation device 400 is applied at a user end. The device 400 includes: a request sending unit 401 configured to: send to a server to obtain recommendation information corresponding to a target service A request, wherein the request carries a target user identification. The condition display unit 403 is configured to receive and display the information filtering conditions returned by the server, the information filtering conditions are based on user data corresponding to the target user identification and conditions corresponding to the target service. Predictive models to get predictions. Recommended information display unit 405 is configured to: receive and display the recommended information returned by the server, which is filtered from the information set corresponding to the target service and meets the information filtering condition. As shown in FIG. 6, one or more embodiments of this specification provide an electronic device (such as a server or a client device). The electronic device may include a processor, an internal bus, a network interface, and a memory (including Memory and non-volatile memory), of course, it may also include hardware required for other businesses. A processor may be one or more instances of a central processing unit (CPU), processing unit, processing circuit, processor, application specific integrated circuit (ASIC), microprocessor, or other processing logic of executable instructions. The processor reads the corresponding program from the non-volatile memory into the memory and then runs. Of course, in addition to the software implementation, one or more embodiments of this specification do not exclude other implementations, such as a logical device or a combination of software and hardware, etc., which means that the execution body of the following processing flow is not limited to Each logic unit may also be a hardware or logic device. In an embodiment, for the server, the processor may be configured to: collect user data of a target user, where the user data includes information generated by the target user accessing an information providing page of the target service Behavioral data; 确定 determining an input value of a conditional prediction model corresponding to the target business based on the user data and inputting the conditional prediction model to output information filtering conditions; 筛选 filtering from a set of information corresponding to the target business Recommend information that meets the information filtering conditions is provided to the target user. In an embodiment, for a client device (such as a mobile phone or a computer), the processor may be configured to: 发送 send a request to a server to obtain recommendation information corresponding to a target service, where the request carries the target use (1) receiving and displaying the information filtering conditions returned by the server, the information filtering conditions are predicted and obtained based on the user data corresponding to the target user identification and a condition prediction model corresponding to the target business; Receiving and displaying the recommended information returned by the server, which is filtered from the information set corresponding to the target business and meets the information filtering condition.各个 Each embodiment in this specification is described in a progressive manner, and the same / similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, as for the device embodiment and the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts may refer to the description of the method embodiment.的 The system, device, module, or unit described in the above embodiments may be implemented by a computer chip or entity, or a product with a certain function. A typical implementation device is a computer, and the specific form of the computer can be a personal computer, a notebook computer, a mobile phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email sending and receiving device, a game console, A tablet, a wearable, or a combination of any of these devices. For the convenience of description, when describing the above device, the functions are divided into various units and described separately. Of course, when implementing one or more embodiments of the present specification, the functions of each unit may be implemented in the same software or hardware.的 Those skilled in the art should understand that the embodiments of the present invention may be provided as a method, a system, or a computer program product. Therefore, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk memory, CD-ROM, optical memory, etc.) containing computer-usable code therein. . The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and a combination of the flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to generate a machine that can be executed by the processor of the computer or other programmable data processing device. The instructions generate means for implementing the functions specified in one or more flowcharts and / or one or more blocks of the block diagram. These computer program instructions may also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including a command device , The instruction device realizes the functions specified in a flowchart or a plurality of processes and / or a block or a block of the block diagram. These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operating steps can be performed on the computer or other programmable equipment to generate computer-implemented processing, so that the computer or other programmable equipment can The instructions executed on the steps provide steps for realizing the functions specified in one or more flowcharts and / or one or more blocks of the block diagram.计算 In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory. Memory may include non-permanent memory, random access memory (RAM), and / or non-volatile memory in computer-readable media, such as read-only memory (ROM) or flash memory ( flashRAM). Memory is an example of a computer-readable medium. Computer-readable media include permanent and non-permanent, removable and non-removable media. Information can be stored by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), and other types of random access memory (RAM) , Read-only memory (ROM), electrically erasable and programmable read-only memory (EEPROM), flash memory or other memory technologies, read-only discs (CD-ROM), digital versatile discs (DVDs) ) Or other optical storage, magnetic tape cartridges, magnetic disk storage or other magnetic storage devices, or any other non-transmission media, may be used to store information that can be accessed by computing devices. According to the definition in this article, computer-readable media does not include temporary computer-readable media (transitorymedia), such as modulated data signals and carrier waves. It should also be noted that the terms "including," "including," or any other variation thereof are intended to encompass non-exclusive inclusion, so that a process, method, product, or device that includes a series of elements includes not only those elements but also Other elements not explicitly listed, or those that are inherent to such a process, method, product, or device. Without more restrictions, the elements defined by the sentence "including a ..." do not exclude the existence of other identical elements in the process, method, product or equipment including the elements.技术 Those skilled in the art should understand that the embodiments of one or more embodiments of the present specification may be provided as a method, a system, or a computer program product. Therefore, one or more embodiments of the present specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, one or more embodiments of the present specification may be implemented on one or more computer-usable storage media (including but not limited to magnetic disk memory, CD-ROM, optical memory, etc.) containing computer-usable code therein. In the form of a computer program product.一个 One or more embodiments of this specification can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present specification may also be practiced in a decentralized computing environment in which tasks are performed by a remote processing device connected through a communication network. In a decentralized computing environment, program modules can be located in local and remote computer storage media, including storage devices. The above description is only an embodiment of one or more embodiments of the present specification, and is not intended to limit one or more embodiments of the present specification. For those skilled in the art, various modifications and changes can be made to one or more embodiments of the present specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of patent application of one or more embodiments of this specification.

