Object recommendation method, device, electronic device and computer-readable storage medium

Abstract

The present application provides an object recommendation method, apparatus, electronic device, and computer-readable storage medium. The method includes: obtaining attribute information of an object to be recommended and attribute information of each reference object among a plurality of reference objects; determining a target reference object having attribute associations with the object to be recommended from the plurality of reference objects based on the attribute information of the object to be recommended and the attribute information of each reference object among the plurality of reference objects; obtaining rating information of the target reference object by a target user; predicting the target user's rating of the object to be recommended based on the rating information, the attribute information of the object to be recommended, and the attribute information of the target reference object to obtain a corresponding first predicted rating; determining whether the object to be recommended meets recommendation conditions based on the first predicted rating; and recommending the object to be recommended to the target user when the object to be recommended meets the recommendation conditions. Through the present application, the recommended objects can be made more in line with the user's preferences.

Description

Technical Field

[0001] The present application relates to computer technology, and in particular to an object recommendation method, device, electronic device, and computer-readable storage medium. Background Art

[0002] Current object recommendation methods generally require more or less user evaluation information on the objects to make recommendations based on the average user information. However, this method solves the data sparsity problem in the recommendation algorithm, but it is difficult to recommend completely new objects. For objects that are already online, using user evaluations does not well meet user preferences. Summary of the Invention

[0003] The embodiments of the present application provide an object recommendation method, device, electronic device, and computer-readable storage medium, which can make the recommended objects more in line with user preferences.

[0004] The technical solution of the embodiment of the present application is implemented as follows:

[0005] This embodiment of the present application provides an object recommendation method, including:

[0006] Obtaining attribute information of the object to be recommended and attribute information of each reference object in a plurality of reference objects;

[0007] Based on the attribute information of the object to be recommended and the attribute information of each reference object in the plurality of reference objects, determining a target reference object having attribute association with the object to be recommended from the plurality of reference objects;

[0008] Obtaining rating information of the target user for the target reference object;

[0009] Based on the rating information, the attribute information of the object to be recommended, and the attribute information of the target reference object, predicting the rating of the target user for the object to be recommended to obtain a corresponding first predicted rating;

[0010] Determining whether the object to be recommended meets a recommendation condition based on the first prediction score;

[0011] When the object to be recommended meets the recommendation condition, the object to be recommended is recommended to the target user.

[0012] In the above scheme, the target user's score for the object to be recommended is predicted based on the scoring information, the attribute information of the object to be recommended and the attribute information of the target reference object, including: determining the number of attributes of the target reference object based on the attribute information of the target reference object; determining the number of identical attributes between the target reference object and the object to be recommended; and predicting the target user's score for the object to be recommended based on the scoring information, the number of attributes of the target reference object and the number of identical attributes.

[0013] In the above scheme, the attribute information of the reference object includes the release time of the reference object, and determining whether the object to be recommended meets the recommendation conditions based on the first predicted score includes: when there is no user rating information for the object to be recommended, obtaining the rating time of the target user for the target reference object; based on the rating time and the release time of the target reference object, determining the second predicted score of the target user for the object to be recommended; based on the first predicted score and the second predicted score, determining whether the object to be recommended meets the recommendation conditions.

[0014] In the above scheme, there are multiple target reference objects, and determining the second predicted score of the target user for the object to be recommended based on the scoring time and the release time of the target reference object includes: separately determining the time interval between the scoring time of the target user for each target reference object and the release time of the corresponding target reference object; summing the time intervals corresponding to multiple target reference objects to obtain the sum of the time intervals; determining the number of target reference objects, and taking the sum of the number of target reference objects and the time interval as the second predicted score.

[0015] In the above scheme, determining whether the object to be recommended meets the recommendation conditions based on the first predicted score and the second predicted score includes: determining the sum of the first predicted score and the second predicted score; when the sum of the scores is greater than or equal to the score threshold, determining that the object to be recommended meets the recommendation conditions; when the sum of the scores is less than the score threshold, determining that the object to be recommended does not meet the recommendation conditions.

