Method, device and equipment for object recommendation and readable medium

Abstract

The embodiment of the invention provides an object recommendation method and device, equipment and a readable medium. The method comprises the following steps: determining a target object recommendation set for a user group; providing the target object recommendation set and the user group to a recommendation system; receiving virtual resource information and a display form for a target object recommendation set from a recommendation system, wherein the virtual resource information indicates virtual resource supply related to at least part of target objects in the target object recommendation set; and recommending a target object in the target object recommendation set to the user group based on the virtual resource information and the display form for the target object recommendation set. In this way, the efficiency of object recommendation can be improved.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computer technology, and more particularly, to a method, apparatus, device, and computer-readable storage medium for object recommendation. Background Art

[0002] With the continuous development of network technology, promotion on platforms outside the recommendation system (off-site) is a common way to recommend objects, which can increase the number of visits and influence of the recommendation system. However, how to share the data on platforms outside the recommendation system with the data within the recommendation system is an urgent problem to be solved. Summary of the invention

[0003] In a first aspect of the present disclosure, a method for object recommendation is provided. The method includes: determining a target object recommendation set for a user group; providing the target object recommendation set and the user group to a recommendation system; receiving virtual resource information and a display form for the target object recommendation set from the recommendation system, the virtual resource information indicating virtual resource supply related to at least some target objects in the target object recommendation set; and recommending the target objects in the target object recommendation set to the user group based on the virtual resource information and the display form for the target object recommendation set.

[0004] In a second aspect of the present disclosure, a device for object recommendation is provided. The device includes: a determination module configured to determine a target object recommendation set for a user group; a providing module configured to provide the target object recommendation set and the user group to a recommendation system; a receiving module configured to receive virtual resource information and a display form for the target object recommendation set from the recommendation system, the virtual resource information indicating virtual resource supply related to at least part of the target objects in the target object recommendation set; and a recommendation module configured to recommend the target objects in the target object recommendation set to the user group based on the virtual resource information and the display form for the target object recommendation set.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The electronic device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit, and when the instructions are executed by the at least one processing unit, the electronic device executes the method of the first aspect of the present disclosure.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to perform the method according to the first aspect of the present disclosure.

[0007] In a fifth aspect of the present disclosure, a computer program product is provided, comprising computer executable instructions, wherein the computer executable instructions can be executed by a processor to perform the method according to the first aspect of the present disclosure.

[0008] It should be understood that the contents described in the summary of the invention are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In the following, in conjunction with the accompanying drawings and with reference to the following detailed description, the above and other features, advantages and aspects of various implementations of the present disclosure will become more apparent. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0011] Figure 2 A flowchart of a process for object recommendation according to some embodiments of the present disclosure is shown;

[0012] Figure 3 A schematic diagram of an object recommendation process according to some embodiments of the present disclosure is shown;

[0013] Figure 4A A flow chart showing a process for a traffic optimization module according to some embodiments of the present disclosure is shown;

[0014] Figure 4B A flow chart showing a process for a user classification module according to some embodiments of the present disclosure;

[0015] Figure 5A A flowchart showing a process for ranking recommendation modules according to some embodiments of the present disclosure is shown;

[0016] Figure 5B A schematic diagram showing an example of a density function according to some embodiments of the present disclosure;

[0017] Figure 5C A schematic diagram showing an example of a function for calculating the points of additional purchase items according to some embodiments of the present disclosure;

[0018] Figure 6 A flowchart showing a process for an object synthesis module according to some embodiments of the present disclosure is shown;

[0019] Figure 7 A flow chart illustrating a process for a virtual resource module according to some embodiments of the present disclosure;

[0020] Figure 8 A flowchart showing a process for rendering a module according to some embodiments of the present disclosure is shown;

[0021] Fig. 9 A schematic structural block diagram of an apparatus for object recommendation according to some embodiments of the present disclosure is shown; and

[0022] Fig.10 A block diagram of an electronic device is shown in which one or more embodiments of the present disclosure may be implemented. DETAILED DESCRIPTION

[0023] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0024] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below.

[0025] It should be noted that the acquisition, storage and application of user personal information involved in the technical solution of the present disclosure are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0026] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0027] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information, so that the user can independently choose whether to provide personal information to software or hardware such as electronic devices, applications, servers or storage media that execute operations of the technical solution of the present disclosure based on the prompt message.

[0028] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information is sent to the user in a manner such as a pop-up window, in which the prompt information can be presented in text form. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0029] Traditionally, object recommendation schemes are mainly implemented through off-site advertising. There are generally three main participants in off-site advertising, namely traffic owners, advertisers, and users. Traffic owners refer to off-site media. Advertisers include operations outside the recommendation system (also called off-site) and operations within the recommendation system (also called on-site). Off-site operations are responsible for interacting with off-site media and introducing off-site traffic into the recommendation system, while on-site operations are responsible for making recommendations within the recommendation system. Traffic is reasonably allocated through recommendation schemes or intelligent algorithms to achieve the purpose of retaining existing users and attracting new users. In the entire process of traditional object recommendation schemes, there is no interaction between the off-site and on-site, but each is carried out separately. In this case, in the process of attracting traffic through off-site advertising, there is no interaction with the on-site, which leads to poor object recommendation results. Specifically, off-site operations and on-site operations respectively implement object recommendations through their own marketing strategies, so that the operation strategies between the on-site and off-site are not coordinated, and all data cannot be shared and fed back in real time.

[0030] In view of this, an embodiment of the present disclosure provides a scheme for object recommendation. The scheme includes: determining a target object recommendation set for a user group; providing the target object recommendation set and the user group to a recommendation system; receiving virtual resource information and a display form for the target object recommendation set from the recommendation system, the virtual resource information indicating a virtual resource supply related to at least part of the target objects in the target object recommendation set; and recommending the target objects in the target object recommendation set to the user group based on the virtual resource information and the display form for the target object recommendation set. In this way, through the interaction between the delivery platform and the recommendation system, data outside the recommendation system and data within the recommendation system can be shared in real time. Through the interaction with the recommendation system, the target objects in the target object recommendation set can be recommended to the user group who may be interested in the target objects in the target object recommendation set in a certain display form, thereby improving the efficiency of object recommendation. Moreover, through the interaction with the recommendation system, when recommending the target object to the user group, the user group can also understand the virtual resource information associated with the target object, thereby increasing the probability of the user group jumping from the delivery platform to the recommendation system, and further increasing the number of visits to the recommendation system.

