CN112100558A - Method, device, equipment and storage medium for object recommendation - Google Patents

Method, device, equipment and storage medium for object recommendation Download PDF

Info

Publication number
CN112100558A
CN112100558A CN202010911397.5A CN202010911397A CN112100558A CN 112100558 A CN112100558 A CN 112100558A CN 202010911397 A CN202010911397 A CN 202010911397A CN 112100558 A CN112100558 A CN 112100558A
Authority
CN
China
Prior art keywords
data
user
recommendation model
static
dynamic
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010911397.5A
Other languages
Chinese (zh)
Inventor
唐海玉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing ByteDance Network Technology Co Ltd
Original Assignee
Beijing ByteDance Network Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing ByteDance Network Technology Co Ltd filed Critical Beijing ByteDance Network Technology Co Ltd
Priority to CN202010911397.5A priority Critical patent/CN112100558A/en
Publication of CN112100558A publication Critical patent/CN112100558A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/20—Education
    • G06Q50/205—Education administration or guidance
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/21—Server components or server architectures
    • H04N21/218—Source of audio or video content, e.g. local disk arrays
    • H04N21/2187—Live feed
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Educational Technology (AREA)
  • Tourism & Hospitality (AREA)
  • Multimedia (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Signal Processing (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Engineering & Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Data Mining & Analysis (AREA)
  • Development Economics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

Disclosed herein are a method, apparatus, device, and storage medium for object recommendation. The method described herein comprises: determining a first object associated with an object recommending entity based on static data, the object recommending entity providing content for guiding a user to obtain the first object, the static data including at least attribute data of the object recommending entity and attribute data of a plurality of candidate objects associated with the first object; acquiring dynamic data associated with a behavior of a user with respect to a first object, the behavior occurring during a process of providing content by an object recommending entity; and determining a second object based on the dynamic data, the object recommending entity being to provide content for guiding the user to obtain the second object. In this way, dynamic object recommendation can be achieved, and the accuracy and efficiency of object recommendation is improved.