[0016] In the above scheme, determining whether the object to be recommended meets the recommendation conditions based on the first predicted score includes: when there is user rating information for the object to be recommended, obtaining the evaluation reference object evaluated by the target user; obtaining the number of multiple other users who evaluated the evaluation reference object, and the number of reference objects evaluated by each of the multiple other users; the multiple other users do not include the target user; based on the number of the multiple other users and the number of reference objects evaluated by each other user, determining the third predicted score of the target user for the object to be recommended; and determining whether the object to be recommended meets the recommendation conditions based on the first predicted score and the third predicted score.

[0017] In the above scheme, determining whether the object to be recommended meets the recommendation conditions based on the first prediction score and the third prediction score includes: obtaining a first weight corresponding to the first prediction score and a second weight corresponding to the third prediction score; based on the first weight and the second weight, performing a weighted summation of the first prediction score and the third prediction score to obtain a corresponding target prediction score; based on the target prediction score, determining whether the object to be recommended meets the recommendation conditions.

[0018] An embodiment of the present application provides an object recommendation device, comprising:

[0019] A first obtaining module is used to obtain attribute information of the object to be recommended and attribute information of each reference object in a plurality of reference objects;

[0020] a target reference object determining module, configured to determine, from a plurality of reference objects, a target reference object having attribute association with the object to be recommended based on attribute information of the object to be recommended and attribute information of each reference object in the plurality of reference objects;

[0021] A second obtaining module is used to obtain the target user's rating information for the target reference object;

[0022] a rating prediction module, configured to predict a rating of the target user for the object to be recommended based on the rating information, the attribute information of the object to be recommended, and the attribute information of the target reference object, to obtain a corresponding first predicted rating;

[0023] a determination module, configured to determine whether the object to be recommended meets a recommendation condition based on the first prediction score;

[0024] The recommendation module is used to recommend the object to be recommended to the target user when the object to be recommended meets the recommendation conditions.

[0025] An embodiment of the present application provides an electronic device, including:

[0026] a memory for storing executable instructions;

[0027] The processor is configured to implement the object recommendation method provided in the embodiment of the present application when executing the executable instructions stored in the memory.

[0028] An embodiment of the present application provides a computer-readable storage medium storing executable instructions for causing a processor to execute and implement the object recommendation method provided in the embodiment of the present application.

[0029] The embodiments of the present application have the following beneficial effects:

[0030] Obtain attribute information of an object to be recommended and attribute information of each reference object among a plurality of reference objects; determine a target reference object having attribute association with the object to be recommended from a plurality of reference objects based on the attribute information of the object to be recommended and attribute information of each reference object among a plurality of reference objects; obtain rating information of the target user for the target reference object; predict the rating of the target user for the object to be recommended based on the rating information, attribute information of the object to be recommended and attribute information of the target reference object, and obtain a corresponding first predicted rating; determine whether the object to be recommended meets the recommendation conditions based on the first predicted rating; when the object to be recommended meets the recommendation conditions, recommend the object to the target user, so that the recommended object is more in line with the user's preferences. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is an optional structural diagram of the object recommendation system architecture provided in an embodiment of the present application;

[0032] Figure 2 This is an optional structural diagram of the electronic device 200 provided in an embodiment of the present application;

[0033] Figure 3 This is an optional flowchart of the object recommendation method provided in the embodiment of the present application;

[0034] Figure 4 This is an optional detailed flow chart of step 304 provided in an embodiment of the present application;

[0035] Figure 5 This is an optional detailed flow chart of step 305 provided in an embodiment of the present application;

[0036] Figure 6 This is an optional detailed flowchart of step 305 provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0038] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0039] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0041] Based on this, embodiments of the present application provide an object recommendation method, device, electronic device, and computer-readable storage medium, which can make the recommended objects more in line with user preferences.