[0031] Figure 1 Schematic diagram of an example environment in which embodiments of the present disclosure can be implemented. Figure 1As shown, the environment 100 may include a recommendation system 110 and a delivery platform 120 .

[0032] In some embodiments, the delivery platform 120 may recommend the target object in the target object recommendation set to the user group 130 by interacting with the recommendation system 110. In some examples, the recommendation system 110 may be a platform, website, mini program, etc. for selling goods.

[0033] The delivery platform 120 may include any computing system with computing capabilities, such as various computing devices / systems, terminal devices, server devices, etc. The terminal device may be any type of mobile terminal, fixed terminal or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, handheld computers, portable game terminals, VR / AR devices, personal communication systems (PCS) devices, personal navigation devices, personal digital assistants (PDA), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio broadcast receivers, e-book devices, game devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof.

[0034] It should be understood that the structure and function of the various elements in the environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure.

[0035] Some example embodiments of the present disclosure will be described below with continued reference to the accompanying drawings.

[0036] Figure 2 200 is a flowchart of a process for object recommendation according to some embodiments of the present disclosure. Process 200 may be implemented at delivery platform 120. For ease of discussion, reference will be made to Figure 1 The process 200 is described with reference to the environment 100 of FIG.

[0037] In block 210 , the delivery platform 120 determines a set of target object recommendations for the user group 130 .

[0038] Specifically, the delivery platform 120 can determine the target object recommendation set for the user group 130 by monitoring whether the user in the user group 130 performs the first operation, the second operation, and the third operation on the candidate object. In some embodiments, if the delivery platform 120 detects the first operation performed by the user in the user group 130 on the candidate object, the first data entry related to the candidate object and the first operation can be determined. In some examples, when the candidate object is a commodity, the delivery platform 120 detects that the first operation performed by the user on the candidate object can be browsing the commodity. Specifically, the first data entry can include candidate object information and first operation information. In some examples, when the candidate object is a commodity, the candidate object information can be commodity information, such as a commodity display interface, commodity name, category, commodity introduction, commodity price, discount information, etc. It can be understood that this is merely exemplary and not restrictive. There can also be other examples, and the scope of the embodiments of the present disclosure is not limited to this. In some embodiments, the first operation information can include at least one of the following, such as operation content, operation time, number of operations, and operation probability density. In some examples, when the candidate object is a product and the first operation is browsing the product, the first operation information may be expressed as "browsing the product, XXX year X month X day, 5 times, 0.8". It is understood that this is merely exemplary and not restrictive. There may be other examples, and the scope of the embodiments of the present disclosure is not limited to this.

[0039] Further, the delivery platform 120 may determine the score of the candidate object based on the first operation information. In some examples, the score of the candidate object may be determined based on the product of the number of operations of the first operation and the probability density of the operation. It is understood that this is merely exemplary and not restrictive. Further, the delivery platform 120 may determine a candidate object recommendation set based on the score and the candidate object. Specifically, the candidate objects in the candidate object recommendation set may be sorted from high to low according to the score. In some examples, the information of a candidate object in the candidate object recommendation set may include "serial number, category, product name, score". It is understood that this is merely exemplary and not restrictive. In addition, the delivery platform 120 may also select a predetermined number of candidate objects from the candidate object recommendation set as target objects based on the score of the candidate object to form a target object recommendation set. In some examples, since the display page can accommodate a certain number of target objects, if the number of candidate objects in the candidate object recommendation set is greater than the number that the display page can accommodate, the candidate objects corresponding to the number that the display page can accommodate can be selected from the candidate object recommendation set according to the score from high to low. In this way, by determining the target object recommendation set based on the scores of the candidate objects from the candidate object recommendations, a target object recommendation set that better meets user needs can be obtained, thereby improving the object recommendation effect.

[0040] In some embodiments, the delivery platform 120 may determine whether it is detected that the user group 130 performs a second operation on the candidate object. In some examples, when the candidate object is a commodity, the delivery platform 120 detects that the second operation performed by the user group 130 on the candidate object may be to purchase additional commodities. It can be understood that this is merely exemplary and not restrictive. Further, if the delivery platform 120 does not detect the second operation performed by the user group 130 on the candidate object, the delivery platform 120 may add the candidate object to the candidate object recommendation set based on the score of the candidate object to determine the candidate object recommendation set. In some examples, when there are newly added candidate objects in the candidate object recommendation set, the scores of the newly added candidate objects and each candidate object in the candidate object recommendation set may be compared in turn to determine the serial number of the newly added candidate object, and the newly added candidate object information is added to the corresponding position. Specifically, assuming that there are already candidate objects A and candidate objects B in the candidate object recommendation set, the score of candidate object A is 87 and the score of candidate object B is 45, then the serial number corresponding to candidate object A is 1, and the serial number corresponding to candidate object B is 2. In this case, the delivery platform 120 needs to add a new candidate object C to the candidate object recommendation set, and the score of the new candidate object C is 72. Then the delivery platform 120 can compare the score of the new candidate object C with the score of the candidate object A. Since 72 is less than 87, it is determined that the new candidate object C is ranked behind the candidate object A. Further, the delivery platform 120 can compare the score of the new candidate object C with the score of the candidate object B. Since 72 is greater than 45, it is determined that the new candidate object C is ranked before the candidate object B. Then it can be determined that after the new candidate object C is added to the candidate object recommendation set, according to the ranking from high to low scores, the first is the sequence number corresponding to the candidate object A, which is 1, followed by the sequence number corresponding to the new candidate object C, which is 2, and finally the sequence number corresponding to the candidate object B, which is 3. In addition, if candidate object A and candidate object B are not candidate objects with adjacent serial numbers, that is, there are other candidate objects between candidate object A and candidate object B, then before adding candidate object C to the candidate object recommendation set, it is necessary to compare the scores with candidate object A and other candidate objects in order from high to low, starting with candidate object A, until the serial number of the newly added candidate object C can be determined. It can be understood that this is only exemplary and not restrictive. In this way, the scores of different candidate products can be clearly understood from the candidate object information set, which facilitates the selection of a certain number of target objects from the candidate objects.

[0041] In some embodiments, if the delivery platform 120 detects a second operation performed by the user group 130 on a candidate object, a second data entry related to the candidate object and the second operation may be determined. Specifically, each second data entry includes candidate object information and second operation information. Specifically, the second operation information includes at least operation content and operation time. In some examples, when the candidate object is a commodity, the candidate object information may include commodity name, commodity price, score, commodity popularity, discount information, etc. In other examples, when the second operation is to purchase additional commodities, the second operation information may include the purchased commodities, the purchase time, the purchase number, etc.

