CN113495996B

CN113495996B - Object recommendation method, device, equipment and medium

Info

Publication number: CN113495996B
Application number: CN202010193379.8A
Authority: CN
Inventors: 王志华
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2020-03-18
Filing date: 2020-03-18
Publication date: 2024-02-23
Anticipated expiration: 2040-03-18
Also published as: CN113495996A

Abstract

The disclosure relates to an object recommendation method, device, equipment and medium, which are used for solving the problem that an object recommended by the existing object recommendation method is not diversified enough. When recommending the same type of object, acquiring an access object currently accessed by a target account, and determining attribute content of an appointed attribute of the access object according to the object type of the access object and different attributes corresponding to each stored object type, wherein the appointed attribute is at least one attribute corresponding to the object type of the access object; taking attribute contents of other attributes meeting the condition of the relevance value as target attribute contents through the relevance value among attribute contents contained in different attributes; recommending the information of the recommended object corresponding to each target attribute content to the target account according to the heat degree of the object type, wherein the heat degree is used for representing the concerned state of the corresponding object by other accounts, so that the recommended object is more diversified, and the click rate of the account selection recommended object is improved.

Description

Object recommendation method, device, equipment and medium

Technical Field

The disclosure relates to the technical field of information recommendation, and in particular relates to an object recommendation method, device, equipment and medium.

Background

With the development of diversification of objects for account access along with the advancement of technology, the amount of information generated by account access to various types of objects has exponentially increased. How to recommend objects of possible interest to an account from a large number of objects is a hot spot of research in recent years.

In the prior art, when recommending the information of the object to the target account by adopting a deep learning method, recommending the information of the object associated with the historical access object of the target account through some algorithms and the historical operation information of the account which is saved in advance. But this approach may appear to referral information of objects of interest to fewer accounts to the target account, thereby placing some limitations on the application of the approach.

For traditional collaborative filtering algorithms, recommendations may be made based on information of objects associated with information of historical access objects of a number of accounts. But the method is generally based on the relevance value of the account to recommend an object, or based on the relevance value of the item. The method has the advantages that the recommended objects can be recommended to the account only according to the correlation value between the articles and the correlation value between the accounts, so that the recommended objects are not diversified enough, and the possibility that the recommended objects are accessed by the account cannot be guaranteed.

Disclosure of Invention

The disclosure provides an object recommendation method, device, equipment and medium, which are used for solving the problem that the objects recommended by the existing object recommendation method are not diversified enough. The technical scheme of the present disclosure is as follows:

according to a first aspect of embodiments of the present disclosure, there is provided an object recommendation method, the method including:

acquiring an access object currently accessed by a target account, and determining attribute contents of specified attributes of the access object according to the object type of the access object and different attributes corresponding to each stored object type, wherein the specified attributes are at least one attribute corresponding to the object type of the access object;

according to the correlation value of each attribute content of other attributes of the object type and the attribute content of the specified attribute, taking the attribute content of the other attributes meeting the condition of the correlation value as target attribute content;

recommending the information of the recommended object corresponding to each target attribute content to the target account according to the heat degree of the object type, wherein the heat degree is used for representing the state of the corresponding object, which is focused by other accounts.

Further, recommending the information of the recommended object corresponding to each target attribute content to the target account according to the heat of the object type includes:

Determining the information of candidate objects corresponding to each target attribute content according to the heat degree of the object type;

and recommending the information of the set number of candidate objects corresponding to each target attribute content to the target account as information of recommended objects.

Further, determining each attribute content of the other attributes of the object type, a relevance value to the attribute content of the specified attribute includes:

acquiring attribute contents of the other attributes of each associated object operated by the account and operation events of each associated object aiming at each account of the object operating the attribute contents of the designated attribute;

for each attribute content of the other attributes, determining the weight sum of the attribute content according to the operated times corresponding to each operation event of each associated object of the attribute content; and determining the relevance value of the attribute contents of the other attributes and the attribute contents of the specified attributes according to the weight sum of the attribute contents, the account number of the associated objects operating the attribute contents and the account number of the objects operating the attribute contents of the specified attributes.

Further, the determining the weight sum of the attribute content according to the operated times corresponding to each operation event of each associated object of the attribute content includes:

for each associated object of the attribute content, determining the weight sum of the associated object according to the stored corresponding relation between the operation event and the weight value and the operated times corresponding to each operation event corresponding to the associated object;

and determining the weight sum of the attribute content according to the weight sum corresponding to each associated object of the attribute content.

Further, the associated object is the first object operated by the account after the object of the attribute content of the specified attribute is operated.

Further, the method further comprises:

and updating the relevance value of each determined attribute content of the other attributes and the attribute content of the designated attribute according to the historical operation information of the account and the operation information of the account in a time range corresponding to the time interval according to the set time interval.

Further, according to the set time interval, updating the relevance value between each determined attribute content of the other attributes and the attribute content of the designated attribute according to the historical operation information of the account and the operation information of the account in the time range corresponding to the time interval includes:

Updating the saved weight sum of the attribute content, the account number of the object operating the attribute content and the account number of the object operating the attribute content of the specified attribute according to the weight sum of the attribute content, the account number of the associated object operating the attribute content and the account number of the object operating the attribute content of the specified attribute, which are determined in the time range, for each attribute content of the other attributes;

and updating the relevance value of the attribute content of the other attributes and the attribute content of the specified attribute according to the updated weight sum of the attribute content, the account number of the object operating the attribute content and the account number of the object operating the attribute content of the specified attribute aiming at each attribute content of the other attributes.

Further, the attribute corresponding to each object type includes at least one of an identification of the object, a style of the object, and a source of the object.

According to a second aspect of embodiments of the present disclosure, there is provided an object recommendation apparatus, the apparatus comprising:

the access control system comprises an acquisition unit, a storage unit and a storage unit, wherein the acquisition unit is configured to execute an access object currently accessed by a target account, and determine attribute contents of specified attributes of the access object according to the object type of the access object and different attributes corresponding to each stored object type, wherein the specified attributes are at least one attribute corresponding to the object type of the access object;

A processing unit configured to execute a correlation value with the attribute contents of the specified attribute according to each attribute content of the other attributes of the object type, taking the attribute contents of the other attributes satisfying a correlation value condition as target attribute contents;

and the recommending unit is configured to execute the heat degree of the object according to the object type, and recommend the information of the recommended object corresponding to each target attribute content to the target account, wherein the heat degree is used for representing the state of the corresponding object focused by other accounts.