Description

Method, device, equipment and storage medium for object recommendation
Technical Field
Embodiments of the present disclosure relate generally to the field of information technology, and more particularly, to a method, apparatus, device, and storage medium for object recommendation.
Background
With the development of information technology, people increasingly depend on networks. Various recommendation techniques have been developed to recommend objects of interest to a user. The recommendation technology is one of important guarantee technologies for improving user experience and improving operation efficiency and accuracy in a network application environment. However, currently known recommendation techniques typically only consider historical behavior of the current target user or other relevant users, and thus recommendations can only be performed based on historical data. Such recommendations may be referred to as "static recommendations". Since static recommendation does not fully consider various participants on the network, the recommendation effect is to be improved.
Disclosure of Invention
In a first aspect of the disclosure, a method for object recommendation is provided. The method comprises determining a first object associated with an object recommending entity, the object recommending entity providing content for guiding a user to obtain the first object, based on static data, the static data comprising at least attribute data of the object recommending entity and attribute data of a plurality of candidate objects associated with the first object; acquiring dynamic data associated with a behavior of a user with respect to a first object, the behavior occurring during a process of providing content by an object recommending entity; and determining a second object based on the dynamic data, the object recommending entity being to provide content for guiding the user to obtain the second object.
In a second aspect of the disclosure, an apparatus for object recommendation is provided. The device includes: a first determination module configured to determine a first object associated with an object recommending entity, the object recommending entity providing content for guiding a user to obtain the first object, based on static data, the static data including at least attribute data of the object recommending entity and attribute data of a plurality of candidate objects associated with the first object; an acquisition module configured to acquire dynamic data associated with a behavior of a user with respect to a first object, the behavior occurring during provision of content by an object recommending entity; and a second determination module configured to determine a second object based on the dynamic data, the object recommending entity to provide content for guiding the user to obtain the second object.
In a third aspect of the disclosure, an apparatus is provided that includes one or more processors; and storage means for storing the one or more programs which, when executed by the one or more processors, cause the one or more processors to carry out the method according to the first aspect of the disclosure.
In a fourth aspect of the present disclosure, a computer-readable medium is provided, on which a computer program is stored which, when executed by a processor, implements a method according to the second aspect of the present disclosure.
It should be understood that the statements herein reciting aspects are not intended to limit the critical or essential 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 apparent from the following description.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, like or similar reference characters designate like or similar elements, and wherein:
FIG. 1 illustrates a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented;
FIG. 2 illustrates a schematic diagram of an example scenario in accordance with some embodiments of the present disclosure;
FIG. 3 illustrates a flow diagram of a process for object recommendation, according to some embodiments of the present disclosure;
FIG. 4 illustrates a flow diagram of a process for updating a recommendation model and selecting a second object based on the updated recommendation model according to some embodiments of the present disclosure;
FIG. 5 shows a schematic block diagram of an apparatus for object recommendation according to an embodiment of the present disclosure; and
FIG. 6 illustrates a block diagram of a computing device capable of implementing various embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
In describing embodiments of the present disclosure, the terms "include" and its derivatives should be interpreted as being inclusive, i.e., "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 terms "first," "second," and the like may refer to different or the same object. Other explicit and implicit definitions are also possible below.
As described above, conventional recommendation techniques typically only take into account historical user behavior, and thus can only perform static recommendations based on historical data. In addition, the conventional recommendation technology does not fully consider various participants on the network, so the recommendation effect is poor.
For example, with the development of live web technologies, live shopping is beginning to become an important live web. The recommended goods selected by the anchor have different degrees of influence on merchants, users, live broadcast platforms and the anchor. However, the anchor may rely solely on its goods selection team to select goods to recommend. Further, even if the anchor determines the goods to be recommended by means of the conventional recommendation technique, such a technique has difficulty in recommending the goods of most interest to the target user of the anchor due to the above-described drawbacks.
As another example, online education techniques are becoming popular, and the lessons selected by teachers to teach will affect the teaching performance of the educational institution or teacher, or the learning interest or performance of students. However, the teacher may rely solely on his experience to select the course to be taught. Further, even if the teacher determines the lesson to be taught by means of the conventional recommendation technique, such technique is difficult to achieve maximization of the teaching effect or learning interest or effect due to the above-described drawbacks.