[0042] Further, the delivery platform 120 may determine whether it is detected that the user group 130 performs a third operation on the candidate object. In some examples, when the candidate object is a commodity, the delivery platform 120 detects that the third operation performed by the user group 130 on the candidate object may be to purchase the commodity. Further, if the delivery platform 120 does not detect the third operation performed by the user group 130 on the candidate object, the candidate object may be added to a candidate object recommendation set to determine the candidate object recommendation set. In some examples, when the candidate object is a commodity and the third operation is to purchase the commodity, if the delivery platform 120 detects that the users in the user group 130 have not purchased the commodity, then the commodity is added to the candidate commodity recommendation set, so as to continue to recommend the commodity to the users in the user group 130 after the delivery platform 120 selects the commodity from the candidate commodity recommendation set to add to the target commodity recommendation set.

[0043] In some embodiments, if the delivery platform 120 detects that the user group 130 performs a third operation on the candidate object, the first data entry and the second data entry may be discarded. In some examples, when the candidate object is a commodity and the third operation is to purchase the commodity, if the delivery platform 120 detects that the user has already purchased the commodity, the first data entry and the second data entry related to the user group 130 and the commodity may be discarded. In this way, it is possible to avoid recommending commodities that have already been purchased to the user, and it is also possible to avoid repeatedly recommending the same commodity, which can improve the user experience.

[0044] After the delivery platform 120 determines the target object recommendation set for the user group 130, the delivery platform 120 may provide the target object recommendation set and the user group 130 to the recommendation system 110 at block 220. In this way, the accuracy of object recommendation may be improved based on the interaction between the delivery platform 120 and the recommendation system 110.

[0045] In some embodiments, the delivery platform 120 may obtain content tags of target delivery content related to at least part of the target objects in the target object recommendation set, as well as user tags for the user group 130. In some examples, the content tag may indicate the category of the target object. Specifically, when the target object is a commodity, the content tag may be an electronic product, stationery, book, clothing, office supplies, etc. In other examples, the content tag may also indicate the name or description of the target object. Specifically, when the target object is a commodity, the content tag may be a camera, a pen, women's clothing, etc. It can be understood that this is merely exemplary and not restrictive. Further, the delivery platform 120 may determine whether the target delivery content is targeted content. In some examples, the targeted content may indicate content for a predetermined user tag. In other examples, the targeted content may indicate content for a predetermined user group 130. It can be understood that this is merely exemplary and not restrictive. There may also be other examples, and the scope of the embodiments of the present disclosure is not limited to this. Furthermore, if the delivery platform 120 determines that the target delivery content is targeted content, the target object recommendation set and the user group 130 may be provided to the recommendation system 110 to receive virtual resource information from the recommendation system 110. In some examples, when the target object is a commodity, the virtual resource information may be preferential information related to the commodity. In this way, by matching user tags and content tags, the accuracy of object recommendation can be improved.

[0046] After the delivery platform 120 provides the target object recommendation set and the user group 130 to the recommendation system 110, the delivery platform 120 can receive virtual resource information and a display form for the target object recommendation set from the recommendation system 110 in box 230. In some examples, the display form for the target object recommendation set can be a double-column display form. In other examples, the display form for the target object recommendation set can be a single-column display form. It can be understood that this is merely exemplary and non-restrictive. There may be other examples, and the scope of the embodiments of the present disclosure is not limited to this. In this way, the accuracy of object recommendation can be improved based on the interaction between the delivery platform 120 and the recommendation system 110.

[0047] In some embodiments, the virtual resource information may indicate the supply of virtual resources related to at least some of the target objects in the target object recommendation set. In some examples, when the target object is a commodity, the virtual resource information may be preferential information related to the commodity, and the target object recommendation set may be a target user recommendation set. Specifically, the preferential information may indicate user rights and interests related to at least some users in the target user recommendation set. In other examples, user rights and interests may be coupons that users can use for the commodity, preferential prices that can be enjoyed, and service peace of mind guarantees that can be enjoyed. Specifically, the service peace of mind guarantee may be an N-day price guarantee service, a free return and exchange service, an X-day no-reason return and exchange service, and the like. It can be understood that this is merely exemplary and not restrictive. There may be other examples, and the scope of the embodiments of the present disclosure is not limited to this.

[0048] After the delivery platform 120 receives the virtual resource information and the display form for the target object recommendation set from the recommendation system 110, the delivery platform 120 can recommend the target object in the target object recommendation set to the user group 130 based on the virtual resource information and the display form for the target object recommendation set in box 240. In some examples, all target objects of the target object recommendation set can be displayed in the media 304 associated with the delivery platform 120 according to the display form. In some examples, part of the target objects of the target object recommendation set can be displayed in the media 304 associated with the delivery platform 120 according to the display form. Specifically, the media 304 associated with the delivery platform 120 can be a media platform, a mini program, a web page, a public account, etc. It can be understood that this is merely exemplary and not restrictive. In this way, the accuracy of object recommendation can be improved and the efficiency of object recommendation can be improved based on the interaction between the delivery platform 120 and the recommendation system 110.

[0049] In some embodiments, if the delivery platform 120 receives a request sent by the user group 130, the data quality corresponding to the request is obtained. In some examples, the data quality may indicate the quality of the data traffic generated by the network-connected device used by the user on the network. It is understood that this is merely exemplary and not restrictive. Further, the delivery platform 120 may determine the user identifier corresponding to the request whose data quality is greater than the quality threshold. In some examples, the user identifier may also be an identifier indicating whether the user has a history of ordering behavior. Specifically, the user identifier with a history of ordering behavior may be a first identifier, such as A. In addition, the user identifier without a history of ordering behavior may also be a second identifier, such as B. In other examples, the user identifier may include both a device number and an identifier indicating whether there is a history of ordering behavior, such as "XXXX.A" or "XXXX.B". It is understood that this is merely exemplary and not restrictive. Further, the delivery platform 120 may filter the user identifier based on the recommendation requirement to determine the user group 130 to which the object recommendation set is to be recommended. In some examples, when the object is a commodity, the recommendation requirement may indicate a user with a history of ordering behavior. Specifically, when the user identifier indicates that the user has no historical ordering behavior, the delivery platform 120 can determine that the user does not meet the recommendation requirements. In addition, when the user identifier indicates that the user has historical ordering behavior, the delivery platform 120 can determine that the user meets the recommendation requirements. It can be understood that this is merely exemplary and not restrictive. There may be other examples, and the scope of the embodiments of the present disclosure is not limited to this. In this way, by screening out users with better traffic quality, the efficiency of object recommendation can be improved.