101 ~ 105‧‧‧ steps

201 ~ 203‧‧‧step

300‧‧‧ Information Recommendation Device

301‧‧‧collection unit

303‧‧‧Condition acquisition unit

305‧‧‧ Information Recommendation Unit

400‧‧‧ information recommendation device

401‧‧‧ request sending unit

403‧‧‧Condition display unit

405‧‧‧Recommended information display unit

FIG. 1 shows a flowchart of an information recommendation method applied on a server side according to an exemplary embodiment; FIG. 2 shows a schematic diagram of a user interface provided by an exemplary embodiment; FIG. 3 shows an exemplary A flowchart of an information recommendation method applied to a user terminal provided by the embodiment; FIG. 4 shows a module diagram of an information recommendation device applied to a server provided by an exemplary embodiment; FIG. 5 shows an example A module diagram of an information recommendation device applied to a user-end device according to an exemplary embodiment; FIG. 6 illustrates a structure of an electronic device according to an exemplary embodiment.

Claims (13)

An information recommendation method includes: collecting user data of a target user, the user data including behavior data generated by the target user's access to the information providing page of the target service; 的 determining the corresponding to the target service based on the user data The input value of the conditional prediction model is input into the conditional prediction model, and the information filtering conditions are output; 推荐 The recommended information that meets the information filtering conditions is selected from the information set corresponding to the target business and provided to the target user. The method according to item 1 of the scope of patent application, further comprising: 更新 updating the information filtering conditions corresponding to the target user according to the selection operation of the recommended information by the target user; based on the user data of the target user and the The target user's updated information filtering conditions are optimized by machine learning algorithms. The method according to item 1 of the scope of patent application, further comprising: 展示 displaying the information filtering conditions output by the condition prediction model to the target user. According to the method described in item 3 of the scope of patent application, the screening of recommended information that meets the information screening conditions and providing to the target user includes: If the target user confirms the displayed information screening conditions, The recommended information matching the information filtering conditions is selected from the information collection corresponding to the business and provided to the target user. According to the method described in the first patent application scope, the training process of the conditional prediction model includes: determining an initial information screening condition corresponding to the target business, wherein the user group matching the initial information screening condition under the target business has the largest user group ; 筛选 screen out the initial recommendation information that meets the initial information filtering conditions from the information set corresponding to the target business and provide it to the user group of the target business; 确定 determine each of the users based on their selection of the initial recommendation information Personalized filter conditions corresponding to users; Collect user data of each user; Based on each user's user data and each user's corresponding personalized filter conditions, use machine learning algorithms to train the target business Conditional prediction model. An information recommendation method includes: 发送 sending a request to a server to obtain recommendation information corresponding to a target business, the request carrying a target user identification; receiving and displaying information filtering conditions returned by the server, the information filtering conditions are based on the The user data corresponding to the target user ID and the conditional prediction model corresponding to the target business are obtained by prediction; receiving a recommendation returned by the server that meets the information screening conditions and is filtered from the information set corresponding to the target business Information and display. An information recommendation device includes: (1) a collection unit that collects user data of a target user, the user data including behavior data generated by the target user accessing a target service's information providing page; (2) a conditional acquisition unit based on the user data Determine the input value of the conditional prediction model corresponding to the target business and enter it into the conditional prediction model to output information screening conditions; Information recommendation unit selects recommendations that meet the information screening conditions from the information collection corresponding to the target business Information and provide it to that target user. The device according to item 7 of the scope of patent application, further comprising: condition updating unit, which updates the information filtering conditions corresponding to the target user according to the target user's selection operation of the recommended information; model optimization unit, based on the target The user data of the user and the information filtering condition updated by the target user are optimized by a machine learning algorithm. The device according to item 7 of the scope of patent application, further comprising: Condition display unit, which displays the information filtering conditions output by the condition prediction model to the target user. According to the device described in item 9 of the scope of patent application, the information recommendation unit is configured as follows: 该 If the target user confirms the displayed information filtering conditions, select the information matching the target business from the information set corresponding to the target business. Filter recommendation information and provide it to the target user. An information recommendation device includes: a request sending unit that sends a request to a server for recommendation information corresponding to a target service, the request carrying a target user identification; a condition display unit that receives and displays information filtering conditions returned by the server, The information filtering condition is predicted and obtained based on the user data corresponding to the target user identification and the condition prediction model corresponding to the target business; Recommended information display unit, which receives the information returned from the server corresponding to the target business. Recommended information filtered from the information collection that meets the information filtering conditions is displayed. An electronic device includes: a processor; a memory for storing processor-executable instructions; a processor configured to: a collection of user data of a target user, the user data including the target user's access to a target service Behavioral data generated from the information feed page of ；; 确定 Determine the input value of the conditional prediction model corresponding to the target business based on the user data and enter it into the conditional prediction model to output information filtering conditions; From the information set corresponding to the target business The recommended information that meets the information filtering conditions is selected and provided to the target user. An electronic device includes: a processor; a memory for storing processor-executable instructions; a processor configured to: a request for obtaining recommendation information corresponding to a target service to a server, the request carrying a target user identification Receive and display the information filtering conditions returned by the server, and the information filtering conditions are predicted and obtained based on the user data corresponding to the target user ID and the condition prediction model corresponding to the target business; receive the server return The recommended information that is filtered from the information collection corresponding to the target business and meets the information filtering conditions is displayed.