To address, at least in part, one or more of the above problems and other potential problems, example embodiments of the present disclosure propose an object recommendation scheme. In general, according to embodiments described herein, a first object (e.g., an item, a course, etc.) associated with an object recommendation entity (e.g., a host, a teacher, etc.) may be determined based on static data. The object recommending entity provides a program for guiding a user (e.g., fan, student, etc.) to acquire content of a first object (e.g., a live video of an anchor providing introduction to an item, or a lesson video of a teacher). The static data includes at least attribute data of the object recommending entity and attribute data of a plurality of candidate objects (e.g., a plurality of items in an item library, or a plurality of courses in a course list) associated with the first object. Further, dynamic data associated with a behavior of a user with respect to the first object may be obtained. Such actions occur during the process of providing content by the object recommending entity. Thus, a second object (e.g., another item, a course, etc.) may be determined based on the dynamic data. The object recommending entity is to provide content for guiding the user to obtain the second object.
In this way, the scheme of the present disclosure can implement dynamic recommendation of objects based on dynamic data. In addition, the scheme comprehensively considers the attributes of the object recommending entity and various candidate objects, and improves the accuracy and efficiency of object recommendation.
As used herein, the term "model" may learn from training data the associations between respective inputs and outputs, such that after training is complete, for a given input, a corresponding output may be generated. It should be understood that a "model" may also be referred to as a "neural network," a "learning model," or a "learning network.
In the following, embodiments of the present disclosure will be discussed taking webcast technology and/or online education technology as examples, however, it should be understood that aspects of the present disclosure may be similarly applied to other scenarios, such as advertisement recommendations, etc.
Embodiments of the present disclosure will be described below in detail with reference to the accompanying drawings.
Fig. 1 illustrates a schematic diagram of an example environment 100 in which various embodiments of the present disclosure can be implemented. In this example environment 100, a computing device 110 may obtain static data 120. For example, the computing device 110 may retrieve the static data 120 from any storage device (not shown), such as a database, that stores the static data 120. In some embodiments, the static data 120 may include attribute data of the object recommending entity 140 (e.g., anchor, teacher, etc.). For example, for a webcast, static data 120 may include the number of fans of the anchor, fan portraits, anchor portraits, and the like. Similarly, for online education, static data 120 may include a number of students of a teacher, student representations, teacher representations, and the like.
The term "portrayal" as used herein refers to the abstraction of concrete information of entities such as fans, anchor, etc. into one or more tags and the use of these tags to materialize the appearance of the entities, thereby characterizing the entities. For example, the picture of vermicelli may be "network youth", the picture of anchor may be "electronic product human-oriented broadcast", the picture of student may be "mathematics special grower", the picture of teacher may be "Oudemans lecturer", etc.
Further, in some embodiments, static data 120 may also include attribute data for multiple candidate objects. For example, attribute data of a plurality of items in the item library (such as price, category, sales promotion, etc.), or attribute data of a plurality of courses in the course list (such as subject, duration, difficulty, etc.).
Optionally, in some embodiments, static data 120 may also include attribute data of user 150 and/or historical data associated with historical behavior of user 150 with respect to multiple candidate objects. The attribute data of the user 150 may be the gender, age, geographical location, etc. of the user 150, such as fans, students, etc. The historical data may be reviews, praise, collections, purchases, shares, etc. of the user 150 over time for the goods, courses, etc.
The computing device 110 may determine, based on the static data 120, a first object 130 (e.g., an item, a course, etc.) associated with the object recommending entity 140. The object recommending entity 140 provides content for guiding a user 150 (e.g., fans, students, etc.) to obtain the first object 130. For example, the anchor may provide a live video that introduces merchandise to guide fans to purchase the merchandise, or the teacher may provide a lesson video to students to guide the students to purchase, view, or download lessons.
In this way, the object recommending entity 140 can be selected with a personalized object to be recommended, so that the selected object is more easily acquired by the user 150, thereby improving the accuracy and efficiency of object recommendation. For example, a anchor might be very adept at recommending electronic products, the anchor's fan is mostly a male digital fan, and there is a mobile phone in the store ready for promotion of the day, in which case choosing to recommend the mobile phone to a fan for the anchor would enable highly accurate and efficient recommendations. As another example, a teacher may be very adept at geometry teaching, the students of the teacher are mostly geometry enthusiasts, and geometry lessons are arranged in the lesson list of the current day, in which case choosing a teaching geometry lesson for the teacher will achieve high accuracy and high efficiency of recommendations.
Further, the computing device 110 may obtain dynamic data 160 associated with the behavior of the user 150 with respect to the first object 130. Such actions occur during the process of providing content by the object recommending entity 140. For example, in the process of anchor live introduction of a commodity or in the process of teacher teaching a course, a fan or a student can comment, like, collect, buy, share, etc. on the commodity or the course.
Thus, the computing device 110 may determine the second object 170 (e.g., another item, a course, etc.) based on the dynamic data 160. The object recommending entity 140 is to provide content for guiding the user 150 to obtain the second object 170. For example, the anchor may provide a live video introducing another item to guide a fan to purchase another item, or the teacher may provide a lesson video of another lesson to the student to guide the student to purchase, view, or download another lesson.