[0050] In some embodiments, if the delivery platform 120 determines that the target delivery content is non-directional content, the matching result of the content tag and the user tag can be further determined. Specifically, the matching result can indicate a successful match or a failed match. If the matching result of the content tag and the user tag indicates a successful match, the delivery platform 120 can provide the target object recommendation set and the user group 130 to the recommendation system 110 to receive virtual resource information from the recommendation system 110. In some examples, the content tag can be a camera, and the user tag can be a camera enthusiast, then it can be determined that the content tag matches the user tag. In other examples, the content tag can be a men's shirt, and the user tag can be a woman, then it can be determined that the content tag does not match the user tag. In more embodiments, when the content tag can be a men's shirt, the user tag can be a woman, and the user has purchased a product labeled as a man, then it can be determined that the content tag matches the user tag. It can be understood that this is merely exemplary and not restrictive. There can also be other examples, and the scope of the embodiments of the present disclosure is not limited to this.

[0051] In addition, users in the user group 130 may also be classified. In some embodiments, users in the user group 130 may be classified according to the registration status of the users in the recommendation system 110. Specifically, users may be classified into accountless users, new users, and old users according to whether the users have registration information and registration duration. In some examples, accountless users may indicate users who have no registration information in the recommendation system 110, new users may indicate users who have registration information and whose registration duration is less than the duration threshold, and old users may indicate users who have registration information and whose registration duration is greater than the duration threshold. Alternatively, users may be classified into accountless users, new users, and old users according to whether they have registration information, registration duration, and relevance to the recommendation system 110. Specifically, accountless users may indicate users who have no registration information in the recommendation system 110, new users may indicate users who have registration information, whose registration duration is less than the duration threshold, and / or whose relevance to the recommendation system 110 is less than the relevance threshold, and old users may indicate users who have registration information, whose registration duration is greater than the duration threshold, and / or whose relevance to the recommendation system 110 is greater than the relevance threshold. In other embodiments, different user rights and interests are provided for different categories of users. In this way, by classifying users and providing different virtual resource information for different categories of users, the accuracy of object recommendation can be improved.

[0052] Continue to refer to Figure 3 The example process for object recommendation is further described. It is understood that this is merely exemplary and not restrictive.

[0053] Figure 3 1 shows a schematic diagram of an object recommendation process 300 according to some embodiments of the present disclosure. The process 300 may be implemented at the delivery platform 120. For ease of discussion, reference will be made to Figure 1 The process 300 is described with reference to the environment 100 of FIG.

[0054] like Figure 3As shown, outside the recommendation system 110, the traffic optimization module 315 in the media 304 associated with the delivery platform 120 receives the user request 310 from the user group 130. Further, the traffic optimization module 315 screens out the user request 310 corresponding to the device identifier with poor traffic quality by monitoring the traffic quality of the device in the user request 310. And the screened user request 310 is provided to the user classification module 320. Further, the user classification module 320 can classify the users in the user group 130 according to the screened user request 310, and determine to provide corresponding commodity discount information and user rights to different categories of users. Further, the user classification module 320 can provide the user request 310 and the user classification information to the sorting recommendation module 325, and the sorting recommendation module 325 can use the user's browsing behavior as the entry point, and combine the user's purchase and purchase situation, etc., to adjust the target object recommendation set 330 in real time. In addition, the target object recommendation set 330 is provided to the object synthesis module 335 in the recommendation system 110. Further, within the recommendation system 110, the object synthesis module 335 can synthesize the target object recommendation set 330 into the corresponding display page based on the interaction between the recommendation system 110 and the delivery platform 120. Further, the virtual resource module 340 can generate virtual resource information in real time based on the interaction between the recommendation system 110 and the delivery platform 120. Further, the rendering module 345 can render virtual resource information, the display form of virtual resource information, etc. based on the received virtual resource information, and can also recommend the target object recommendation set 330 to the user group 130, and can also undertake user traffic. More, within the delivery platform 120, the synthesis module 350 can synthesize the final display interface of the target object recommendation set 330 based on the received rendered virtual resource information, the display form of virtual resource information, and the target object recommendation set 330 and the template. In addition, the display module 355 of the media 304 associated with the delivery platform 120 displays the display interface of the target object recommendation set 330.

[0055] Alternatively, if the delivery platform 120 detects the user's viewing behavior 360 of the display interface of the target object recommendation set 330, it detects whether there is user exposure 365 and records relevant data. If user exposure 365 is detected, it is further detected whether the user has a page jump 370. If it is detected that the user has a page jump 370, then a directional jump service 375 is provided in the media 304 for users in the user group 130 who have page jumps 370, and the detection module 380 detects and records relevant data. In this way, the accuracy of object recommendation can be improved and the efficiency of object recommendation can be improved.

[0056] Continue to refer to Figure 4AThe following further describes an example process for the traffic optimization module 315. It should be understood that this is merely exemplary and not limiting.

[0057] Figure 4A FIG. 4 is a flow chart showing a process 400A for a flow optimization module according to some embodiments of the present disclosure. Figure 4A As shown, process 400 can be implemented at delivery platform 120. For ease of discussion, reference will be made to Figure 1 The process 400 is described with reference to the environment 100 of FIG.

[0058] In some embodiments, the traffic optimization module 315 may screen out user requests 310 corresponding to device identifiers with poor traffic quality by monitoring the traffic quality of devices related to the user requests 310 .

[0059] like Figure 4A As shown, in the traffic optimization module 315, the delivery platform 120 receives the user request 310 in block 410. In some examples, the user request 310 may indicate a user's request to access the recommendation system 110. It is understood that this is merely exemplary and not limiting.

[0060] After the delivery platform 120 receives the user request 310, it can be checked in box 420 whether the user identification meets the recommendation requirements. In some examples, when the object is a commodity, the recommendation requirement can indicate that the user is not a cheating user. Specifically, a cheating user can indicate a user who has no historical ordering behavior. Specifically, when the user identification indicates that the user is a cheating user, that is, the user has no historical ordering behavior, the delivery platform 120 can determine that the user does not meet the recommendation requirements. In addition, when the user identification indicates that the user is not a cheating user, that is, the user has a historical ordering behavior, the delivery platform 120 can determine that the user meets the recommendation requirements.