[0042] First, the object recommendation system provided in the embodiment of the present application is described. Figure 1 , Figure 1 This is an optional architectural diagram of the object recommendation system 100 provided in an embodiment of the present application, in which the terminal 103 is connected to the server 101 via the network 102. In some embodiments, the terminal 103 can be a laptop, a tablet computer, a desktop computer, a smart phone, a dedicated messaging device, a portable gaming device, a smart speaker, a smart watch, etc., but is not limited thereto. The server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (CDN, Content Delivery Network) services, and big data and artificial intelligence platforms. The network 102 can be a wide area network or a local area network, or a combination of the two. The terminal 103 and the server 101 can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiments of the present application.

[0043] Next, the electronic device for implementing the above-mentioned object recommendation method provided in the embodiment of the present application is described. Figure 2 , Figure 2 This is an optional structural diagram of the electronic device 200 provided in the embodiment of the present application. In practical applications, the electronic device 200 can be implemented as Figure 1 The terminal 103 or server 101 in the embodiment of the present invention is an electronic device. Figure 1 Taking the terminal 103 as an example, an electronic device for implementing the object recommendation method according to the embodiment of the present application is described. Figure 2 The electronic device 200 shown includes: at least one processor 201, a memory 205, at least one network interface 202, and a user interface 203. The various components in the electronic device 200 are coupled together via a bus system 204. It is understood that the bus system 204 is used to achieve connection and communication between these components. In addition to including a data bus, the bus system 204 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, the bus system 204 is not described in detail. Figure 2 Various buses are labeled as bus system 204 .

[0044] The processor 201 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0045] The user interface 203 includes one or more output devices 2031 that enable presentation of media content, including one or more speakers and / or one or more visual display screens. The user interface 203 also includes one or more input devices 2032, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

[0046] The memory 205 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard drives, optical drives, etc. The memory 205 may optionally include one or more storage devices that are physically remote from the processor 201.

[0047] The memory 205 includes volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be a read-only memory (ROM), and the volatile memory may be a random access memory (RAM). The memory 205 described in the embodiments of the present application is intended to include any suitable type of memory.

[0048] In some embodiments, the memory 205 can store data to support various operations. Examples of such data include programs, modules, and data structures, or subsets or supersets thereof. In the embodiment of the present application, the memory 205 stores an operating system 2051, a network communication module 2052, a presentation module 2053, an input processing module 2054, and an object recommendation device 2055. Specifically,

[0049] Operating system 2051, including system programs for processing various basic system services and performing hardware-related tasks, such as the framework layer, core library layer, and driver layer, which are used to implement various basic services and process hardware-based tasks;

[0050] A network communication module 2052 for reaching other computing devices via one or more (wired or wireless) network interfaces 202 , exemplary network interfaces 202 including Bluetooth, WiFi, and USB;

[0051] a presentation module 2053 for enabling presentation of information (e.g., a user interface for operating peripheral devices and displaying content and information) via one or more output devices 2031 (e.g., a display screen, a speaker, etc.) associated with the user interface 203;

[0052] The input processing module 2054 is configured to detect one or more user inputs or interactions from one of the one or more input devices 2032 and to translate the detected inputs or interactions.

[0053] In some embodiments, the object recommendation device provided in the embodiments of the present application can be implemented in software. Figure 2 The object recommendation device 2055 stored in the memory 205 is shown. This device can be software in the form of a program or plug-in, and includes the following software modules: a first acquisition module 20551, a target reference object determination module 20552, a second acquisition module 20553, a rating prediction module 20554, a determination module 20555, and a recommendation module 20556. These modules are logical and can be arbitrarily combined or further separated according to the functions they implement. The functions of each module will be described below.

[0054] In other embodiments, the object recommendation device provided in the embodiments of the present application can be implemented in hardware. As an example, the object recommendation device provided in the embodiments of the present application can be a processor in the form of a hardware decoding processor, which is programmed to execute the object recommendation method provided in the embodiments of the present application. For example, the processor in the form of a hardware decoding processor can adopt one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0055] The object recommendation method provided in the embodiment of the present application will be described in conjunction with the exemplary application and implementation of the terminal provided in the embodiment of the present application.