In this manner, the selection of the second object 170 is made dynamically, for example, during live broadcast of the first item by the anchor, or dynamically as the teacher teaches a lesson. For example, the interest of the users in the electronic products can be reflected by various actions (such as comment, like, favorite, buy, share, and the like) of the fans watching the live broadcast on the mobile phones recommended by the anchor broadcast. In this case, the recommended electronic product, such as a headset, a charger, or another mobile phone, may be continuously selected from the store. As another example, teaching math lessons may continue to be selected from the list of lessons by reflecting the learning interest in mathematics through the various activities of the geometric lessons taught by the teacher by the student currently watching the lesson.
In some embodiments, the computing device 110 may determine a plurality of objects to be recommended based on the static data 120 in addition to the first object 120. In this case, the dynamically determined second object 170 may replace an object of the plurality of objects to be recommended or join the plurality of objects to be recommended. Therefore, unlike the case where conventionally the commodities to be recommended before the anchor starts live broadcast are all determined or the courses are all determined before the teacher attends a class, the subsequent commodities to be recommended or the courses for professors can be dynamically adjusted according to the fan or the student's behavior.
In this way, on one hand, the object to be recommended can be dynamically, accurately and quickly determined for the object recommending entity 140, so that the object recommended by the object recommending entity 140 better meets the requirements of its target user. On the other hand, the user 150 can find the object of interest more easily, thereby saving the time it takes to select the object of interest among the mass information.
Fig. 2 illustrates a schematic diagram of an example scenario 200, in accordance with some embodiments of the present disclosure. Taking the live broadcast as an example, initially, the computing device 110 may select various objects to be recommended for the object recommending entity 140 based on the static data 120. For example, the computing device may utilize a trained recommendation model to select an object to be recommended based on the static data 120. These objects to be recommended may include at least the first object 130, and optionally may also include other objects to be recommended, such as the objects to be recommended 230 and 240, and the like. In some embodiments, the objects to be recommended may be formed as a list of objects to be recommended 220.
The object recommending entity 140 may live according to the objects listed in the list of objects to be recommended 220 to recommend these objects to the user 150. Assume that the object recommending entity 140 is recommending the first object 130 through live broadcasting. At this time, the user 150 may view a live broadcast of the recommendation of the first object 130 made by the object recommending entity 140 on the terminal device 210 thereof, and perform actions of approval, sharing, purchase, and/or comment, and the like.
The computing device 110 may adjust the objects in the list of objects to be recommended 220 based on the dynamic data 160, thereby generating an updated list of objects to be recommended 250. For example, the computing device 110 may utilize a streaming computing engine to determine the second object 170 based on the dynamic data 160. The second object 170 may be added to the list of objects to be recommended 220 to generate an updated list of objects to be recommended 250. Alternatively, the second object 170 may replace an object (such as the objects to be recommended 230 and/or 240) in the list of objects to be recommended 220 to generate the updated list of objects to be recommended 250.
In this way, the object to be recommended may be dynamically, accurately, and quickly determined for the object recommending entity 14, so that the object recommended by it is, with a greater probability, the object of interest to the user 150.
The operation of the computing device 110 will be described in detail below in conjunction with fig. 3-4. FIG. 3 illustrates a flow diagram of a process 300 for object recommendation, according to some embodiments of the present disclosure. For example, process 300 may be performed by computing device 110 as shown in fig. 1. It should be understood that process 300 may also include additional steps not shown and/or may omit steps shown, as the scope of the present disclosure is not limited in this respect.
At block 310, the computing device 110 determines the first object 130 associated with the object recommending entity 140 based on the static data 120. The object recommending entity 140 may provide a content for guiding the user 150 to obtain the first object 130. For example, the computing device 110 may determine, based on the static data 120, that the anchor is to recommend items, and the anchor may provide a live video that introduces the items to guide fans to purchase the items. Alternatively, the computing device 110 may determine a course that the teacher is to teach based on the static data 120, and the teacher may provide a course video to the student to guide the student in purchasing, viewing, or downloading the course.
As described above, the static data 120 includes at least attribute data of the object recommending entity 140 and attribute data of a plurality of candidate objects associated with the first object 130. In some embodiments, static data 120 may also include attribute data of the user and/or historical data associated with historical behavior of the user with respect to multiple candidate objects.
The first object 130 may be determined in various ways. In some embodiments, the first object 130 may be determined by pattern matching. In particular, the computing device 110 may determine a pattern indicating an object to be recommended based on at least one of attribute data of the object recommending entity 140, attribute data of the user, historical data. For example, the image of the anchor is "electronic product talent," vermicelli is 15-30 years old, sex is male, and vermicelli purchases electronic products within one month. In this case, the mode of the article to be recommended may be determined as an electronic product. As another example, the representation of the teacher is "historical teacher," the geographic location of the student is beijing, and popular science articles about the mindset are shared. In this case, it may be determined that the pattern of the lessons to be recommended is the beijing history of the time period of the mingxi.