[0061] If the delivery platform 120 determines that the user does not meet the recommendation requirements, at block 425 , the delivery platform 120 may wait to receive the next user request 310 .

[0062] If the delivery platform 120 determines that the user meets the recommendation requirements, the delivery platform 120 may determine in block 430 whether the target delivery content is targeted content.

[0063] If the delivery platform 120 determines that the target delivery content is targeted content, the delivery platform 120 may determine whether the content tag matches the user tag at block 440 .

[0064] If the delivery platform 120 determines that the target delivery content is targeted content or the delivery platform 120 determines that the content tag matches the user tag, the user classification module 320 may be entered at block 450. In this way, by screening the quality of user data, the efficiency of object recommendation may be improved.

[0065] Continue to refer to Figure 4B The following is a further description of an example process for the user classification module 320. It is to be understood that this is merely exemplary and not limiting.

[0066] Figure 4B FIG. 4 is a flow chart showing a process 400B for a user classification module according to some embodiments of the present disclosure. Figure 4B As shown, process 400B can be implemented at delivery platform 120. For ease of discussion, reference will be made to Figure 1 The process 400B is described with reference to the environment 100 of FIG.

[0067] In some embodiments, the user classification module 320 may classify users in the user group 130 and determine to provide corresponding product discount information and user rights to users of different categories.

[0068] Specifically, the user 460 in the user group 130 is classified, and the user 460 can be divided into a first type of user 470, a second type of user 480, and a third type of user 490. In some examples, the first type of user 470, the second type of user 480, and the third type of user 490 can represent a user without an account, a new user, and an old user, respectively. In some examples, users can be divided into a user without an account, a new user, and an old user according to whether the user has registration information and the registration duration. In some examples, a user without an account can indicate a user who has no registration information in the recommendation system 110, a new user can indicate a user with registration information and a registration duration less than a duration threshold, and an old user can indicate a user with registration information and a registration duration greater than a duration threshold. Alternatively, users can also be divided into a user without an account, a new user, and an old user according to whether they have registration information, registration duration, and relevance to the recommendation system 110. Specifically, users without an account can indicate users who have no registration information in the recommendation system 110, new users can indicate users who have registration information, whose registration duration is less than the duration threshold and whose relevance to the recommendation system 110 is less than the relevance threshold, and old users can indicate users who have registration information, whose registration duration is greater than the duration threshold and / or whose relevance to the recommendation system 110 is greater than the relevance threshold.

[0069] In addition, different user rights and interests may be provided for different types of users. Specifically, first virtual resources 475 may be provided for first type users 470 , second virtual resources 485 may be provided for second type users 480 , and third virtual resources 495 may be provided for third type users 490 .

[0070] In some examples, users without accounts can be attracted to new accounts by offering hot products and login incentives and benefits. Specifically, hot products refer to products that are popular and relatively cheap, and login incentives and benefits refer to attracting users without accounts to complete registration by displaying preferential information related to products.

[0071] In other examples, new users may indicate users whose registration time is less than a time threshold and / or whose relevance to the recommendation system 110 is less than a relevance threshold. Specifically, users whose relevance to the recommendation system 110 is less than the relevance threshold may be users who have not purchased a product after registration or who have been in a silent period for a long time. For such users, some new user-exclusive prices related to products or some new user rights may be used to attract new users, so as to improve the relevance of new users to the recommendation system 110. For example, new users can purchase products at a relatively low price by receiving red envelopes.

[0072] In more embodiments, old users can be attracted by providing some user rights or product discount information for products that users are interested in, so as to improve the relevance of old users to the recommendation system 110. Specifically, after the old user enters the product purchase page, the available discount information can be displayed. In some examples, the discount information can be determined based on the historical purchase behavior and activity level of the old user. In this way, user rights that are more appropriate to the user category can be provided for different categories of users, thereby improving the relevance of users to the recommendation system 110 and improving the recommendation effect of the target recommendation set.

[0073] Continue to refer to Figure 5A The exemplary process of the ranking recommendation module 325 is further described. It can be understood that this is merely exemplary and not restrictive.

[0074] Figure 5A FIG. 5 is a flowchart of a process 500 for ranking recommendation modules according to some embodiments of the present disclosure. The process 500 may be implemented at the delivery platform 120. For ease of discussion, reference will be made to FIG. Figure 1 The process 500 is described with reference to the environment 100 of FIG.

[0075] In some embodiments, the sorting recommendation module 325 can use the user's browsing behavior as an entry point and combine the user's add-to-cart and purchase status to adjust the target object recommendation set 330 in real time.

[0076] In block 510, the delivery platform 120 detects that the user performs a first operation on the candidate object. In some examples, when the candidate object is a commodity, the first operation may be browsing the commodity. It is understood that this is merely exemplary and not restrictive.

[0077] After the delivery platform 120 detects that the user performs a first operation on the candidate object, in box 520, the first data entry is determined and saved. In some examples, when the user browses the product, the delivery platform 120 can store the relevant first data entry based on the Remote Dictionary Server (Redis), which is a high-performance key-value database. Specifically, in Redis, the redis-hash structure can be used to store the latest time and number of views of the user browsing the product, that is, the hash table structure. In other examples, if a key is selected to represent the user's device number, then a hash-key can be used to store the minimum stock keeping unit (SKU) of the browsed product, and a hash-value can be used to store the user's browsing time and number of views of the product. For example, assuming that the SKU of the product browsed by user A is 183598323, the browsing time and number of times can be stored as {"browse_time":"2023-11-21 14:35:25",browse_count":5}, then the first data entry of Redis storing user A and the product can be expressed as HSET BROWSE-A183598323"{\"browse_time\":\"2023-11-2114:35:25\",\"browse_count\":5}". This can indicate that the minimum inventory unit of the product browsed by user A is 183598323, and the time when the user browsed the product is 2023-11-2114:35:25.

[0078] In block 530, the delivery platform 120 determines whether it is detected that the user performs a second operation on the candidate object. In some examples, when the candidate object is a commodity, the second operation may represent purchasing an additional commodity. It is understood that this is merely exemplary and not restrictive.