[0056] See also Figure 3 , Figure 3 This is an optional flow chart of the object recommendation method provided in the embodiment of the present application, which will be combined with Figure 3 The steps shown are explained.

[0057] Step 301: Obtain attribute information of the object to be recommended and attribute information of each reference object in a plurality of reference objects;

[0058] Step 302: Based on the attribute information of the object to be recommended and the attribute information of each reference object in the plurality of reference objects, determine a target reference object having attribute association with the object to be recommended from the plurality of reference objects;

[0059] Step 303: obtaining the target user's rating information for the target reference object;

[0060] Step 304: Based on the rating information, the attribute information of the object to be recommended, and the attribute information of the target reference object, predict the target user's rating for the object to be recommended, and obtain a corresponding first predicted rating;

[0061] Step 305: Determine whether the object to be recommended meets the recommendation condition based on the first prediction score;

[0062] Step 306: When the object to be recommended meets the recommendation condition, the object to be recommended is recommended to the target user.

[0063] In actual scenarios, the recommended objects and reference objects involved in the embodiments of the present application are objects of the same type, such as but not limited to videos, music, and commodities. Among them, videos can be but not limited to TV series or movies. The attribute information of the object includes multiple attributes, and the attributes can be but not limited to the name of the object, release time, origin information (such as the country of production or production), object classification, etc. For example, when the object is a movie project, the attribute information of the object can include but is not limited to the movie name, release year (i.e., release time), subject matter (i.e., object classification), country (and object origin information), duration, etc.

[0064] Here, the attribute information of the object to be recommended and the attribute information of multiple reference objects can be stored in the server, and can also be stored in an external storage device that is communicatively connected to the server, such as a database. In actual implementation, the server obtains the attribute information of the object to be recommended and the attribute information of each reference object in the multiple reference objects from a local or external storage device. Then, based on the attribute information of the object to be recommended and the attribute information of each reference object in the multiple reference objects, a target reference object that has an attribute association with the object to be recommended is determined from the multiple reference objects. Here, having an attribute association with the object to be recommended means having at least one identical attribute with the object to be recommended. In some embodiments, having an attribute association with the object to be recommended can also mean that the attribute information is similar to the attribute information of the object to be recommended.

[0065] In the embodiment of the present application, the server compares the attribute information of the object to be recommended with the attribute information of multiple reference objects, and obtains a target reference object with attribute association with the object to be recommended from the multiple reference objects. Here, the number of target reference objects is at least two.

[0066] Next, the server obtains rating information for the target reference objects from at least two target users. Here, the rating information includes the rating values ​​of the target users for the target reference objects. It should be understood that when the target user has not rated a target reference object, the server cannot obtain the rating information of the target reference object. In actual implementation, after obtaining the rating information of the target reference objects, the server predicts the target user's rating for the target reference object based on the rating information of each target reference object, the attribute information of the target reference object, and the attribute information of the target reference object, and obtains a corresponding first predicted rating.

[0067] Specifically, see Figure 4 , Figure 4 This is an optional detailed flow chart of step 304 provided in the embodiment of the present application. Step 304 can also be implemented in the following manner:

[0068] Step 401: determining the number of attributes of the target reference object based on the attribute information of the target reference object;

[0069] Step 402: determining the number of common attributes between the target reference object and the object to be recommended;

[0070] Step 403 : Predicting the target user's rating for the object to be recommended based on the rating information, the number of attributes of the target reference object, and the number of identical attributes.

[0071] In actual implementation, the server counts the number of attributes of the corresponding target reference object based on the attribute information of each target reference object. Then, the target reference object is compared with the attribute information of the object to be recommended, and the same attributes of the target reference object and the object to be recommended are determined, and the number of the same attributes is counted. The server determines the first predicted score of the target user for the object to be recommended based on the score information, the number of attributes of the target reference object, and the number of the same attributes. In one embodiment, the server determines the first predicted score f of the target user u for the object to be recommended by formula (1): a (u):

[0072]

[0073] Among them, AC j Indicates the number of attributes of the target reference object j, IAC l represents the number of target reference objects that share attribute l with the object to be recommended; when the target user u has evaluated the target reference object j, then r uj =1, otherwise, r uj = 0; when the target reference object j has attribute l, then h lj =1, otherwise, h lj =0; p is the number of attributes of the object to be recommended, and n is the number of target reference objects.