Computing device 110 may determine whether attribute data of each of the plurality of candidate objects matches the determined pattern. In some embodiments, for each object of the plurality of candidate objects, the computing device 110 may determine whether the attribute data of the respective object matches the pattern. For example, for each item in the commodity library, it may be determined whether the attribute data of the item matches the electronic product, or for each course in the course list, it may be determined whether the attribute data of the course matches the Beijing history of the Ming Dynasty period.
If the attribute data of the corresponding object matches the pattern, the computing device 110 determines the corresponding object as the first object 130. For example, the category of the mobile phone in the commodity library is an electronic product or the category of the forbidden city history in the course list is the beijing history of the time period of the mingzhou, and thus may be determined as the first object 130.
Further, in addition to pattern matching, the first object 130 may be determined using a trained recommendation model. In particular, the computing device 110 may obtain a recommendation model that characterizes at least a relationship between the static data 120 and the objects to be recommended. The computing device 110 may apply the static data 120 to a recommendation model to select a first object 130 from a plurality of candidate objects.
In some embodiments, the computing device 110 may train the recommendation model before determining the first object 130 using the recommendation model. In particular, the computing device 110 may input the static data of the plurality of candidate objects and the identification of the object to be recommended of the plurality of candidate objects as training samples into the recommendation model to train the recommendation model. Thus, the trained recommendation model may well characterize the relationship between the static data 120 and the objects to be recommended. It should be appreciated that in some embodiments, the computing device 110 may determine a plurality of objects to be recommended based on the static data 120 in addition to the first object 120.
The above-described stage of determining the first object 130 from historical or past static data 120 may be considered a cold start stage. In the cold start phase, one or more objects to be recommended are preliminarily selected for the object recommending entity 140. After the object recommending entity 140 starts providing content for guiding the user 150 to acquire the first object 130 (e.g., the anchor starts live or the teacher starts lecturing), various actions (e.g., comment, like, favorite, buy, share, etc.) that the user 150 will perform on the first object 130. By collecting dynamic data 160 of the user 150, the objects to be recommended by the object recommending entity 140 may be dynamically adjusted, thereby recommending objects of more interest to the user 150.
To do so, at block 320, the computing device 110 may obtain dynamic data 160 associated with the user's actions performed with respect to the first object 130. Such actions occur during the process of providing content by the object recommending entity 140. The dynamic data 160 may include data associated with comment operations by the user 150 on the first object 130, data associated with approval operations by the user 150 on the first object 130, data associated with collection operations by the user 150 on the first object 130, data associated with purchase operations by the user 150 on the first object 130, and/or data associated with sharing operations by the user 150 on the first object 130, and so forth.
At block 330, the computing device 110 may determine the second object 170 based on the dynamic data 160. The object recommending entity 140 is to provide content for guiding the user 150 to obtain the second object 170. For example, various actions (such as comments, praise, collection, purchase, share and the like) performed on a mobile phone recommended by a main broadcast by a fan watching the live broadcast currently can reflect that the users are interested in the electronic products, and the recommended electronic products can be continuously selected from the commodity library. As another example, teaching math lessons may continue to be selected from the list of lessons by reflecting the learning interest in mathematics through the various activities of the geometric lessons taught by the teacher by the student currently watching the lesson.
In some embodiments, the recommendation model may be updated by means of a streaming computation engine, thereby enabling dynamic adjustment of the objects to be recommended. In principle, in an iterative process based on dynamic model update of the streaming computing engine, dynamic data of a user is subjected to data merging and sampling in a preset time window (for example, a window in the order of minutes) through the streaming computing engine, and feature data representing the dynamic data, such as a vector representing the dynamic data, is generated. And then, performing model iteration of minute level by using the characteristic data as an input sample, and outputting an updated recommended model after the iteration is completed. The model may be trained for various goals, for example, the goal of model training may be to purchase the largest number of purchases, share the largest number of times, and so on.
In the following, a flow chart of a process 400 for updating a recommendation model and selecting a second object 170 based on the updated recommendation model will be described in detail in connection with fig. 4. The computing device 110 may update the recommendation model based on the dynamic data 160 and the static data 120. The recommendation model characterizes the relationship between the dynamic data 160, the static data 120 and the objects to be recommended. Specifically, at block 410, the computing device 110 may apply the dynamic data 160 to a streaming computing engine to generate a characterization representation of the portion of the dynamic data within the predetermined time window, such as a vector characterizing the portion of the dynamic data within the predetermined time window.