[0079] After the delivery platform 120 determines that the user has performed a second operation on the candidate object, the second data entry can be determined and saved in box 540. In some examples, the second data entry can be stored using a redis-hash structure, where the key is the user's device number, the hash-key can represent the sku of the browsed product, and the hash-value can represent the time of adding the product to the purchase. Specifically, the sku of the product browsed by user A is 183598323, and the time of adding the product to the purchase is {"cart_time":"2023-11-21 14:35:27"}, then the Redis storage primitive can be HSET CART-A 183598323"{\"cart_time\":\"2023-11-21 14:35:27\"}". This can indicate that the minimum inventory unit of the product browsed by user A is 183598323, and the time when the user added the product to the purchase is 2023-11-21 14:35:27.

[0080] After the delivery platform 120 determines and saves the second data entry, the delivery platform 120 may determine whether it is detected that the user performs a third operation on the candidate object at block 550. In some examples, the user performing the third operation on the candidate object may be purchasing a product. It is understood that this is merely exemplary and not restrictive.

[0081] After the delivery platform 120 determines that it has detected that the user has performed the third operation on the candidate object, in block 555 , the delivery platform 120 clears the first data entry and the second data entry and returns to the initial state.

[0082] After the delivery platform 120 determines that the user has not performed the second operation on the candidate object, or after the delivery platform 120 determines that the user has not performed the third operation on the candidate object, the score of the candidate object is calculated and added to the candidate object recommendation set in block 560. In this way, the accuracy of object recommendation can be improved by adding the candidate object to the candidate object recommendation set based on the candidate object's score.

[0083] In some examples, when the candidate object is a product, the score of the candidate object can be calculated by first calculating the score of the first operation on the product, that is, the score of browsing the product. Specifically, the score of browsing the product can be calculated using a probability density function, which is as follows:

[0084] y=e -λx (1)

[0085] Among them, λ is a constant, and x is the time difference between the current time and the latest time of browsing the product.

[0086] Then the total score calculation formula for browsing products can be expressed as follows:

[0087] q=b×y (2)

[0088] Among them, b represents the number of times a product is browsed. As time increases, the weight influence of b will become smaller and smaller.

[0089] Continue to refer to Figure 5B The schematic diagram of the density function of browsed commodities is further described. It is understood that this is merely exemplary and not restrictive.

[0090] Figure 5B A schematic diagram of an example 500B of a density function according to some embodiments of the present disclosure is shown. For ease of discussion, reference will be made to Figure 1 Example 500B is described with reference to environment 100 .

[0091] like Figure 5B As shown, the delivery platform 120 detects that the user is browsing the product at the current time, and the score of browsing the product calculated at this time will be relatively large. If the user has not browsed the product for a period of time, the score of browsing the product will gradually decrease. In addition, the number of browsing products can be used as a positive weight to affect the total score of browsing products.

[0092] Continue to refer to Figure 5C The schematic diagram of the function for calculating the score of the added-to-cart item is further described. It should be understood that this is merely exemplary and not restrictive.

[0093] Figure 5C A schematic diagram of an example 500C of a function for calculating the score of an additional product according to some embodiments of the present disclosure is shown. Figure 1 Example 500C is described with reference to environment 100 .

[0094] like Figure 5C As shown, the delivery platform 120 detects that the user adds a product to the shopping cart, which means that the user has a very high probability of purchasing the product, and the probability will increase as time goes by. This growth conforms to the definition of a logarithmic curve. The score calculation function for adding a product to the shopping cart is as follows:

[0095] y=lg x (3)

[0096] Here, x represents the time difference between the current time and the latest time when the product was browsed.

[0097] Then the total score of the product can be determined according to the weight and score of the browsed products and the purchased products. The calculation formula of the total score of the product can be expressed as:

[0098] y=w c ×lg x+1 +w b ×b×e-λx (4)

[0099] Continue to refer to Figure 6 The following is a further description of an example process for the object synthesis module 335. It is to be understood that this is merely exemplary and not limiting.

[0100] Figure 6 Schematic diagram of a process 600 for an object synthesis module according to some embodiments of the present disclosure is shown. Process 600 may be implemented at a delivery platform 120. For ease of discussion, reference will be made to Figure 1 The process 600 is described with reference to the environment 100 of FIG.

[0101] In some embodiments, the object synthesis module 335 may synthesize the target object recommendation set 330 into a corresponding display page based on the interaction between the recommendation system 110 and the delivery platform 120 .

[0102] At block 610, the delivery platform 120 receives the user request 310. In some examples, the object synthesis module 335 may receive a user's request to browse for merchandise. It is understood that this is merely exemplary and not limiting.

[0103] After the delivery platform 120 receives the user request 310, in block 620, a target object recommendation set 330 is obtained. In some examples, when the target object is a commodity, the target object recommendation set 330 may include commodities that may be of interest to the user.

[0104] In block 630 , the delivery platform 120 is in a predetermined mode. In some examples, the predetermined mode may indicate an on-site and off-site linkage mode for the recommendation system 110 , that is, recommending the target object recommendation set 330 to the user group 130 through the interaction between the recommendation system 110 and the delivery platform 120 .

[0105] If the delivery platform 120 determines that it is not the predetermined mode, the delivery platform 120 may wait to receive the next user request 310 at block 635 .

[0106] If the delivery platform 120 determines that it is a predetermined mode, the delivery platform 120 may provide the target object recommendation set 330 to the recommendation system 110 at block 640. In some examples, the target object recommendation set 330 may be provided to the recommendation system 110 through an interface for push in the recommendation system 110.

[0107] After the recommender system 110 receives the target object recommendation set 330 , at block 650 , the recommender system 110 checks the validity of the target objects in the target object recommendation set 330 .

[0108] For determining valid target objects, in box 660, the recommendation system 110 can select a predetermined number of target objects and templates from the target object recommendation set 330 for synthesis. In some examples, the template can indicate the display form of the target object on the activity page. It will be understood that this is merely exemplary and not restrictive. In other examples, if the number of target objects in the target object recommendation set 330 is less than the number of products required by the template, some products can be randomly selected from the hot product pool to supplement, so as to reach the number of products required to generate the display page of the target recommendation set. In this way, the display page of the target recommendation set can be flexibly generated.

[0109] Continue to refer to Figure 7 The following is a further description of an example process for the virtual resource module 340. It is to be understood that this is merely exemplary and not limiting.

[0110] Figure 7 FIG. 7 is a flowchart of a process 700 for a virtual resource module according to some embodiments of the present disclosure. The process 700 may be implemented at the delivery platform 120. For ease of discussion, reference will be made to FIG. Figure 1 The process 700 is described with reference to the environment 100 of FIG.