[0074] Based on this, the association between the object to be recommended and multiple target reference objects is determined according to the target user's rating information of each target reference object, the attribute information of the object to be recommended, the attribute information of each target reference object, the number of attributes of each target reference object, and the number of target reference objects that have common attributes with the object to be recommended, thereby obtaining the target user's first predicted score for the object to be recommended.

[0075] Next, the server determines whether the object to be recommended meets the recommendation criteria based on the first predicted score. Here, the server can determine whether the object to be recommended meets the recommendation criteria by determining whether the first predicted score reaches a first score threshold. If the first predicted score reaches the first score threshold, the object to be recommended is determined to meet the recommendation criteria. If the first predicted score does not reach the first score threshold, the object to be recommended is determined to not meet the recommendation criteria.

[0076] In some embodiments, the attribute information of the reference object includes the release time of the reference object. Figure 5 , Figure 5 This is an optional detailed flow chart of step 305 provided in an embodiment of the present application. Step 305 can also be implemented in the following manner:

[0077] Step 501: When there is no user rating information for the object to be recommended, obtain the rating time of the target user for the target reference object;

[0078] Step 502: determining a second predicted score of the target user for the object to be recommended based on the scoring time and the release time of the target reference object;

[0079] Step 503: Determine whether the object to be recommended meets the recommendation condition based on the first prediction score and the second prediction score.

[0080] In actual scenarios, the object to be recommended to the target user may be a newly published object and may not have any rating information from any user. In this embodiment of the present application, whether the object to be recommended meets the recommendation conditions is further determined by combining the time when the target user rated the target reference object and the first predicted rating. Specifically, the server obtains the time when the target user rated the target reference object and determines the second predicted rating of the target user for the object to be recommended based on the rating time and the release time of the target reference object.

[0081] Here, there are multiple target reference objects. In some embodiments, step 502 can also be implemented by: determining the time interval between the time when the target user scores each target reference object and the time when the corresponding target reference object is published; summing the time intervals corresponding to the multiple target reference objects to obtain the sum of the time intervals; determining the number of target reference objects, and using the sum of the number of target reference objects and the time intervals as the second predicted score.

[0082] Specifically, the server can determine the second predicted score of the target user u for the object to be recommended by formula (2):

[0083]

[0084] Among them, (time ui -date i ) is smaller, w u The larger the value, the closer the time when the user evaluates the project is to the time when the project is released, which means that the user is more active and likes to pay attention to new things. On the contrary, (time ui -date i ) is larger, w u The smaller the value, the more passive the user is, and they prefer to follow items that have already been followed or reviewed by many users. Formula (2) reflects the average degree to which users prefer to review newly released items. In the process of recommending new items, both active and passive users exist, but new items are recommended to active users first.

[0085] In some embodiments, step 503 can also be implemented in the following manner: determine the sum of the first predicted score and the second predicted score; when the sum of the scores is greater than or equal to the score threshold, determine that the object to be recommended meets the recommendation conditions; when the sum of the scores is less than the score threshold, determine that the object to be recommended does not meet the recommendation conditions.

[0086] In actual implementation, the server sums the first prediction score and the second prediction score to obtain the score sum Based on the ratings and To determine whether the recommended object meets the recommendation conditions.

[0087] In some embodiments, see Figure 6 , Figure 6 This is an optional detailed flow chart of step 305 provided in an embodiment of the present application. Step 305 can also be implemented in the following manner:

[0088] Step 601: When the object to be recommended has user rating information, obtain the evaluation reference object evaluated by the target user;

[0089] Step 602: Obtain the number of multiple other users who have evaluated the evaluation reference object and the number of reference objects evaluated by each of the multiple other users; the multiple other users do not include the target user;

[0090] Step 603: determining a third predicted score of the target user for the object to be recommended based on the number of the multiple other users and the number of reference objects evaluated by each other user;

[0091] Step 604: Determine whether the object to be recommended meets the recommendation condition based on the first prediction score and the third prediction score.

[0092] Here, when the object to be recommended has user rating information, the target user's rating for the object to be recommended is predicted based on the target user's evaluation information of the target reference object, and a corresponding third predicted rating is obtained. The first predicted rating and the third predicted rating are then combined to determine whether the object to be recommended meets the recommendation conditions. Specifically, the server can determine the third predicted rating of the target user u for the object to be recommended using formula (3):

[0093]

[0094] Among them, f u (u) represents the predicted rating value of user u for the target reference object j. If user u evaluates item j, then r uj =1; otherwise, r uj = 0. If user k evaluates item j, then r kj =1; otherwise, r kj = 0. IC k Indicates the number of items evaluated by user k, UC j Denotes the number of users who jointly rated item j. Then, based on the user's rating information on the item, the number of items rated by the user, and the number of times the item has been rated by the user, a predicted rating value based on the item rating information can be defined to mine the relationship between them.

[0095] In some embodiments, step 604 can also be implemented in the following manner: obtain a first weight corresponding to the first prediction score and a second weight corresponding to the third prediction score; based on the first weight and the second weight, perform weighted summation on the first prediction score and the third prediction score to obtain a corresponding target prediction score; based on the target prediction score, determine whether the object to be recommended meets the recommendation conditions.

[0096] Specifically, the server may calculate the weighted sum of the first prediction score and the third prediction score by using formula (4):

[0097]

[0098] Among them; UC j represents the number of users who jointly evaluate item j; w u is the time weight of user u. If project j is a new project, then UC j =0; otherwise; UC j ≠0. Whether it is a new project or a project that has been evaluated, it will have its own attribute information. On the other hand, user time weight information refers to the time interval between the user's rating time and the project release time. It has nothing to do with whether the project is new or not. However, user time weight information can directly reflect the user's preference for the project from another perspective.

[0099] In an embodiment of the present application, attribute information of an object to be recommended and attribute information of each reference object among a plurality of reference objects are obtained; based on the attribute information of the object to be recommended and attribute information of each reference object among a plurality of reference objects, a target reference object having attribute association with the object to be recommended is determined from a plurality of reference objects; rating information of the target user for the target reference object is obtained; based on the rating information, attribute information of the object to be recommended and attribute information of the target reference object, the target user's rating for the object to be recommended is predicted to obtain a corresponding first predicted rating; based on the first predicted rating, whether the object to be recommended meets the recommendation conditions is determined; when the object to be recommended meets the recommendation conditions, the object to be recommended is recommended to the target user, so that the recommended object can be more in line with the user's preferences.

[0100] The following continues to describe the exemplary structure of the object recommendation device 555 provided in the embodiment of the present application implemented as a software module. In some embodiments, such as Figure 2 As shown, the software modules stored in the object recommendation device 20551 of the memory 2055 may include:

[0101] A first obtaining module is used to obtain attribute information of the object to be recommended and attribute information of each reference object in a plurality of reference objects;

[0102] a target reference object determining module, configured to determine, from a plurality of reference objects, a target reference object having attribute association with the object to be recommended based on attribute information of the object to be recommended and attribute information of each reference object in the plurality of reference objects;

[0103] A second obtaining module is used to obtain the target user's rating information for the target reference object;

[0104] a rating prediction module, configured to predict a rating of the target user for the object to be recommended based on the rating information, the attribute information of the object to be recommended, and the attribute information of the target reference object, to obtain a corresponding first predicted rating;

[0105] a determination module, configured to determine whether the object to be recommended meets a recommendation condition based on the first prediction score;

[0106] The recommendation module is used to recommend the object to be recommended to the target user when the object to be recommended meets the recommendation conditions.

[0107] In some embodiments, the rating prediction module is also used to: determine the number of attributes of the target reference object based on the attribute information of the target reference object; determine the number of identical attributes between the target reference object and the object to be recommended; and predict the target user's rating for the object to be recommended based on the rating information, the number of attributes of the target reference object, and the number of identical attributes.

[0108] In some embodiments, the attribute information of the reference object includes the release time of the reference object, and the determination module is further used to: when there is no user rating information for the object to be recommended, obtain the rating time of the target user for the target reference object; based on the rating time and the release time of the target reference object, determine the second predicted rating of the target user for the object to be recommended; based on the first predicted rating and the second predicted rating, determine whether the object to be recommended meets the recommendation conditions.

[0109] In some embodiments, there are multiple target reference objects, and the rating prediction module is further used to: respectively determine the time interval between the rating time of the target user for each target reference object and the release time of the corresponding target reference object; sum the time intervals corresponding to multiple target reference objects to obtain the sum of the time intervals; determine the number of target reference objects, and use the sum of the number of target reference objects and the time interval as the second predicted rating.

[0110] In some embodiments, the determination module is further used to: determine the sum of the first predicted score and the second predicted score; when the sum of the scores is greater than or equal to a score threshold, determine that the object to be recommended meets the recommendation conditions; when the sum of the scores is less than the score threshold, determine that the object to be recommended does not meet the recommendation conditions.

[0111] In some embodiments, the determination module is further used to: when there is user rating information for the object to be recommended, obtain the evaluation reference object evaluated by the target user; obtain the number of multiple other users who evaluate the evaluation reference object, and the number of reference objects evaluated by each of the multiple other users; the multiple other users do not include the target user; based on the number of the multiple other users and the number of reference objects evaluated by each other user, determine the third predicted rating of the target user for the object to be recommended; based on the first predicted rating and the third predicted rating, determine whether the object to be recommended meets the recommendation conditions.

[0112] In some embodiments, the determination module is further used to: obtain a first weight corresponding to the first prediction score and a second weight corresponding to the third prediction score; based on the first weight and the second weight, perform a weighted sum of the first prediction score and the third prediction score to obtain a corresponding target prediction score; based on the target prediction score, determine whether the object to be recommended meets the recommendation conditions.

[0113] The present invention provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the object recommendation method described above in the present invention.

[0114] An embodiment of the present application provides a computer-readable storage medium storing executable instructions, wherein the executable instructions are stored. When the executable instructions are executed by a processor, the processor will execute the method provided by the embodiment of the present application.

[0115] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface storage, optical disk, or CD-ROM; or various devices including one or any combination of the above memories.

[0116] In some embodiments, executable instructions may be in the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0117] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinating files (e.g., files storing one or more modules, subroutines, or code portions).

[0118] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0119] In summary, the embodiments of the present application can make the objects recommended to users more in line with user preferences.

[0120] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent replacements, and improvements made within the spirit and scope of the present application are included in the scope of protection of the present application.

Claims

1. An object recommendation method, characterized in that: include: Obtaining attribute information of the object to be recommended and attribute information of each reference object in a plurality of reference objects; Based on the attribute information of the object to be recommended and the attribute information of each reference object in the plurality of reference objects, determining a target reference object having attribute association with the object to be recommended from the plurality of reference objects; Obtaining rating information of the target user for the target reference object; Based on the rating information, the attribute information of the object to be recommended, and the attribute information of the target reference object, predicting the rating of the target user for the object to be recommended to obtain a corresponding first predicted rating; Determining whether the object to be recommended meets a recommendation condition based on the first prediction score; When the object to be recommended meets the recommendation condition, recommending the object to be recommended to the target user; The attribute information of the reference object includes the release time of the reference object, and determining whether the object to be recommended meets the recommendation condition based on the first prediction score includes: When there is no user rating information for the object to be recommended, obtaining the rating time of the target user for the target reference object, where the number of the target reference objects is multiple; respectively determining the time interval between the scoring time of each target reference object by the target user and the publishing time of the corresponding target reference object; Summing the time intervals corresponding to the multiple target reference objects to obtain the sum of the time intervals; determining the number of the target reference objects, and taking a ratio of the number of the target reference objects to the sum of the time intervals as a second prediction score; Based on the first prediction score and the second prediction score, it is determined whether the object to be recommended meets the recommendation condition.

2. The object recommendation method according to claim 1, wherein: The predicting, based on the rating information, the attribute information of the to-be-recommended object, and the attribute information of the target reference object, of the target user's rating for the to-be-recommended object includes: Determining the number of attributes of the target reference object based on the attribute information of the target reference object; Determining the number of common attributes between the target reference object and the object to be recommended; Based on the rating information, the number of attributes of the target reference object, and the number of the same attributes, a rating of the target user for the object to be recommended is predicted.

3. The object recommendation method according to claim 1, wherein: The determining whether the object to be recommended meets the recommendation condition based on the first prediction score and the second prediction score includes: determining a sum of the first prediction score and the second prediction score; When the score sum is greater than or equal to the score threshold, determining that the object to be recommended meets the recommendation condition; When the sum of the scores is less than a score threshold, it is determined that the object to be recommended does not meet the recommendation condition.

4. The object recommendation method according to claim 1, wherein: The determining, based on the first prediction score, whether the object to be recommended meets the recommendation condition includes: When the object to be recommended has user rating information, obtaining the evaluation reference object evaluated by the target user; Obtaining the number of multiple other users who have evaluated the evaluation reference object and the number of reference objects evaluated by each of the multiple other users; the multiple other users do not include the target user; determining, based on the number of the multiple other users and the number of reference objects evaluated by each other user, a third predicted score of the target user for the object to be recommended; Based on the first prediction score and the third prediction score, it is determined whether the object to be recommended meets the recommendation condition.

5. The object recommendation method according to claim 4, characterized in that The determining whether the to-be-recommended object meets a recommendation condition based on the first prediction score and the third prediction score includes: Obtaining a first weight corresponding to the first prediction score and a second weight corresponding to the third prediction score; Based on the first weight and the second weight, performing a weighted summation on the first prediction score and the third prediction score to obtain a corresponding target prediction score; Based on the target prediction score, determine whether the object to be recommended meets the recommendation conditions.

6. An object recommendation device, characterized in that: include: A first obtaining module is used to obtain attribute information of the object to be recommended and attribute information of each reference object in a plurality of reference objects; a target reference object determining module, configured to determine, from a plurality of reference objects, a target reference object having attribute association with the object to be recommended based on attribute information of the object to be recommended and attribute information of each reference object in the plurality of reference objects; A second obtaining module is used to obtain the target user's rating information for the target reference object; a rating prediction module, configured to predict a rating of the target user for the object to be recommended based on the rating information, the attribute information of the object to be recommended, and the attribute information of the target reference object, to obtain a corresponding first predicted rating; a determination module, configured to determine whether the object to be recommended meets a recommendation condition based on the first prediction score; A recommendation module, configured to recommend the object to be recommended to the target user when the object to be recommended meets the recommendation conditions; The attribute information of the reference object includes the release time of the reference object, and the determining module is further configured to obtain the rating time of the target user for the target reference object when no user rating information exists for the to-be-recommended object, and the number of the target reference objects is multiple; respectively determining the time interval between the scoring time of each target reference object by the target user and the publishing time of the corresponding target reference object; Summing the time intervals corresponding to the multiple target reference objects to obtain the sum of the time intervals; determining the number of the target reference objects, and taking a ratio of the number of the target reference objects to the sum of the time intervals as a second prediction score; Based on the first prediction score and the second prediction score, it is determined whether the object to be recommended meets the recommendation condition.

7. An electronic device, characterized in that: include: a memory for storing executable instructions; The processor is configured to implement the object recommendation method according to any one of claims 1 to 5 when executing the executable instructions stored in the memory.

8. A computer-readable storage medium, characterized in that Executable instructions are stored, and when executed by a processor, the object recommendation method according to any one of claims 1 to 5 is implemented.

Images