At block 420, the computing device 110 may update the recommendation model based on the feature representations and the static data 120. At block 430, the computing device 110 may apply the dynamic data 160 and the static data 120 to the updated recommendation model to select the second object 170 from the plurality of candidates. It should be appreciated that the dynamic data 160 and the static data 120 are used herein for both updating the recommendation model and selecting the second object 170 based on the updated recommendation model. Indeed, in some embodiments, the dynamic data 160 and static data 120 may also be grouped into training data and prediction data. In this case, the training data may be used to update the recommendation model, and the prediction data may be used to select the second object 170 based on the updated recommendation model.
In this way, the recommendation model may be dynamically updated and continually iterated with the dynamic data of the user that is newly generated during the recommendation of the object by the object recommending entity. In this case, the recommendation model can more accurately and quickly determine the object to be recommended which meets the needs of the user, so that the probability of the user obtaining the object is improved, and the needs of each party of an object recommendation entity (e.g., teacher, anchor), a user (e.g., fan, student), an object provider (e.g., merchant, education institution), an object recommendation platform (e.g., live broadcast platform, online education platform), and the like are better met.
Fig. 5 shows a schematic block diagram of an apparatus 500 for object recommendation according to an embodiment of the present disclosure. As shown in fig. 5, the apparatus 500 includes: a first determination module 510 configured to determine a first object associated with an object recommending entity, the object recommending entity providing content for guiding a user to obtain the first object, based on static data, the static data including at least attribute data of the object recommending entity and attribute data of a plurality of candidate objects associated with the first object; an obtaining module 520 configured to obtain dynamic data associated with a behavior of a user with respect to a first object, the behavior occurring during a process of providing content by an object recommending entity; and a second determining module 530 configured to determine a second object based on the dynamic data, the object recommending entity to provide content for guiding the user to obtain the second object.
In certain embodiments, the static data further comprises at least one of: attribute data of the user, and historical data associated with historical behavior of the user against the plurality of candidate objects.
In some embodiments, the first determining module comprises: a pattern determination module configured to determine a pattern indicating an object to be recommended based on at least one of attribute data of the object recommending entity, attribute data of the user, and history data; a matching module configured to determine whether attribute data of each of the plurality of candidate objects matches the pattern; and a first object determination module configured to determine the corresponding object as the first object if the attribute data of the corresponding object matches the pattern.
In some embodiments, the first determining module comprises: a model obtaining module configured to obtain a recommendation model characterizing at least a relationship between the static data and an object to be recommended; and a first selection module configured to apply the static data to the recommendation model to select a first object from the plurality of candidate objects.
In some embodiments, the second determining module comprises: an update module configured to update a recommendation model based on the dynamic data and the static data, the recommendation model characterizing a relationship between the dynamic data, the static data, and an object to be recommended; and a second selection module configured to apply the dynamic data and the static data to the updated recommendation model to select a second object from the plurality of candidates.
In some embodiments, the update module comprises: a generation module configured to apply the dynamic data to a streaming computation engine to generate a characterization of a portion of the dynamic data within a predetermined time window; and a model update module configured to update the recommendation model based on the feature representation and the static data.
In certain embodiments, the dynamic data includes at least one of: the data processing method comprises the following steps of data associated with comment operation of a user on a first object, data associated with approval operation of the user on the first object, data associated with collection operation of the user on the first object, data associated with purchase operation of the user on the first object, and data associated with sharing operation of the user on the first object.
Fig. 6 illustrates a schematic block diagram of an example device 600 that can be used to implement embodiments of the present disclosure. Device 600 may be used to implement computing device 110 of fig. 1. As shown, device 600 includes a Central Processing Unit (CPU)601 that may perform various appropriate actions and processes in accordance with computer program instructions stored in a Read Only Memory (ROM)602 or loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
A number of components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, a mouse, or the like; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
Processing unit 601 performs the various methods and processes described above, such as process 300 and/or process 400. For example, in some embodiments, process 300 and/or process 400 may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM 602 and/or the communication unit 609. When the computer programs are loaded into RAM 603 and executed by CPU 601, one or more steps of process 300 and/or process 400 described above may be performed. Alternatively, in other embodiments, CPU 601 may be configured to perform process 300 and/or process 400 by any other suitable means (e.g., by way of firmware).
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a load programmable logic device (CPLD), and the like.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Further, while operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims (16)