[0111] In some embodiments, the virtual resource module 340 may generate virtual resource information in real time based on the interaction between the recommendation system 110 and the delivery platform 120 .

[0112] In block 710, the delivery platform 120 receives the user request 310. In some examples, the delivery platform 120 may receive a user's request to access a product display page in the virtual resource module 340. It is understood that this is merely exemplary and not limiting.

[0113] After the delivery platform 120 receives the user request 310, the delivery platform 120 may determine whether the user uses the virtual resource information at block 720. In some examples, the user's rights may indicate coupons, discounts, etc. that the user can use to purchase goods. It is understood that this is merely exemplary and not limiting.

[0114] If the delivery platform 120 determines that the user has used the virtual resource information, the delivery platform 120 may wait to receive the next user request 310 at block 725 .

[0115] If the delivery platform 120 determines that the user has not used the virtual resource information, the delivery platform 120 may receive the virtual resource information in box 730. After the delivery platform 120 receives the virtual resource information, in box 740, the delivery platform 120 places the virtual resource information in the corresponding display position. In some examples, the display position corresponding to the virtual resource information may be a corresponding floor of the landing page of the recommendation system 110. It is understood that this is merely exemplary and not restrictive. In this way, after the user uses the virtual resource information, the target object is no longer recommended to the user, and repeated recommendations can be avoided.

[0116] Continue to refer to Figure 8 The following further describes an example process for the rendering module 345. It should be understood that this is merely exemplary and not limiting.

[0117] Figure 8 800 is a flowchart of a process for rendering a module according to some embodiments of the present disclosure. The process 800 may be implemented at the delivery platform 120. For ease of discussion, reference will be made to Figure 1 The process 800 is described with reference to the environment 100 of FIG.

[0118] In some embodiments, the rendering module 345 can render virtual resource information, display form of virtual resource information, etc. based on the interaction between the recommendation system 110 and the delivery platform 120, and can also recommend the target object recommendation set 330 to the user group 130, and can also undertake user traffic.

[0119] In block 810, a user request 310 is received. In some examples, the delivery platform 120 may receive a user's request to access a product display page in the rendering module 345. It is understood that this is merely exemplary and not limiting.

[0120] At block 820 , the virtual resource information and template are obtained. In some examples, at the rendering module 345 , the delivery platform 120 receives the determined virtual resource information and template.

[0121] In block 830 , whether it is a predetermined mode. In some examples, the predetermined mode may indicate an on-site and off-site linkage mode for the recommendation system 110 , that is, recommending the target object recommendation set 330 to the user group 130 through the interaction between the recommendation system 110 and the delivery platform 120 .

[0122] If the delivery platform 120 determines that it is not the predetermined mode, it may wait to receive the next user request 310 at block 835 .

[0123] If the delivery platform 120 determines that it is a predetermined mode, the target objects in the target object recommendation set 330 may be recommended to the user group 130 in block 840 based on the virtual resource information and the display form of the target object recommendation set 330. In some examples, the display form of the target object recommendation set 330 may be a double-column display or a single-column display. In other examples, the display form of the target object recommendation set 330 may be displayed according to other predetermined display forms.

[0124] In summary, the embodiments of the present disclosure can recommend target objects in the target object recommendation set to the user group based on the virtual resource information received from the recommendation system and the display form for the target object recommendation set. In this way, through the interaction between the delivery platform and the recommendation system, data outside the recommendation system and data within the recommendation system can be shared in real time. Through the interaction with the recommendation system, the target objects in the target object recommendation set can be recommended to the user group who may be interested in the target objects in the target object recommendation set in a certain display form, thereby improving the efficiency of object recommendation. Moreover, through the interaction with the recommendation system, when recommending the target object to the user group, the user group can also understand the virtual resource information associated with the target object, thereby increasing the probability of the user group jumping from the delivery platform to the recommendation system, and further increasing the number of visits to the recommendation system. The embodiments of the present disclosure also provide corresponding devices for implementing the above-mentioned methods or processes.

[0125] Fig. 9 A schematic structural block diagram of an apparatus 900 for object recommendation according to some embodiments of the present disclosure is shown. The apparatus 900 may be implemented as or included in the electronic device 110. Each module / component in the apparatus 900 may be implemented by hardware, software, firmware, or any combination thereof.

[0126] like Fig. 9 As shown, the device 900 includes a determination module 910, which is configured to determine a target object recommendation set for a user group. The device 900 also includes a providing module 920, which is configured to provide the target object recommendation set and the user group to a recommendation system. The device 900 also includes a receiving module 930, which is configured to receive virtual resource information and a display form for the target object recommendation set from the recommendation system, and the virtual resource information indicates a virtual resource supply related to at least part of the target objects in the target object recommendation set. The device 900 also includes a recommendation module 940, which is configured to recommend the target objects in the target object recommendation set to the user group based on the virtual resource information and the display form for the target object recommendation set.

[0127] In some embodiments, the determination module 910 is also configured to determine a first data entry related to the candidate object and the first operation in response to detecting a first operation performed by a user in the user group on the candidate object, the first data entry including candidate object information and first operation information; determine a score of the candidate object based on the first operation information; determine a candidate object recommendation set based on the score and the candidate object, the candidate objects in the candidate object recommendation set are sorted from high to low according to the scores; and select a predetermined number of candidate objects from the candidate object recommendation set as target objects based on the scores of the candidate objects to form a target object recommendation set.

[0128] In some embodiments, the determination module 910 is also configured to determine whether the user group is detected to perform a second operation on the candidate object; and in response to not detecting the user group performing the second operation on the candidate object, add the candidate object to a candidate object recommendation set based on the score of the candidate object to determine the candidate object recommendation set.

[0129] In some embodiments, the determination module 910 is also configured to determine, in response to detecting a second operation performed by a user group on a candidate object, second data entries related to the candidate object and the second operation, each second data entry including candidate object information and second operation information, the second operation information including at least operation content and operation time; determine whether the user group is detected to perform a third operation on the candidate object; and in response to not detecting the third operation performed by the user group on the candidate object, add the candidate object to a candidate object recommendation set to determine the candidate object recommendation set.

[0130] In some embodiments, the determination module 910 is further configured to discard the first data entry and the second data entry in response to detecting a third operation performed by the user group on the candidate object.

[0131] In some embodiments, the determination module 910 is also configured to, in response to receiving a request sent by a user group, obtain data quality corresponding to the request; determine user identifiers corresponding to requests whose data quality is greater than a quality threshold; and filter user identifiers based on recommendation requirements to determine the user group to which the object recommendation set is to be recommended.