Further, the recommending unit is specifically configured to determine information of candidate objects corresponding to each target attribute content according to the heat degree of the object type; and recommending the information of the set number of candidate objects corresponding to each target attribute content to the target account as information of recommended objects.

Further, the processing unit is specifically configured to execute each account of the object for operating the attribute content of the specified attribute, acquire the attribute content of the other attribute of each associated object operated by the account, and operate the event for each associated object; for each attribute content of the other attributes, determining the weight sum of the attribute content according to the operated times corresponding to each operation event of each associated object of the attribute content; and determining the relevance value of the attribute contents of the other attributes and the attribute contents of the specified attributes according to the weight sum of the attribute contents, the account number of the associated objects operating the attribute contents and the account number of the objects operating the attribute contents of the specified attributes.

Further, the processing unit is specifically configured to execute each associated object of the attribute content, and determine a weight sum of the associated object according to the saved corresponding relation between the operation event and the weight value and the operated times corresponding to each operation event corresponding to the associated object; and determining the weight sum of the attribute content according to the weight sum corresponding to each associated object of the attribute content.

Further, the apparatus further comprises:

and the updating unit is configured to update the relevance value of each determined attribute content of the other attributes and the attribute content of the designated attribute according to the set time interval, the historical operation information of the account and the operation information of the account in a time range corresponding to the time interval.

Further, the updating unit is specifically configured to perform updating of the saved weight sum of the attribute content, the account number of the object operating the attribute content, and the account number of the object operating the attribute content of the specified attribute according to the determined weight sum of the attribute content in the time range, the account number of the associated object operating the attribute content in the time range, and the account number of the object operating the attribute content of the specified attribute for each attribute content of the other attributes; and updating the relevance value of the attribute content of the other attributes and the attribute content of the specified attribute according to the updated weight sum of the attribute content, the account number of the object operating the attribute content and the account number of the object operating the attribute content of the specified attribute aiming at each attribute content of the other attributes.

According to a third aspect of embodiments of the present disclosure, there is provided an electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the object recommendation method of any one of the above.

According to a fourth aspect of embodiments of the present disclosure, there is provided a storage medium, which when executed by a processor of an electronic device, causes the processor to perform any one of the above-described object recommendation methods.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising: program code for enabling an electronic device to perform an object recommendation method as described above, when said computer program product is executed by said electronic device.

The technical scheme provided in the embodiment of the disclosure at least brings the following beneficial effects:

in the process of object recommendation, an access object currently accessed by a target account is obtained, and attribute content of an appointed attribute of the access object is determined according to the object type of the access object and different attributes corresponding to each stored object type, wherein the appointed attribute is at least one attribute corresponding to the object type of the access object; according to each attribute content of other attributes of the object type and the correlation value of the attribute content of the appointed attribute, taking the attribute content of the other attributes meeting the condition of the correlation value as target attribute content; recommending the information of the recommended object corresponding to each target attribute content to the target account according to the heat degree of the object type, wherein the heat degree is used for representing the state of the corresponding object, which is focused by other accounts. When the object recommendation is carried out aiming at the same object type, the object is recommended to the account through the correlation value among the attribute contents contained in different attributes, so that the recommended object is more diversified, and the click rate of the account selection recommended object is improved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure and do not constitute an undue limitation on the disclosure.

FIG. 1 is a flow diagram illustrating an object recommendation method according to an exemplary embodiment;

FIG. 2 is a schematic diagram illustrating a specific object recommendation process, according to an example embodiment;

FIG. 3 is a graph of relevance values of each attribute content of other attributes to each attribute content of a specified attribute, as shown in accordance with an exemplary embodiment;

FIG. 4 is a schematic diagram illustrating a specific object recommendation process, according to an example embodiment;

FIG. 5 is a block diagram of an object recommendation device, according to an example embodiment;

fig. 6 is a block diagram of an electronic device, according to an example embodiment.

Detailed Description

In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.

Fig. 1 is a flow chart illustrating an object recommendation method according to an exemplary embodiment, the object recommendation method including the steps of:

in step S101, an access object currently accessed by a target account is obtained, and attribute content of a specified attribute of the access object is determined according to an object type of the access object and different attributes corresponding to each stored object type, wherein the specified attribute is at least one attribute corresponding to the object type of the access object.

The object recommendation method provided by the disclosure can be applied to electronic equipment, and particularly to intelligent terminals such as mobile terminals, tablet computers, PCs and the like. In addition, the object recommendation method of the present disclosure may be to recommend various types of objects such as video, audio, pictures, novels, articles, and the like.

In specific implementation, when an access object currently accessed by a target account is identified, determining an object type of the access object, determining a designated attribute corresponding to the access object according to a corresponding relation between the object type and the attribute, and acquiring attribute content of the designated attribute of the access object.

In the embodiment of the present disclosure, the obtained specified attribute of the access object is different for different object types, and in order to facilitate object recommendation, the object type of the access object needs to be determined. Specifically, when determining the object type of the access object, the object type of the access object may be determined according to the object type identifier included in the uniform resource locator (Uniform Resource Locator, URL) of the access object, for example, if the object type identifier included in the URL of the access object is "jpg", the access object is determined to be a picture; if the object type contained in the URL of the access object is identified as 'mp 4', determining that the access object is video; if the object type contained in the URL of the access object is identified as "txt", the access object is determined to be text.

The corresponding attributes will also be different due to the different object types. Therefore, in the disclosure, different attributes corresponding to each object type are saved in advance. Such as: when the access object is a novel, the attribute corresponding to the novel can be keywords, publishers, styles and the like; when the access object is an article, the attribute corresponding to the article may be manufacturer, price, shipping place, etc.

Optionally, in this disclosure, the attribute corresponding to each object type includes: at least one of identification of the object, style of the object, source of the object, and the like. The identification of the object is the name of the object, the ID of the object, etc., and specifically, if the object is a video, the name of the video, the ID of the video, etc. The style of the object is also different according to the content contained in the object type, for example, if the object is a picture, the style of the object may be sadness, freshness, etc., and if the object is a video, the style of the object may be comedy, historic drama, etc. The source of the object may be different according to the content contained in the object type, for example, if the object is an article, the source of the object may be a shipment place of the article, a manufacturer of the article, or the like, and if the object is a video, the source of the object may be an ID of a publisher of the video, a sponsor of the video, or the like.

In order to accurately recommend an object to an account, in the embodiment of the present disclosure, when determining an object type of an access object and different attributes corresponding to the object type, determining a specified attribute of the access object may take at least one attribute of the different attributes corresponding to the object type of the access object as the specified attribute, for example, take any one of the different attributes corresponding to the object type of the access object as the specified attribute, or take each attribute corresponding to the object type of the access object as the specified attribute.

In another possible implementation manner, the designated attribute corresponding to each object type may also be preset. At least one attribute of each object type may be taken as a specified attribute when the specified attribute is specifically set. For example, when the access object is a novel, the specified attribute may be a keyword or the like; when the access object is an article, the specified attribute may be a delivery place, a shipper, or the like.

In step S102, according to the relevance value of each attribute content of the other attributes of the object type and the attribute content of the specified attribute, the attribute content of the other attributes satisfying the relevance value condition is taken as the target attribute content.

For each object type in this disclosure, attributes of that object type other than the specified attribute may be considered other attributes. For example, if the object is a picture, the attributes of the picture include: the keywords, the styles and the publishers are other attributes of the object after the keywords are taken as the appointed attributes of the picture.

Further, in order to accurately recommend objects to an account, in the embodiment of the disclosure, for each attribute content of a specified attribute, a relevance value of each attribute content of other attributes to the attribute content of the specified attribute is saved. Therefore, after the attribute contents of the specified attribute of the access object are obtained, each attribute content included in the stored other attributes is determined, the relevance value of the attribute content is related to the attribute content, the attribute content of the other attribute meeting the relevance value condition is taken as the target attribute content, specifically, the attribute content of the first set number of other attribute with the higher relevance value is taken as the target attribute content, and then corresponding processing is performed based on each target attribute content, so that recommendation to the target account is realized.

If the other attributes only comprise one attribute, after the attribute contents of the specified attribute are obtained, determining the relevance value of each attribute content contained in the stored other attribute and the attribute contents of the specified attribute, wherein the relevance value is larger, taking the first set number of attribute contents as target attribute contents, and then carrying out corresponding processing based on each target attribute content, thereby realizing recommendation to the target account.

For example, the obtained designated attribute is price, the other attributes are manufacturers, and the first set number is 1. When the price of the object currently accessed by the target account is R, the relevance value of each attribute content manufacturer A, manufacturer B and manufacturer C contained in other attributes of the stored manufacturer is obtained, wherein the manufacturer with the largest relevance value is manufacturer B, and the manufacturer B is taken as the target attribute content.

If the other attributes comprise at least two kinds of attributes, after the attribute contents of the specified attributes are obtained, determining the relevance value of each attribute content contained in each other attribute and the attribute contents of the specified attributes, taking the attribute contents with a first set number and larger relevance value as target attribute contents, and then carrying out corresponding processing based on each target attribute content, thereby realizing recommendation to the target account.

For example, the acquired designated attribute is price, other attributes are manufacturer, and style, and the first set number is 1. And when the price of the object currently accessed by the target account is R, taking the style 1 with the largest correlation value as target attribute content according to the correlation values of the saved factories A, B and C and the price R and the correlation values of the saved styles 1, 2 and 3 and the price R.

The first set number may be flexibly set according to actual requirements, which is not specifically limited herein.

In step S103, according to the heat degree of the object type, the information of the recommended object corresponding to each target attribute content is recommended to the target account, where the heat degree is used to represent the state of the corresponding object that is focused by other accounts.

Because a large number of objects are corresponding to each target attribute content, if each object is recommended to the account, the account cannot conveniently and quickly select the interested object, so that account experience is reduced. Therefore, in order to further accurately recommend objects to an account, in the embodiment of the present disclosure, objects corresponding to each target attribute content are filtered according to the heat of the objects of the object type, so as to determine recommended objects corresponding to each target attribute content, and information of each recommended object is recommended to the target account. Wherein, the heat is used to represent the state of the corresponding object that is focused on by other accounts.

Specifically, according to the state that the object of the object type is focused on by other accounts, the object corresponding to each target attribute content is screened, so that a recommended object corresponding to each target attribute content is determined, and the information of each recommended object is recommended to the target account.

Note that the recommended object is the same as the object type of the access object.

In the process of object recommendation, an access object currently accessed by a target account is obtained, and attribute content of an appointed attribute of the access object is determined according to the object type of the access object and different attributes corresponding to each stored object type; according to the correlation value of each attribute content of other attributes of the object type and the attribute content of the appointed attribute, taking the attribute content of the other attributes meeting the condition of the correlation value as target attribute content; and recommending the information of the recommended object corresponding to each target attribute content to the target account according to the heat of the object type. When the object recommendation is carried out aiming at the same object type, the object is recommended to the account through the correlation value among the attribute contents contained in different attributes, so that the recommended object has more diversity, and the click rate of the account selection recommended object is improved.

In order to further accurately recommend an object to an account, in the embodiment of the present disclosure, recommending information of a recommendation object corresponding to each target attribute content to the target account according to the popularity of the object type includes:

According to the heat degree of the object type, determining the information of candidate objects corresponding to the set number of candidates of each target attribute content;

and recommending the information of the object corresponding to each target attribute content to the target account as the information of the recommended object.

In an actual application scenario, for each target attribute content, a large number of objects are generally corresponding to the target attribute content, so that according to the heat of the objects of the object type, a part of objects can be screened out as candidate objects corresponding to the target attribute content.

When information of an object is recommended to an account, the account selects an object to be accessed from the recommended objects, and in general, the account accesses an object which is not accessed before, and for the object which is accessed before, the account is likely not to continue to access. If an object previously accessed by an account is recommended to the account, the likelihood of the account clicking on the recommended object is reduced and the account experience is reduced.

In the embodiment of the disclosure, the heat degree of the object is used to represent the state of the corresponding object that is closed by other accounts, according to the heat degree of the object type, the candidate object that is corresponding to each target attribute content and is not accessed by the target account can be determined, and for each candidate object, the set number of candidate objects are recommended to the target account as recommended objects, so that the click rate of the account is improved, and the account experience is improved.

To determine recommended objects, the status of the object being focused on by other accounts may be represented by the access frequency of the object by other accounts, the collection frequency by other accounts, the forwarding frequency by other accounts, the praise frequency by other accounts, and so forth. For example, if the popularity of the object is represented as the access frequency of the object by other accounts, the access frequency of the object by other accounts of each object corresponding to the target attribute content is obtained for each target attribute content, and a second set number of objects with more access frequencies by other accounts are screened out. If the heat degree of the object is embodied as the praise frequency of the object by other accounts, the praise frequency of each object corresponding to the target attribute content by other accounts is acquired for each target attribute content, and the objects with the second set number and more praise frequencies by other accounts are screened out.

In the implementation process, the heat degree of the object can be represented by the state that any one of the objects is focused by other accounts, or the heat degree of the object can be represented by at least two states of the object focused by other accounts. For example, the heat degree of the object is represented by the access frequency of the object by other accounts and the collection frequency of the object by other accounts, then the access frequency of each object corresponding to the target attribute content by other accounts and the collection frequency of the object by other accounts are respectively obtained, and a second set number of objects with more access frequencies by other accounts and more collection frequencies by other accounts are used as candidate objects of the target attribute content object. Specifically, the heat of the object can be flexibly set according to actual requirements.

In addition, since the click rate of the user is further increased when the object which is recently released and is focused on by the other account is generally recommended to the target user, the second set number of objects which are highly hot and are recently released can be used as candidates for the target attribute content object according to the hot degree of the object and the release time of the object. For example, if the heat of the object is characterized as the access frequency of the corresponding object by other accounts, the release time of each object corresponding to the target attribute content and the access frequency of the other accounts are respectively obtained, and the object with the second set number which is recently released and has the higher access frequency by the other accounts is used as the candidate object corresponding to the target attribute content.

FIG. 2 is a schematic diagram of a particular object recommendation process, according to an example embodiment, the process comprising:

s201: an access object currently accessed by the target account is identified.

S202: determining the object type of the access object, determining the designated attribute corresponding to the access object according to the stored different attributes corresponding to each object type, and acquiring the attribute content of the designated attribute of the access object.

The appointed attribute is at least one attribute corresponding to the object type of the access object.

S203: and taking the attribute contents of other attributes meeting the condition of the correlation value as target attribute contents according to the correlation value of each attribute content of other attributes of the object type and the attribute contents of the designated attributes.

S204: and determining the information of the candidate object corresponding to each target attribute content according to the heat of the object type.

Wherein, the heat is used to represent the state of the corresponding object that is focused on by other accounts. Specifically, if the state of the object focused by the other accounts is the access frequency of the object by the other accounts, the process of determining the information of the candidate object corresponding to each target attribute content includes: and aiming at each target attribute content, acquiring the access frequency of each object corresponding to the target attribute content by other accounts, and taking the objects with a second set number, which are more in access frequency by other accounts, as candidate objects corresponding to the target attribute content.

The value of the second set number is not smaller than the set number.

S205: and recommending the information of the candidate objects with the set number corresponding to each target attribute content to the target account as the information of the recommended object.

In order to further accurately recommend an object to an account, in the embodiments of the present disclosure, determining, based on the above embodiments, each attribute content of other attributes of the object type, a relevance value of the attribute content of the specified attribute includes:

In the implementation, the video class object is taken as an example for explanation, the appointed attribute corresponding to the video class object is the identification of the author of the video, and the other attributes are the video styles. If the account operation is acquired, the ID of the author of the video A is acquired, for example, the account operation is yellow. There may be multiple videos published in the yellow, for example, the published videos include: video a, video B, and video C.

While different videos may be operated by different accounts, e.g., account 1 operated on video a, account 2 operated on video B, and account 3 operated on video a and video B. Thus, it is known that an account that has operated on video published somewhere in yellow includes: account 1, account 2, and account 3.

According to the above operation information, it can be determined that the account 1 operates the video E and the video F, the account 2 operates the video G, the account 3 operates the video G and the video F, specifically, the account 1 performs the collection operation on the video E, the approval operation on the video F, the account 2 performs the collection operation and the attention operation on the video G, and the account 3 performs the approval operation and the collection operation on the video G.

Because the other attribute is video genre and video E is comedy, video F's video grid is a historical play and video G's video genre is comedy.

Because the operation events performed by the account on the objects with different object types may be different, for example, if the object is a picture, the operation events performed by the account on the picture may be a downloading operation, a praying operation, a collecting operation, etc.; if the object is a video, the operation event of the account on the video can be a praise operation, a collection operation, a focus operation and the like; if the object is an item, the operation time of the account on the item may be a collection operation, a focus operation, a purchase operation, or the like.

For each object type, the operation event of the account on the object can reflect the interest degree of the account on the object. For example, when a video is still taken as an object, and an account operates a certain video, if the account performs a praise operation on the video, the account is higher in interest in the video, and the likelihood of comparing the happy video and subsequently accessing the video is not high; if the video is collected, the account is highly interested in the video, not only like the video but also follow-up is likely to continue accessing the video. Thus, for each type of object, different operational events of the object may be set with different weight values, and the operational events of the object may be ordered from large to small in weight values. For example, if the object is a picture, the operation events of the picture are sequenced into downloading operation, collecting operation and praise operation according to the weight value from big to small; if the object is a video, sequencing the operation events of the video from large to small according to the weight value into attention operation, collection operation and praise operation; and if the object is an article, sorting the operation events of the article into purchasing operation, focusing operation and collecting operation according to the weight value from large to small.

According to the operation information, determining that the video with the video style of comedy has a video E and a video G, aiming at the video E, only performing praise operation when the video E is operated by an account 1, wherein the corresponding operated times are 1, and determining the weight sum of the video E of the comedy according to a preset weight value corresponding to the praise operation; for the video G, the collection operation and the attention operation are performed when the account 2 operates the video G, and the praise operation and the collection operation are performed when the account 3 operates the video G. In summary, the number of operated times corresponding to the collection operation is 2, the number of operated times corresponding to the attention operation is 1, the number of operated times corresponding to the praise operation is 1, and the weight sum of the video G of the comedy is determined according to the preset weight value corresponding to each operation event.

And determining the weight sum of the comedy according to the obtained weight sum of the video E of the comedy and the weight sum of the video G of the comedy.

Specifically, the determining the weight sum of the attribute content according to the number of operated times corresponding to each operation event of each associated object of the attribute content includes:

Because the weight values corresponding to different operation events are different, in the embodiment of the disclosure, the corresponding relationship between the operation event and the weight value is preset. Taking the above example as the case, the weight value corresponding to the like operation is 3, the weight value corresponding to the collection operation is 5, the weight value corresponding to the attention operation is 10, when determining a certain weight sum of comedy and yellow, the weight sum of video E of comedy is determined to be 1*3 =3 for video E, and the weight sum of video G of comedy is determined to be 1×3+2×5+1×10=23 for video G. The obtained weight sum of the video E of the comedy and the weight sum of the video G of the comedy are added, that is, 3+23=26, and the weight sum of the comedy is determined to be 26.

The weight sum of the historical drama is determined in the same way as the weight sum of the comedy, and is not described in detail herein.

When the weight sum of the comedy is obtained, a relevance value of the comedy to the video may be determined based on the weight sum of the comedy, the number of accounts operating the video of the comedy, and the number of accounts operating the video of the yellow. The more the account number of the object of a certain attribute content of other attributes is operated and the account number of a certain attribute content of a specified attribute is operated, the lower the correlation value between the attribute content of other attributes and the attribute content of the specified attribute is; the greater the weighted sum of the attribute contents of the other attributes, the higher the attribute content correlation value of the attribute contents of the other attributes with the attribute contents of the specified attributes. Therefore, when the correlation value between comedy and video is determined after the weight sum of comedy and the account number of video operated by yellow are obtained, the guaranteed account number of video operated by comedy and the account number of video operated by yellow are inversely proportional to the weight sum of comedy, so that the correlation value between comedy and yellow can be determined.

Specifically, for each attribute content of the other attributes, when determining a correlation value of the attribute content of the other attributes with the attribute content of the specified attribute, it may be determined according to the following formula:

I(i _k ,t _m )＝pair_count ₁ (i _k ,t _m )/(sqrt(Count ₁ (i _k ))*sqrt(Count ₁ (t _m )))

wherein I (ik, tm) is attribute content t of other attributes _m Attribute content i with specified attribute _k Is a correlation value of pair_count ₁ (i _k ,t _m ) Attribute content t for other attributes _m Weights and Count of (2) ₁ (i _k ) Attribute content i specifying attributes for operations _k Account number, count of objects of (c) ₁ (t _m ) Attribute content t for manipulating other attributes _m Is the open square process.

In addition, in the actual application scenario, when the operation information is counted, the operation information may be counted in time sequence. In the process of determining the correlation value between each attribute content of other attributes and the attribute content of the designated attribute based on the obtained operation information, if the associated object is the first object of the operation after the operation of the object of the attribute content of the designated attribute, the correlation value between each attribute content of other attributes and the attribute content of the designated attribute is determined according to each associated object of the attribute content, so that the time sequence between the objects can be better reflected, and the click rate of the recommended object selected by the target account can be further ensured when the object is recommended to the target account according to each determined correlation value. Thus, in the disclosed embodiment, the associated object is the first object that an account operates after operating on the object of the attribute content of the specified attribute.

In particular implementations, accounts of objects operating with certain attribute content of a specified attribute, attribute content of other attributes of associated objects of a first operation after the operation of the object of the attribute content of the specified attribute, and operation events for the corresponding associated objects may be stored in order.

Fig. 3 is a graph showing a correlation value of each attribute content of other attributes with each attribute content of a specified attribute according to an exemplary embodiment. As shown in fig. 3, when each attribute content i of the specified attribute is acquired ₁ ，i ₂ ，……，i _n Each attribute content t of other attributes ₁ ，t ₂ ，……，t _m For each attribute content of the designated attribute, establishing a directional connection line between each attribute content of the other attribute and each attribute content of the designated attribute according to the attribute content of the other attribute of the first associated object operated after the object of the attribute content of the designated attribute is operated. For each directional connection line, attribute content i of a specified attribute connected according to the directional connection line _H And attribute content t of other attributes _K Attribute contents t including the other attribute _K The number of times of operated corresponding to each operation event of each associated object and the corresponding relation between the stored operation event and the weight value are used for determining the attribute content t of other attributes _K Attribute content i with specified attribute _H Weight sum w of (2) _HK 。

After the weight sum of each attribute content of the other attributes and each attribute content of the specified attributes is obtained, determining a correlation value of each attribute content of the other attributes and each attribute content of the specified attributes according to the weight sum of the attribute content of the other attributes and the attribute content of the specified attributes, the account number of the associated objects of the attribute content of the operation other attributes and the account number of the objects of the attribute content of the operation specified attributes.

In order to ensure that the object is recommended more accurately, in the embodiments of the disclosure, according to the historical operation information of the account and the operation information of the account in a time range corresponding to the time interval, the relevance value of each determined attribute content of the other attributes and the attribute content of the designated attribute is updated according to the set time interval.

Due to changes over time, objects of interest to the account may also change, such as: in time period a, most accounts are relatively interested in news 1, and as time goes by, new news may appear in time period B, most accounts are relatively interested in news 2. Therefore, in order to further accurately recommend an object, in the embodiment of the present disclosure, the correlation value between each attribute content of the determined other attributes and the attribute content of the specified attribute may be updated according to the historical operation information of the account and the operation information of the account in the time range corresponding to the time interval.

In order to update the relevance value of each attribute content of the determined other attributes and the attribute content of the designated attribute in real time, the set time interval may be shorter, for example, 2s, 1min, etc.

Specifically, the updating the relevance value of each attribute content of the other attributes and the attribute content of the specified attribute according to the historical operation information of the account and the operation information of the account in the time range corresponding to the time interval according to the set time interval includes:

Specifically, when updating the relevance value, for each attribute content of other attributes, the weight sum of the attribute content and the corresponding first weight value thereof, and the stored weight sum of the attribute content and the corresponding second weight value thereof are operated according to the time range corresponding to the time interval, and the stored weight sum of the attribute content is updated.

In the implementation process, for each attribute content of other attributes, the weight sum of the determined attribute content of the other attributes and the attribute content of the designated attribute is updated, and the weight sum can be determined according to the following formula:

pair_count ₁ (i _k ,t _m )＝α ₁ *Δpair_count(i _k ,t _m )+α ₂ *pair_count ₁ ‘(i _k ,t _m )

wherein, pair_count ₁ (i _k ,t _m ) Attribute content t for other updated attributes _m Attribute content i with specified attribute _k Weight sum, alpha ₁ For the first weight value, Δpair_count (i _k ,t _m ) For the attribute content t of other determined attribute in the time range corresponding to the time interval _m Attribute content i with specified attribute _k ，α ₂ Two weight values, pair_count ₁ ‘(i _k ,t _m ) Attribute content t for other attributes saved _m Attribute content i with specified attributes _k Is a weight sum of (2).

In a special scenario, when the second weight value is 0, the weight sum of the attribute contents of other attributes and the attribute contents of the designated attributes and the corresponding first weight value thereof can be directly determined according to the time range corresponding to the set time interval, and the weight sum of the attribute contents of the stored other attributes and the attribute contents of the designated attributes can be updated.

And updating the account number of the stored object of the attribute content of the operation appointed attribute according to the account number of the object of the operation attribute content and the corresponding third weight value thereof and the stored account number of the object of the operation attribute content and the corresponding fourth weight value thereof in the time range corresponding to the time interval aiming at the attribute content of the appointed attribute.

Specifically, updating the account number of the stored object operating the attribute content of the specified attribute may be determined according to the following formula:

Count ₁ (i _k )＝α ₃ *ΔCount(i _k )+α ₄ *Count ₁ ‘(i _k )

wherein Count ₁ (i _k ) Attribute content i of the specified attribute for the updated operation _k Account number, alpha, of objects of (a) ₃ For the third weight value, Δcount (i _k ) Operating the attribute content i of the specified attribute in a time range corresponding to the time interval _k Account number, alpha, of objects of (a) ₄ For the fourth weight value, count ₁ ‘(i _k ) Attribute content i of the specified attribute for the saved operation _k Account number of the object of (c).

In a special scenario, when the fourth weight value is 0, the account number of the object of the attribute content of the designated attribute and the corresponding third weight value thereof can be directly operated in the time range corresponding to the time interval, and the stored account number of the object of the attribute content of the designated attribute is updated.

And updating the stored account number of the object of the attribute content operating other attributes according to the account number of the associated object operating the attribute content and the corresponding fifth weight value thereof and the stored account number of the object operating the attribute content and the corresponding sixth weight value thereof in the time range corresponding to the time interval for each attribute content of other attributes.

Specifically, updating the account number of the stored object operating the attribute content of other attributes can be determined according to the following formula:

Count ₁ (t _m )＝α ₅ *ΔCount(t _m )+α ₆ *Count ₁ ‘(t _m )

wherein Count ₁ (t _m ) For manipulating the attribute contents t of other attributes _m Updated account number, alpha, of objects of (a) ₅ For the fifth weight value, Δcount (t _m ) Operating the attribute content t of other attributes in a time range corresponding to the set time interval _m Account number, alpha, of associated objects of (a) ₆ For the sixth weight value, count ₁ ‘(t _m ) The attribute content t for other attributes of saved operations _m Account number of the object of (c).

In a special scenario, when the sixth weight value is 0, the number of accounts of the related objects of the attribute content of other attributes and the corresponding fifth weight value thereof can be directly operated in a time range corresponding to a set time interval, and the number of accounts of the stored objects of the attribute content of other attributes is updated.

FIG. 4 is a schematic diagram of a particular object recommendation process, according to an example embodiment, the process comprising: the method comprises the steps of determining a relevance value, recommending an object and updating the relevance value, wherein the electronic equipment is taken as a server as a main body, and each part is described in detail as follows:

a first part: and determining a correlation value. For each attribute content of a specified attribute, determining each attribute content of other attributes and the attribute content i of the specified attribute _k Comprises:

s401: the first server specifies attribute content i of the attribute for the operation _k Acquiring attribute contents of other attributes of each associated object operated by the account, and operating events for each associated object.

S402: the first server, for each attribute content of the other attributes, generates a content t according to the attribute content t _m The number of times of being operated corresponding to each operation event of each associated object of the plurality of the associated objects, determining the attribute content t _m Is a weight sum of (2).

Specifically, the first server determines the attribute content t _m The weight sum of (2) includes: the first server aims at the attribute content t _m According to the corresponding relation between the saved operation event and the weight value and the operated times corresponding to each operation event corresponding to the associated object, determining the weight sum of the associated object; the first server determines the attribute content t according to the weight sum corresponding to each associated object of the attribute content _m Is a weight sum of (2).

S403: the first server receives the attribute content t _m Weight sum of (2) and operation of the attribute content t _m Account number of associated objects of (a) and attribute content i of operation-specified attribute _k Account number of objects of (a) determining the attribute content t of other attributes _m Attribute content i with specified attribute _k Is a correlation value of (a).

A second part: object recommendation. Storing the relevance value of each attribute content of other attributes determined by the first server and each attribute content of the appointed attribute into a second server, and recommending the object through the second server, wherein the specific implementation comprises the following steps:

s404: the second server identifies an access object currently accessed by the target account.

S405: the second server determines the object type of the access object, determines the appointed attribute corresponding to the access object according to the stored different attributes corresponding to each object type, and acquires the attribute content of the appointed attribute of the access object.

S406: the second server takes the attribute contents of other attributes meeting the condition of the correlation value as target attribute contents according to the correlation value of each stored attribute content of other attributes and the attribute contents of the designated attributes.

S407: and the second server determines the information of the candidate object corresponding to each target attribute content according to the heat degree of the object type.

Wherein, the heat is used to represent the state of the corresponding object that is focused on by other accounts. Specifically, if the state of the object focused by the other accounts is the collection frequency of the object focused by the other accounts, the process of determining the information of the candidate object corresponding to each target attribute content by the second server includes: the second server obtains the collection frequency of each object corresponding to the target attribute content by other accounts according to each target attribute content, and takes the objects with a second set number, which are more collected by other accounts, as candidate objects corresponding to the target attribute content.

The value of the second set number is not smaller than the set number.

S408: and the second server recommends the information of the candidate objects with the set number corresponding to each target attribute content to the target account as the information of the recommended objects.

Note that, the object recommendation may also be completed in the first server, and in this embodiment, the execution subject for performing the object recommendation is not limited.

Third section: and updating the correlation value. For each attribute content of the specified attribute, updating each attribute content of the other determined attributes with the attribute content i of the specified attribute at set time intervals _k Comprises:

s409: the first server updates, for each attribute content of the other attributes, the stored weight sum of the attribute content, the number of accounts of the object operating the attribute content, and the number of accounts of the object operating the attribute content of the specified attribute according to the weight sum of the attribute content, the number of accounts of the associated object operating the attribute content, and the number of accounts of the object operating the attribute content of the specified attribute, which are determined in a time range corresponding to the time interval.

S410: the first server updates the attribute content of other attributes and the correlation value of the attribute content of the specified attribute according to the updated weight sum of the attribute content, the account number of the object operating the attribute content and the account number of the object operating the attribute content of the specified attribute.

FIG. 5 is a block diagram of an object recommendation device, according to an example embodiment. Referring to fig. 5, the apparatus 500 includes: an acquisition unit 501, a processing unit 502, a recommendation unit 503, and an update unit 504.

An obtaining unit 501, configured to perform obtaining an access object currently accessed by a target account, and determine attribute content of a specified attribute of the access object according to an object type of the access object and different attributes corresponding to each stored object type, where the specified attribute is at least one attribute corresponding to the object type of the access object;

a processing unit 502 configured to execute a correlation value with the attribute contents of the specified attribute according to each attribute content of the other attributes of the object type, taking the attribute contents of the other attributes satisfying a correlation value condition as target attribute contents;

and a recommending unit 503 configured to execute a degree of heat of the object according to the object type, and recommend information of a recommended object corresponding to each target attribute content to the target account, wherein the degree of heat is used for representing a state of the corresponding object focused by other accounts.

Further, the recommending unit 503 is specifically configured to determine information of candidate objects corresponding to each of the target attribute contents according to the heat of the objects of the object types; and recommending the information of the set number of candidate objects corresponding to each target attribute content to the target account as information of recommended objects.

Further, the processing unit 502 is specifically configured to execute each account of the object for operating the attribute content of the specified attribute, obtain the attribute content of the other attribute of each associated object operated by the account, and operate the event for each associated object; for each attribute content of the other attributes, determining the weight sum of the attribute content according to the operated times corresponding to each operation event of each associated object of the attribute content; and determining the relevance value of the attribute contents of the other attributes and the attribute contents of the specified attributes according to the weight sum of the attribute contents, the account number of the associated objects operating the attribute contents and the account number of the objects operating the attribute contents of the specified attributes.

Further, the processing unit 502 is specifically configured to execute each associated object of the attribute content, and determine a weight sum of the associated object according to the saved correspondence between the operation event and the weight value and the number of times of the operation corresponding to each operation event corresponding to the associated object; and determining the weight sum of the attribute content according to the weight sum corresponding to each associated object of the attribute content.

Further, the apparatus further comprises:

and an updating unit 504 configured to perform updating of the relevance value of each determined attribute content of the other attributes and the attribute content of the specified attribute according to the historical operation information of the account and the operation information of the account in a time range corresponding to the time interval according to the set time interval.

Further, the updating unit 504 is specifically configured to perform updating, for each attribute content of the other attributes, the saved weight sum of the attribute content, the account number of the object operating the attribute content, and the account number of the object operating the attribute content of the specified attribute according to the determined weight sum of the attribute content in the time range, the account number of the associated object operating the attribute content in the time range, and the account number of the object operating the attribute content of the specified attribute; and updating the relevance value of the attribute content of other attributes and the attribute content of the specified attribute according to the updated weight sum of the attribute content, the account number of the object operating the attribute content and the account number of the object operating the attribute content of the specified attribute aiming at each attribute content of the other attributes.

In the process of object recommendation, an access object currently accessed by a target account is obtained, and attribute content of an appointed attribute of the access object is determined according to the object type of the access object and different attributes corresponding to each stored object type; according to the correlation value of each attribute content of other attributes of the object type and the attribute content of the appointed attribute, taking the attribute content of the other attributes meeting the condition of the correlation value as target attribute content; and according to the heat of the object type, recommending the information of the recommended object corresponding to each target attribute content to the target account. When the object recommendation is carried out aiming at the same object type, the object is recommended to the account through the correlation value among the attribute contents contained in different attributes, so that the recommended object has more diversity, and the click rate of the account selection recommended object is improved.

Fig. 6 is a block diagram of an electronic device, according to an example embodiment. An electronic device 600 according to such an embodiment of the present disclosure is described below with reference to fig. 6. The electronic device 600 of fig. 6 is merely an example and should not be construed to limit the functionality and scope of use of embodiments of the present disclosure in any way.

Referring to fig. 6, an electronic device 600 may include one or more of the following components: a processing component 602, a memory 604, a power component 606, a multimedia component 608, an audio component 610, an input/output (I/O) interface 612, a sensor component 614, and a communication component 616.

The processing component 602 generally controls overall operation of the electronic device 600, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 602 may include one or more processors 620 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 602 can include one or more modules that facilitate interactions between the processing component 602 and other components. For example, the processing component 602 may include a multimedia module to facilitate interaction between the multimedia component 608 and the processing component 602.

The memory 604 is configured to store various types of data to support operations at the device 600. Examples of such data include instructions for any application or method operating on the electronic device 600, contact data, phonebook data, messages, pictures, videos, and the like. The memory 604 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power supply component 606 provides power to the various components of the electronic device 600. The power components 606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 600.

The multimedia component 608 includes a screen between the electronic device 600 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, swipe, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 608 includes a front camera and/or a rear camera. The front-facing camera and/or the rear-facing camera may receive external multimedia data when the device 600 is in an operational mode, such as a shooting mode or a video mode. Each of the front and rear cameras may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 610 is configured to output and/or input audio signals. For example, the audio component 610 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 600 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 604 or transmitted via the communication component 616. In some embodiments, audio component 610 further includes a speaker for outputting audio signals.

The I/O interface 612 provides an interface between the processing component 602 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 614 includes one or more sensors for providing status assessment of various aspects of the electronic device 600. For example, the sensor assembly 614 may detect an on/off state of the device 600, a relative positioning of the components, such as a display and keypad of the electronic device 600, the sensor assembly 614 may also detect a change in position of the electronic device 600 or a component of the electronic device 600, the presence or absence of a user's contact with the electronic device 600, an orientation or acceleration/deceleration of the electronic device 600, and a change in temperature of the electronic device 600. The sensor assembly 614 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. The sensor assembly 614 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 614 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 616 is configured to facilitate communication between the electronic device 600 and other devices, either wired or wireless. The electronic device 600 may access a wireless network based on a communication standard, such as WiFi, an operator network (e.g., 2G, 3G, 4G, or 5G), or a combination thereof. In one exemplary embodiment, the communication component 616 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 616 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 600 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.

In an exemplary embodiment, a storage medium is also provided, such as a memory 604 including instructions executable by the processor 620 of the electronic device 600 to perform the above-described method. Alternatively, the storage medium may be a non-transitory computer readable storage medium, which may be, for example, ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.

The computer program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, 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.

In some possible implementation manners, aspects of the request processing provided in the present disclosure may also be implemented as a form of a computer program product, which includes program code for causing a server to execute steps in image processing according to various exemplary embodiments of the present disclosure described in the present specification when the computer program product is run on the server, for example, the electronic device may execute step S101 as shown in fig. 1, obtain an access object currently accessed by a target account, determine attribute contents of a specified attribute of the access object according to an object type of the access object and different attributes corresponding to each saved object type, wherein the specified attribute is at least one attribute corresponding to the object type of the access object, and step S102, based on a correlation value of each attribute contents of other attributes of the object type and the attribute contents of the specified attribute, take the attribute contents of other attributes satisfying a correlation value condition as target attribute contents, and step S103, based on a thermal state of each of the attributes corresponding to the object type of the object is applied to a recommended state, wherein the corresponding attribute of the object is indicated to the other thermal state of interest.

The computer program product for image processing of embodiments of the present disclosure may employ a portable compact disc read-only memory (CD-ROM) and include program code and may run on an electronic device. However, the computer program product of the present disclosure is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

In this scheme, the user information (such as user equipment information, user personal information, user operation behavior information, etc.) is collected and processed or analyzed later by the authorization of the user.

It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An object recommendation method, the method comprising:

according to the relevance value of each attribute content of other attributes of the object type and the attribute content of the appointed attribute, taking the attribute content of the other attributes meeting the relevance value condition as target attribute content;

recommending the information of the recommended object corresponding to each target attribute content to the target account according to the heat degree of the object type, wherein the heat degree is used for representing the state of the corresponding object, which is concerned by other accounts;

wherein determining each attribute content of the other attributes of the object type, a relevance value of the attribute content of the specified attribute includes:

2. The method of claim 1, wherein recommending information of recommended objects corresponding to each of the target attribute contents to the target account according to the popularity of the object type comprises:

3. The method according to claim 1, wherein determining the sum of weights of the attribute contents according to the number of times operated corresponding to each operation event of each associated object of the attribute contents comprises:

for each associated object of the attribute content, determining the weight sum of the associated object according to the corresponding relation between the saved operation event and the weight value and the operated times corresponding to each operation event corresponding to the associated object;

4. The method of claim 1, wherein the associated object is a first object that an account operates after an object that operates the attribute content of the specified attribute.

5. The object recommendation method according to claim 1, wherein the method further comprises:

6. The method according to claim 5, wherein updating the relevance value of each determined attribute content of the other attributes and the attribute content of the specified attribute according to the historical operation information of the account at the set time interval and the operation information of the account in the time range corresponding to the time interval comprises:

7. The method according to any one of claims 1 to 6, wherein the attribute corresponding to each object type includes at least one of an identification of the object, a style of the object, and a source of the object.

8. An object recommendation device, the device comprising:

a recommending unit configured to execute a degree of heat of an object according to the object type, and recommend information of a recommended object corresponding to each target attribute content to the target account, wherein the degree of heat is used for representing a state of the corresponding object focused by other accounts;

The processing unit is specifically configured to execute each account of the object for operating the attribute content with the specified attribute, acquire the attribute content with the other attribute of each associated object operated by the account, and operate the event for each associated object; for each attribute content of the other attributes, determining the weight sum of the attribute content according to the operated times corresponding to each operation event of each associated object of the attribute content; and determining the relevance value of the attribute contents of the other attributes and the attribute contents of the specified attributes according to the weight sum of the attribute contents, the account number of the associated objects operating the attribute contents and the account number of the objects operating the attribute contents of the specified attributes.

9. The object recommendation device according to claim 8, wherein the recommendation unit is specifically configured to perform determining information of candidate objects corresponding to each of the target attribute contents according to the heat of the object type; and recommending the information of the set number of candidate objects corresponding to each target attribute content to the target account as information of recommended objects.

10. The object recommendation device according to claim 8, wherein the processing unit is specifically configured to execute each associated object of the attribute content, and determine a weight sum of the associated object according to the saved correspondence between the operation event and the weight value and the number of times each operation event corresponding to the associated object is operated; and determining the weight sum of the attribute content according to the weight sum corresponding to each associated object of the attribute content.

11. The object recommendation device of claim 8, wherein said device further comprises:

12. The object recommendation device according to claim 11, wherein the updating unit is specifically configured to execute updating of the saved weight sum of the attribute contents, the number of accounts of the objects operating the attribute contents, and the number of accounts of the objects operating the attribute contents of the specified attribute, based on the determined weight sum of the attribute contents in the time range, the number of accounts of the associated objects operating the attribute contents in the time range, and the number of accounts of the objects operating the attribute contents of the specified attribute, for each attribute content of the other attributes; and updating the relevance value of the attribute content of the other attributes and the attribute content of the specified attribute according to the updated weight sum of the attribute content, the account number of the object operating the attribute content and the account number of the object operating the attribute content of the specified attribute aiming at each attribute content of the other attributes.

13. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the object recommendation method according to any one of claims 1 to 7.

14. A storage medium, characterized in that instructions in the storage medium, when executed by a processor of an electronic device, enable the processor to perform the object recommendation method according to any one of claims 1 to 7.