1. A method of object recommendation, comprising:
determining a first object associated with an object recommending entity that provides content for guiding a user to obtain the first object based on static data that includes at least attribute data of the object recommending entity and attribute data of a plurality of candidate objects associated with the first object;
obtaining dynamic data associated with a behavior of the user with respect to the first object, the behavior occurring during provision of the content by the object recommending entity; and
determining a second object based on the dynamic data, the object recommending entity to provide content for guiding the user to obtain the second object.
2. The method of claim 1, wherein the static data further comprises at least one of:
attribute data of the user, and
historical data associated with historical behavior of the user against the plurality of candidate objects.
3. The method of claim 2, wherein determining the first object comprises:
determining a mode indicating an object to be recommended based on at least one of attribute data of the object recommending entity, attribute data of the user, and the history data;
determining whether attribute data of each of the plurality of candidate objects matches the pattern; and
determining the corresponding object as the first object if the attribute data of the corresponding object matches the pattern.
4. The method of claim 1, wherein determining the first object comprises:
obtaining a recommendation model, wherein the recommendation model at least represents the relation between the static data and an object to be recommended; and
applying the static data to the recommendation model to select the first object from the plurality of candidate objects.
5. The method of claim 1, wherein determining the second object comprises:
updating a recommendation model based on the dynamic data and the static data, the recommendation model characterizing a relationship between the dynamic data, the static data, and an object to be recommended; and
applying the dynamic data and the static data to an updated recommendation model to select the second object from the plurality of candidates.
6. The method of claim 5, wherein updating the recommendation model comprises:
applying the dynamic data to a streaming computing engine to generate a characterization of a portion of the dynamic data within a predetermined time window; and
updating the recommendation model based on the feature representation and the static data.
7. The method of claim 1, wherein the dynamic data comprises at least one of:
data associated with a comment operation performed by the user on the first object,
data associated with a praise operation of the first object by the user,
data associated with a favorite operation of the first object by the user,
data associated with a purchase made by the user of the first object, an
Data associated with a sharing operation performed by the user on the first object.
8. An apparatus for object recommendation, comprising:
a first determination module configured to determine a first object associated with an object recommending entity that provides content for guiding a user to obtain the first object based on static data that includes at least attribute data of the object recommending entity and attribute data of a plurality of candidate objects associated with the first object;
an obtaining module configured to obtain dynamic data associated with a behavior of the user with respect to the first object, the behavior occurring during provision of the content by the object recommending entity; and
a second determination module configured to determine a second object based on the dynamic data, the object recommending entity to provide content for guiding the user to obtain the second object.
9. The apparatus of claim 8, wherein the static data further comprises at least one of:
attribute data of the user, and
historical data associated with historical behavior of the user against the plurality of candidate objects.
10. The apparatus of claim 9, wherein the first determining module comprises:
a pattern determination module configured to determine a pattern indicating an object to be recommended based on at least one of attribute data of the object recommending entity, attribute data of the user, and the history data;
a matching module configured to determine whether attribute data of each of the plurality of candidate objects matches the pattern; and
a first object determination module configured to determine the respective object as the first object if the attribute data of the respective object matches the pattern.
11. The apparatus of claim 8, wherein the first determining module comprises:
a model obtaining module configured to obtain a recommendation model characterizing at least a relationship between the static data and an object to be recommended; and
a first selection module configured to apply the static data to the recommendation model to select the first object from the plurality of candidate objects.
12. The apparatus of claim 8, wherein the second determining module comprises:
an update module configured to update a recommendation model based on the dynamic data and the static data, the recommendation model characterizing a relationship between the dynamic data, the static data, and an object to be recommended; and
a second selection module configured to apply the dynamic data and the static data to an updated recommendation model to select the second object from the plurality of candidates.
13. The apparatus of claim 12, wherein the update module comprises:
a generation module configured to apply the dynamic data to a streaming computation engine to generate a characterization of a portion of the dynamic data within a predetermined time window; and
a model update module configured to update the recommendation model based on the feature representation and the static data.
14. The apparatus of claim 8, wherein the dynamic data comprises at least one of:
data associated with a comment operation performed by the user on the first object,
data associated with a praise operation of the first object by the user,
data associated with a favorite operation of the first object by the user,
data associated with a purchase made by the user of the first object, an
Data associated with a sharing operation performed by the user on the first object.
15. An apparatus, the apparatus comprising:
one or more processors; and
storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to carry out the method according to any one of claims 1-7.
16. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.
CN202010911397.5A 2020-09-02 2020-09-02 Method, device, equipment and storage medium for object recommendation Pending CN112100558A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010911397.5A CN112100558A (en) 2020-09-02 2020-09-02 Method, device, equipment and storage medium for object recommendation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010911397.5A CN112100558A (en) 2020-09-02 2020-09-02 Method, device, equipment and storage medium for object recommendation