[0132] In some embodiments, the providing module 920 is further configured to obtain content tags of target delivery content related to at least part of the target objects in the target object recommendation set, and user tags for the user group; determine whether the target delivery content is targeted content; and in response to determining that the target delivery content is targeted content, provide the target object recommendation set and the user group to the recommendation system to receive virtual resource information from the recommendation system.

[0133] In some embodiments, the providing module 920 is further configured to, in response to determining that the target delivery content is non-targeted content, determine a matching result between the content tag and the user tag, the matching result indicating a successful match or a failed match; and in response to the matching result between the content tag and the user tag indicating a successful match, provide the target object recommendation set and the user group to the recommendation system to receive virtual resource information from the recommendation system.

[0134] The units and / or modules included in the device 900 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units and / or modules can be implemented using software and / or firmware, such as machine executable instructions stored on a storage medium. In addition to or as an alternative to machine executable instructions, some or all of the units and / or modules in the device 900 can be implemented at least in part by one or more hardware logic components. As an example and not limitation, exemplary types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0135] It should be understood that one or more steps in the above method can be performed by a suitable electronic device or a combination of electronic devices. Such an electronic device or a combination of electronic devices may include, for example, Figure 1 The delivery platform 120 in the.

[0136] Fig.10 1 shows a block diagram of an electronic device 1000 in which one or more embodiments of the present disclosure may be implemented. It should be understood that Fig.10 The electronic device 1000 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Fig.10 The electronic device 1000 shown can be used to implement Figure 1 The delivery platform 120 or Fig. 9 Device 900.

[0137] like Fig.10 As shown, the electronic device 1000 is in the form of a general electronic device. The components of the electronic device 1000 may include, but are not limited to, one or more processors or processing units 1010, a memory 1020, a storage device 1030, one or more communication units 1040, one or more input devices 1050, and one or more output devices 10100. The processing unit 1010 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 1020. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 1000.

[0138] The electronic device 1000 typically includes a plurality of computer storage media. Such media may be any available media accessible to the electronic device 1000, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 1020 may be a volatile memory (e.g., a register, a cache, a random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 1030 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 1000.

[0139] The electronic device 1000 may further include additional removable / non-removable, volatile / non-volatile storage media. Fig.10 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. Memory 1020 may include a computer program product 1025 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0140] The communication unit 1040 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 1000 can be implemented in a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 1000 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0141] The input device 1050 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 10100 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 1000 may also communicate with one or more external devices (not shown) through the communication unit 1040 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 1000, or communicate with any device that allows the electronic device 1000 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0142] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0143] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0144] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0145] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0146] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0147] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A method for object recommendation, the method comprising: Determine a target object recommendation set for the user group; Providing the target object recommendation set and the user group to a recommendation system; receiving virtual resource information and a presentation form for the target object recommendation set from the recommendation system, the virtual resource information indicating virtual resource supply related to at least some of the target objects in the target object recommendation set; as well as Based on the virtual resource information and the presentation form for the target object recommendation set, the target objects in the target object recommendation set are recommended to the user group.

2. The method according to claim 1, wherein determining a target object recommendation set for a user group comprises: In response to detecting a first operation performed by a user in the user group on a candidate object, determining a first data entry related to the candidate object and the first operation, the first data entry including candidate object information and first operation information; Determining a score of the candidate object based on the first operation information; Based on the scores and the candidate objects, determining a candidate object recommendation set, wherein the candidate objects in the candidate object recommendation set are sorted from high to low according to the scores; as well as Based on the scores of the candidate objects, a predetermined number of candidate objects are selected from the candidate object recommendation set as target objects to form the target object recommendation set.

3. The method according to claim 2, wherein determining a recommended set of candidate objects based on the scores and the candidate objects comprises: determining whether it is detected that the user group performs a second operation on the candidate object; as well as In response to not detecting a second operation performed by the user group on the candidate object, adding the candidate object to the candidate object recommendation set based on the score of the candidate object to determine the candidate object recommendation set.

4. The method according to claim 3, wherein determining the candidate object recommendation set further comprises: In response to detecting a second operation performed by the user group on the candidate object, determining second data entries related to the candidate object and the second operation, each second data entry including candidate object information and second operation information, wherein the second operation information includes at least operation content and operation time; determining whether it is detected that the user group performs a third operation on the candidate object; as well as In response to not detecting a third operation performed by the user group on the candidate object, adding the candidate object to the candidate object recommendation set to determine the candidate object recommendation set.

5. The method according to claim 4, further comprising: In response to detecting a third operation performed by the user group on the candidate object, the first data entry and the second data entry are discarded.

6. The method according to claim 1, further comprising: In response to receiving a request sent by the user group, obtaining data quality corresponding to the request; Determine a user identifier corresponding to the request whose data quality is greater than a quality threshold; as well as The user identification is screened based on the recommendation requirement to determine the user group to which the object recommendation set is to be recommended.

7. The method according to claim 1, wherein providing the target object recommendation set and the user group to a recommendation system comprises: Acquire content tags of target delivery content related to at least some target objects in the target object recommendation set, and user tags for the user group; Determining whether the target delivery content is targeted content; as well as In response to determining that the target delivery content is targeted content, the target object recommendation set and the user group are provided to the recommendation system to receive the virtual resource information from the recommendation system.

8. The method according to claim 7, further comprising: In response to determining that the target delivery content is non-targeted content, determining a matching result between the content tag and the user tag, wherein the matching result indicates a matching success or a matching failure; as well as In response to the matching result of the content tag and the user tag indicating a successful match, the target object recommendation set and the user group are provided to the recommendation system to receive the virtual resource information from the recommendation system.

9. A device for object recommendation, comprising: A determination module, configured to determine a target object recommendation set for a user group; A providing module, configured to provide the target object recommendation set and the user group to a recommendation system; A receiving module configured to receive virtual resource information and a presentation form for the target object recommendation set from the recommendation system, wherein the virtual resource information indicates virtual resource supply related to at least some target objects in the target object recommendation set; as well as The recommendation module is configured to recommend the target objects in the target object recommendation set to the user group based on the virtual resource information and the presentation form for the target object recommendation set.

10. An electronic device, comprising: at least one processing unit; as well as At least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, cause the electronic device to perform the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 8.

12. A computer program product comprising computer executable instructions, wherein the computer executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 8.

Images