Publications (1)

Publication Number Publication Date
CN112100558A true CN112100558A (en) 2020-12-18

Family

ID=73757026

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010911397.5A Pending CN112100558A (en) 2020-09-02 2020-09-02 Method, device, equipment and storage medium for object recommendation

Country Status (1)

Country Link
CN (1) CN112100558A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112399195A (en) * 2020-11-17 2021-02-23 播商(广州)科技有限公司 One-stop retail live broadcast matrix platform based on network operation
CN113205382A (en) * 2021-04-30 2021-08-03 北京有竹居网络技术有限公司 Method, apparatus, device, storage medium and program product for determining object
CN113709576A (en) * 2021-09-03 2021-11-26 广州微行网络科技有限公司 E-commerce online live broadcast method and system based on Internet
WO2022228075A1 (en) * 2021-04-30 2022-11-03 北京有竹居网络技术有限公司 Method, apparatus, and device for determining promoter, storage medium, and program product

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105872629A (en) * 2016-03-18 2016-08-17 合网络技术（北京）有限公司 Content recommendation method, apparatus and system
CN106874522A (en) * 2017-03-29 2017-06-20 珠海习悦信息技术有限公司 Information recommendation method, device, storage medium and processor
CN108076353A (en) * 2017-05-18 2018-05-25 北京市商汤科技开发有限公司 Business object recommends method, apparatus, storage medium and electronic equipment
CN108073671A (en) * 2017-04-12 2018-05-25 北京市商汤科技开发有限公司 Business object recommends method, apparatus and electronic equipment

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105872629A (en) * 2016-03-18 2016-08-17 合网络技术（北京）有限公司 Content recommendation method, apparatus and system
CN106874522A (en) * 2017-03-29 2017-06-20 珠海习悦信息技术有限公司 Information recommendation method, device, storage medium and processor
CN108073671A (en) * 2017-04-12 2018-05-25 北京市商汤科技开发有限公司 Business object recommends method, apparatus and electronic equipment
CN108076353A (en) * 2017-05-18 2018-05-25 北京市商汤科技开发有限公司 Business object recommends method, apparatus, storage medium and electronic equipment

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112399195A (en) * 2020-11-17 2021-02-23 播商(广州)科技有限公司 One-stop retail live broadcast matrix platform based on network operation
CN112399195B (en) * 2020-11-17 2022-05-17 播商(广州)科技有限公司 One-stop retail live broadcast matrix platform based on network operation
CN113205382A (en) * 2021-04-30 2021-08-03 北京有竹居网络技术有限公司 Method, apparatus, device, storage medium and program product for determining object
WO2022228075A1 (en) * 2021-04-30 2022-11-03 北京有竹居网络技术有限公司 Method, apparatus, and device for determining promoter, storage medium, and program product
WO2022228074A1 (en) * 2021-04-30 2022-11-03 北京有竹居网络技术有限公司 Method and apparatus for determining object, and device, storage medium and program product
CN113205382B (en) * 2021-04-30 2024-02-20 北京有竹居网络技术有限公司 Method, apparatus, device, storage medium and program product for determining object
CN113709576A (en) * 2021-09-03 2021-11-26 广州微行网络科技有限公司 E-commerce online live broadcast method and system based on Internet
CN113709576B (en) * 2021-09-03 2024-04-09 郴州优趣信息科技有限公司 Online live broadcast method and system for E-commerce based on Internet

Similar Documents

Publication Publication Date Title
US10613726B2 (en) Removing and replacing objects in images according to a directed user conversation
CN112100558A (en) Method, device, equipment and storage medium for object recommendation
US20150339034A1 (en) User interactions using digital content
CN109460514A (en) Method and apparatus for pushed information
US10290032B2 (en) Blacklisting based on image feature analysis and collaborative filtering
CN113592535B (en) Advertisement recommendation method and device, electronic equipment and storage medium
US20190155864A1 (en) Method and apparatus for recommending business object, electronic device, and storage medium
CN109417644A (en) The income optimization launched across screen advertisement
CN109460503A (en) Answer input method, device, storage medium and electronic equipment
CN111695041B (en) Method and device for recommending information
CN112836128A (en) Information recommendation method, device, equipment and storage medium
CN116894711A (en) Commodity recommendation reason generation method and device and electronic equipment
CN114461871A (en) Recommendation model training method, object recommendation device and storage medium
CN113407854A (en) Application recommendation method, device and equipment and computer readable storage medium
CN110109937A (en) A kind of assessment of popular science knowledge and learning method, system and equipment
CN112446214A (en) Method, device and equipment for generating advertisement keywords and storage medium
CN116628349A (en) Information recommendation method, device, equipment, storage medium and program product
CN112308648A (en) Information processing method and device
CN110909154A (en) Abstract generation method and device
CN116611891A (en) Content information recommendation method, device, server and storage medium
CN115482415A (en) Model training method, image classification method and device
CN112348594A (en) Method, device, computing equipment and medium for processing article demands
Alqahtani et al. iMAP-CampUS (an Intelligent Mobile Augmented Reality Program on Campus as a Ubiquitous System) A Theoretical Framework to Measure User's Behavioural Intention
CN111915339A (en) Data processing method, device and equipment
CN111626805B (en) Information display method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination