CN111597454A - Account recommendation method and device - Google Patents
Account recommendation method and device Download PDFInfo
- Publication number
- CN111597454A CN111597454A CN202010256301.6A CN202010256301A CN111597454A CN 111597454 A CN111597454 A CN 111597454A CN 202010256301 A CN202010256301 A CN 202010256301A CN 111597454 A CN111597454 A CN 111597454A
- Authority
- CN
- China
- Prior art keywords
- account
- target
- user
- rule
- recalling
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 230000006399 behavior Effects 0.000 claims description 34
- 238000004590 computer program Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 9
- 230000003796 beauty Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an account recommending method, an account recommending device, electronic equipment and a computer-readable storage medium. The method comprises the following steps: recalling the target account according to a multi-way recall rule, wherein the recall rule has an association relation with a target user to be recommended, and the target account meets at least one recall rule in the multi-way recall rule; determining an account candidate set according to the recalled target account; the account candidate set comprises at least one target account; and sending a recommended account to the target user, wherein the recommended account is at least one target account in the account candidate set. The method can solve the problems of single account number recommendation mode and limited range in the prior art.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to an account recommending method and apparatus, an electronic device, and a computer-readable storage medium.
Background
With the development of internet technology, a network user can perform social contact through a social network, for better user experience, the social network platform can recommend an account which the network user may be interested in to the network user, for example, in a microblog platform, a user a often searches and browses a bobble of beauty makeup, and at this time, the account of a beauty makeup bobbler owner can be recommended to the user a.
In the prior art, account recommendation methods generally recommend accounts based on user interests, for example, if a user is interested in a certain type of account, the type of account is always recommended.
However, this method is simple in recommendation and limited in scope. And because the recommendation mode is single and the range is limited, sometimes specific service requirements may not be met, for example, an advertiser user wants to publish an advertisement through a social network to promote a product, and at this time, if an account of another network user is recommended to the advertiser user only according to the interest of the advertiser user, more potential users cannot be mined, and the advertisement effect is poor.
Disclosure of Invention
The embodiment of the specification provides an account recommending method, an account recommending device, electronic equipment and a computer-readable storage medium, so as to solve the problems that in the prior art, an account recommending mode is single and the range is limited.
The embodiment of the specification adopts the following technical scheme:
an account number recommendation method comprises the following steps:
recalling a target account number according to a multi-way recall rule, wherein the recall rule has an association relation with a target user to be recommended, and the target account number meets at least one recall rule in the multi-way recall rule;
determining an account candidate set according to the recalled target account; the account candidate set comprises at least one target account;
and sending a recommended account to the target user, wherein the recommended account is at least one target account in the account candidate set.
An account recommending apparatus, comprising:
the system comprises a recall module, a recall module and a recommendation module, wherein the recall module is used for recalling a target account according to a multi-way recall rule, the recall rule has an association relation with a target user to be recommended, and the target account meets at least one recall rule in the multi-way recall rule;
the determining module is used for determining an account candidate set according to the recalled target account; the account candidate set comprises at least one target account;
and the sending module is used for sending a recommended account to the target user, wherein the recommended account is at least one target account in the account candidate set.
An electronic device, comprising: the account recommendation method comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the computer program is executed by the processor, the steps of any account recommendation method are realized.
A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of any of the account recommendation methods.
The embodiment of the specification adopts at least one technical scheme which can achieve the following beneficial effects:
by recalling the target account number meeting at least one recall rule according to the multi-recall rule, determining an account number candidate set according to the recalled target account number, and sending at least one target account number contained in the account number candidate set to the target user, compared with a single recommendation mode in the prior art in which recommendation is only performed according to user interest, the target account number in the account number candidate set is recalled based on the multi-recall rule, so that account number recommendation to the user from multiple angles can be realized, the diversity of account number recommendation is improved, and the account number recommendation range is expanded.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a schematic flow chart of an account recommendation method provided in an embodiment of the present specification;
fig. 2 is a schematic flowchart of an implementation manner of determining a candidate set of account numbers according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an account recommendation device provided in an embodiment of the present specification;
fig. 4 is a schematic structural diagram of an electronic device provided in an embodiment of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
In the prior art, account recommendation methods generally recommend accounts based on interests of users, for example, if a user is interested in a certain type of account, the user always recommends the type of account. However, this method is simple in recommendation and limited in scope.
In order to solve the technical problem, an embodiment of the present specification provides an account number recommendation method, which is used for solving the problems of a single account number recommendation method and a limited range in the prior art. The execution subject of the method includes, but is not limited to, a server, a personal computer, a notebook computer, a tablet computer, a smart phone, and other intelligent electronic devices that can execute a predetermined process, such as numerical calculation and/or logical calculation, by running a predetermined program or instruction. The server may be a single network server or a server group consisting of a plurality of network servers or a Cloud Computing (Cloud Computing) based Cloud consisting of a large number of computers or network servers. In the embodiments of the present specification, the execution subject of the method is explained as a server. The flow diagram of the method is shown in figure 1, and comprises the following steps:
step 11: and recalling the target account according to the multi-way recall rule.
In practical application, considering that in the prior art, generally, only the interest of a user is targeted, the way of recommending an account to the user is single, in the embodiment of the present specification, a multi-recall rule may be preset to realize that a target account is recalled according to the multi-recall rule, and then the target account recalled according to the multi-recall rule is recommended to the user, so that diversity of account recommendation can be increased, and the range of account recommendation is expanded.
The multi-way recall rule may be an association relationship between the recall rule and a target user to be recommended, or a preset rule for recalling a target account. It is understood that the recall rule may be set based on a plurality of aspects such as behavior, interest, and social relationship of the target user to be recommended, so the recall rule may be a rule of an association relationship with the target user to be recommended.
In practical applications, when the target account is recalled according to the multi-recall rule, the target account may satisfy at least one recall rule in the multi-recall rule.
In one or more embodiments of the present description, the multi-recall rule may include, but is not limited to: at least one of a user collaborative recall rule, a user historical behavior recall rule, a tag recall rule, and a relationship recall rule.
Since the content of the specific implementation of recalling the target account according to each recall rule in the multiple recall rules is more, and for brevity of the lines, in the embodiment of the present specification, the specific implementation of recalling the target account according to the multiple recall rules will be described below, and is not described herein again.
In practical applications, in order to facilitate the computer processing data, it is usually necessary to perform data processing on the recalled target account, and in one or more embodiments of the present specification, after recalling the target account number according to the multi-recall rule, the method may further include: and performing reverse indexing on the target account. The inverted index may include, but is not limited to, data processing modes such as lexicography, stop word removal, term normalization, stem reduction, and morphological merging.
In practical application, the target account numbers after being inverted and indexed can be stored in a material library, so that an account number candidate set can be determined according to the recalled target account numbers. The material library may be a database or other readable storage media, and the application is not limited thereto.
In practical application, storing the target account in the material library may specifically include: at least one account identifier corresponding to the determined target account is stored in the material library, where the account identifier may be information uniquely representing the target account, such as "User Identification (UID)", "mobile phone number", "account name", and the like, and in the embodiment of the present specification, the recalling the target account may include, but is not limited to, account information such as the UID, the mobile phone number, the account name, and the like of the recalling the target account.
Step 12: and determining an account candidate set according to the recalled target account.
The target account number here may be the target account number recalled by step 11.
The account candidate set may be a target account for storing a recall to facilitate later recommendation of the target account to the user from the account candidate set.
In practical applications, considering that the target account recalled in step 11 may include a blacklist account, which may be an account issuing false information, an account issuing dishonest speech, and the like, and if the blacklist account is recommended to a target user, which may cause poor user experience, in one or more embodiments of the present specification, determining an account candidate set according to the recalled target account may include:
judging whether the target account is a blacklist account;
if the account number is the blacklist account number, screening out the target account number;
and if the account number is not the blacklisted account number, adding the target account number to the account number candidate set.
In practical applications, the blacklist account may be determined by detecting the content of the blog posted by the user in the social network. The blacklist account may be stored in a database or other readable storage medium, so that whether the target account is a blacklist account is determined by matching the target account with the stored blacklist account.
By screening out the blacklist account in the recalled target account, the blacklist account can be prevented from being recommended to the target user, and therefore poor user experience is avoided.
In practical applications, considering that the number of target account numbers recalled according to the multi-recall rule may be large, and the number of target account numbers included in the account number candidate set is limited, in one or more implementations of the present specification, determining the account number candidate set according to the recalled target account numbers may further include:
judging whether the number of target accounts in the account candidate set reaches a preset threshold value or not;
and if the target account number does not reach the preset threshold value, adding the target account number to the account number candidate set.
The preset threshold may be a preset numerical value according to actual requirements, for example, if 10 accounts need to be recommended to the target user, the preset threshold may be 10.
It can be understood that, if the preset threshold is not reached, the target account may be added to the account candidate set, and if the preset threshold is reached, the target account may not be added to the account candidate set.
In practical application, target accounts added to the account candidate set may be manually deleted from the account candidate set in some scenarios, for example, some accounts which are considered to have no recommendation value may be manually deleted from the account candidate set, so that validity of the recommended accounts may be further improved. When the target account is deleted from the account candidate set, the target account in the account candidate set can be supplemented immediately by circularly traversing the target account in the material library according to a preset threshold and the blacklist account. It will be appreciated that accounts that have been deleted from the account candidate set may not be re-selected into the account candidate set.
Alternatively, as shown in fig. 2, a specific implementation of determining the account candidate set according to the recalled target account may be implemented. The material library can contain target account numbers which are recalled according to a multi-way recall rule and subjected to inverted indexing, whether the target account numbers are blacklist account numbers or not is sequentially judged by traversing the target account numbers contained in the material library, if the target account numbers are the blacklist account numbers, the target account numbers are screened out, if the target account numbers are not the blacklist account numbers, whether the data of the target account numbers in the account number candidate set reach a preset threshold value or not is judged, if the data do not reach the preset threshold value, the target account numbers are added into the account number candidate set, if the data reach the preset threshold value, the target account numbers are not added into the account number candidate set, and the target account numbers contained in the material library are continuously and circularly traversed, so that the target account numbers in the account number candidate set can be timely supplemented when the target account numbers are. It can be understood that after the target accounts included in the material library are completely traversed, an account candidate set for recommending accounts to the target user can be obtained.
Step 13: and sending the recommended account to the target user.
In practical application, after the account candidate set is determined in step 12, the server may send the recommended account to the client through a hypertext Transfer Protocol (HTTP), that is, the recommended account may be sent to the target user.
After the client receives the recommended account sent by the server, the recommended account can be displayed to the target user, for example, for a microblog platform, the recommended account can be displayed to the target user through a "recommend" block under "attention" so that the target user pays attention to the recommended account.
In practical application, the target user may be an advertiser user, and after an account is recommended to the advertiser user, the advertiser user may place an advertisement to the recommended account.
It is to be appreciated that the recommended account number can be at least one target account number in a candidate set of account numbers. The number of the specific recommended accounts may be determined according to actual requirements, and in an embodiment, the recommended accounts may be all target accounts included in the account candidate set.
In the embodiment of the specification, by recalling the target account number meeting at least one recall rule according to the multiple recall rules, determining an account number candidate set according to the recalled target account number, and sending at least one target account number contained in the account number candidate set to the target user, compared with a single recommendation method in the prior art in which recommendation is performed only according to user interest, because the target account number in the account number candidate set is recalled based on the multiple recall rules, account number recommendation to the user from multiple angles can be realized, the diversity of account number recommendation is improved, and the range of account number recommendation is expanded.
As described above, the multi-way recall rule may include at least one of a user collaborative recall rule, a user historical behavior recall rule, a tag recall rule, a relational recall rule. The following is a description of a specific implementation manner of recalling a target account according to each recall rule in a multi-recall rule provided in an embodiment of the present specification.
Detailed description of the invention
In one or more embodiments of the present specification, when the multi-recall rule is a user collaborative recall rule, recalling the target account according to the multi-recall rule may include:
determining users with similar interests with the target user according to a collaborative filtering algorithm;
and recalling the target account corresponding to the user with similar interest to the target user.
In practical applications, the user collaboration rule may include determining users with similar interests as the target user according to the interest similarity, and specifically, may be determining users with similar interests as the target user according to a collaborative filtering algorithm. The collaborative filtering algorithm may mainly use the similarity of user behaviors to calculate the interest similarity, for example, given user u and user v, n (u) may be represented as an item set that user u has positive feedback, n (v) may be represented as an item set that user v has positive feedback, where the items may be articles, advertisements, etc., and the items that user has positive feedback may be articles, advertisements, etc., that user forwards, evaluates, or approves, and the collaborative filtering algorithm may be Jaccard coefficient formula, calculating the interest similarity w of user u and user v by the Jaccard coefficient formulauvThe method can be as follows:
it is understood that the higher the interest similarity, the more similar the interest representing the user. In practical application, a similarity threshold value can be preset, and when the calculated interest similarity between the target user and a certain user is not lower than the similarity threshold value, the user can be considered as a user with similar interest to the target user.
In practical application, after the users with similar interests to the target user are determined, the method can be used for directly pushing the blog articles, advertisements and the like which are interested by the users and are not browsed by the target user to the target user, so that the blog articles, the advertisements and the like can be directly recommended by the recommended account, and the expandability of personalized recommendation can be improved.
By means of the first mode, the target account corresponding to the user with similar interest to the target user can be recalled, and diversity of the recalled target account is increased.
Detailed description of the invention
In practical applications, considering that the target user may be an advertiser user, and the historical behavior of the advertiser user may include placing an advertisement on a specific account, in one or more embodiments of the present specification, when the multi-recall rule is a user historical behavior recall rule, recalling the target account according to the multi-recall rule may include:
and recalling the target account number which is advertised by the target user in the first preset historical time period.
As described above, considering that the target user may be an advertiser user, the historical behavior of the target user may include the target user having placed an advertisement on a specific account, which may be the target account that was placed the advertisement by the target user.
It can be understood that, in consideration of timeliness, it is not necessary to recall all account numbers that have been advertised, and a first preset history time period may be set, and a target account number that has been advertised by a target user within the first preset history time period may be recalled. The first preset history time period may be set according to an actual requirement, for example, the first preset history time period may be set from a current day to 90 days in the past, where the current day may be a date when an account is to be recommended to a target user, and the application is not limited to a specific numerical value of the first preset history time period.
By means of the method II, the target account number which is advertised by the target user in the first preset historical time period can be recalled, and diversity of the recalled target account number is improved.
Detailed description of the invention
In an embodiment of the present disclosure, if the multi-recall rule is a user history behavior recall rule, recalling the target account according to the multi-recall rule may include:
determining account names contained in blog articles issued by a target user through a social network within a second preset historical time period;
the target account number corresponding to the account name contained in the blog is recalled.
Based on the same consideration as the first preset historical time period, a second preset historical time period can be set to determine account names contained in the blog articles published by the target user through the social network in the second preset historical time period. In practical applications, the second preset historical time period may be the same as the first preset historical time period, for example, may also be from the current day to 90 days in the past, and of course, may also be different, and the application is not limited thereto.
In practical application, the account name contained in the blog article released by the target user through the social network in the second preset history time period is determined, and the account name in the blog article content can be obtained by analyzing the blog article content released by the target user in the second preset history time period.
In practical application, after the account name contained in the blog text is determined, the target account corresponding to the account name can be recalled, and the target account corresponding to the account name can include account information such as the UID (user identification) and the mobile phone number of the target account.
By means of the third mode, the target account corresponding to the account name contained in the blog article issued by the target user can be recalled, and the diversity of the recalled target account is increased.
Detailed description of the invention
In one or more embodiments of the present specification, when the multi-recall rule is a tag recall rule, recalling the target account according to the multi-recall rule may include:
according to the first interest of the target user, determining an interest tag corresponding to the first interest;
and recalling a specified number of target account numbers with the interest tags according to the interest tags.
In practical applications, considering that a user can post a blog in a social network, other users can interact with the posted blog, for example: forward, comment, like the blog. Then determining, from the first interest of the target user, an interest tag corresponding to the first interest may include: and adding corresponding interest labels to the target users according to the interest classification of the blog articles issued by the target users and the interest classification with the highest user number ratio of interaction with the issued blog articles. For example, if there are many messages about beauty makeup in the messages issued by the user a, the interest classification of the issued messages may be beauty makeup, and the messages about fitness issued by the user a having the greatest amount of interaction with other users may be fitness, and the interest classification having the highest number of users interacting with the issued messages may be fitness, so that a beauty makeup label and a fitness label may be added to the user a.
In practical application, considering that the target user can also be an advertiser user, when the interest labels are added to the advertiser user, the interest labels can be added to the advertiser user according to the interest classification of the advertisements historically delivered by the advertiser and the interest classification with the highest proportion of the number of users interacting with the delivered advertisements.
It is understood that, besides the target user, other users in the social network may also be added with interest tags, each interest tag may correspond to each interest category, and each interest category may include users with each interest tag, that is, the interest category corresponds to the user category. In practical application, the corresponding relationship between the interest tags and the interest categories may be pre-stored, and the account numbers of the users with the interest tags included in each interest category are stored in the database, so that a specified number of target account numbers with the interest tags are recalled according to the determined interest tags.
In practical application, the number of account numbers contained in each interest category may be large, and considering that the number of target account numbers which can be stored in the material library is limited and the number of target account numbers in the account number candidate set is limited, a specified number may be set, and the specified number of target account numbers with interest tags may be recalled.
By means of the method IV, the target account numbers with the interest tags in the specified number can be recalled, and the diversity of the recalled target account numbers is increased.
Detailed description of the invention
In practical applications, considering that the interest of the user may change at any time, and based on that the method four may not meet the real-time property of recommending the account based on the interest of the user, in one or more embodiments of the present specification, when the multi-way recall rule is a tag recall rule, recalling the target account according to the multi-way recall rule, which may include:
determining a second interest generated by the target user except the first interest according to the user behavior of the target user;
and recalling the target account matched with the second interest.
Wherein the user behavior may include: at least one of search behavior, browse behavior, comment behavior. In practical application, the instant interest of the target user can be judged by monitoring user behaviors such as search behavior, browsing behavior and comment behavior generated by the user in real time, and if the instant interest is not included in the first interest in the fourth mode, the instant interest can be a second interest generated by the target user except the first interest.
After the second interest is determined, the target account matched with the second interest may be recalled, for example, when it is monitored that a search term of the target user during searching in the social network is more around a brand, the target user may be considered to be interested in the brand, and then the target account matched with the brand may be recalled according to the search behavior.
By means of the fifth mode, the target account matched with the second interest generated by the target user can be recalled, and diversity and real-time performance of the recalled target account can be improved.
Detailed description of the invention
In practical applications, considering relationships such as attention and being concerned among users of a social network, recalling a target account to increase diversity of recommended accounts through the relationships may also be implemented, in an embodiment of the present specification, when the multi-recall rule is a relationship recall rule, recalling the target account according to the multi-recall rule may include:
determining a target account having a first type relationship with a target user, wherein the first type relationship may include: at least one of an account number concerned by the target user and an account number concerned by the target user;
determining a target account number having a second type of relationship with a target user, wherein the second type of relationship may include: paying attention to the account which has a first type relationship with the target user and is not concerned with the target user;
and recalling the target account number with the first type relation with the target user and/or the target account number with the second type relation with the target user.
It can be understood that, by recalling accounts with the first type of relationship, it may be to recall a target account that has a direct contact with a target user, and by recalling accounts with the second type of relationship, it may be possible to recommend accounts that may have the first type of relationship with the target user to the target user, which expands the recommendation range of the target account.
By the sixth mode, the target account numbers with the first-type relationship and/or the second-type relationship with the target user can be recalled, and the diversity of the recalled target account numbers is further increased.
It should be noted that, when the target account is recalled according to the multi-way recall rule, at least one of the first way to the sixth way may be adopted, and the scheme obtained by arranging and combining the first way to the sixth way is within the protection scope of the present application.
In the embodiment of the present specification, by means of the first to sixth ways, the diversity of recalled target accounts can be increased, so as to further increase the diversity of accounts recommended to the target user.
The account recommending method provided by the embodiment of the specification is based on the same inventive concept, and the embodiment of the specification further provides a corresponding account recommending device. As shown in fig. 3, the apparatus specifically includes:
the system comprises a recall module 101, a recall module and a recall module, wherein the recall module is used for recalling a target account according to a multi-way recall rule, the recall rule has an association relation with a target user to be recommended, and the target account meets at least one recall rule in the multi-way recall rule;
the determining module 102 is configured to determine an account candidate set according to the recalled target account; the account candidate set comprises at least one target account;
a sending module 103, configured to send a recommended account to the target user, where the recommended account is at least one target account in the account candidate set.
The specific workflow of the above device embodiment may include: the recall module 101 recalls the target account according to the multi-path recall rule; the determining module 102 is configured to determine an account candidate set according to the recalled target account; the sending module 103 sends a recommended account to the target user, where the recommended account is at least one target account in the account candidate set.
In one embodiment, the multi-recall rule comprises: at least one of a user collaborative recall rule, a user historical behavior recall rule, a tag recall rule, and a relationship recall rule.
In one embodiment, when the multi-way recall rule is the user collaborative recall rule, the recall module 101 includes:
a similar interest determining unit, configured to determine, according to a collaborative filtering algorithm, a user with similar interest to the target user;
and the first recalling unit is used for recalling the target account corresponding to the user with similar interest to the target user.
In one embodiment, when the multi-way recall rule is the user historical behavior recall rule, the recall module 101 includes:
and the second recall unit is used for recalling the target account number which is advertised by the target user in the first preset historical time period.
In one embodiment, when the multi-way recall rule is the user historical behavior recall rule, the recall module 101 includes:
the account name determining unit is used for determining account names contained in blog articles issued by the target user through a social network in a second preset historical time period;
and the third recall unit is used for recalling the target account corresponding to the account name contained in the blog article.
In one embodiment, when the multi-way recall rule is the tag recall rule, the recall module 101 includes:
the interest tag determining unit is used for determining an interest tag corresponding to a first interest of the target user according to the first interest;
and the fourth recalling unit is used for recalling the specified number of target account numbers with the interest tags according to the interest tags.
In one embodiment, when the multi-way recall rule is the interest tag recall rule, the recall module 101 includes:
the second interest determining unit is used for determining a second interest generated by the target user except the first interest according to the user behavior of the target user; the user behavior comprises: at least one of a search behavior, a browse behavior, and a comment behavior;
and the fifth recalling unit is used for recalling the target account matched with the second interest.
In one embodiment, when the multi-way recall rule is the relationship recall rule, the recall module 101 includes:
a first-type relationship account determination unit, configured to determine a target account having a first-type relationship with the target user, where the first-type relationship includes: at least one of an account number concerned by the target user and an account number concerned by the target user;
a second-type relationship account determination unit, configured to determine a target account having a second-type relationship with the target user, where the second-type relationship includes: paying attention to the account which has the first type relationship with the target user and not paying attention to the target user;
and the sixth recalling unit is used for recalling the target account number which has the first type relationship with the target user and/or the target account number which has the second type relationship with the target user.
In one embodiment, the determining module 102 includes:
a blacklist account determination unit, configured to determine whether the target account is a blacklist account;
the screening unit is used for screening the target account if the blacklist account is the blacklist account;
a first adding unit, configured to add the target account to the account candidate set if the target account is not a blacklisted account.
In one embodiment, the determining module 102 includes:
a preset threshold value judging unit, configured to judge whether the number of target account numbers in the account number candidate set reaches a preset threshold value;
and the second adding unit is used for adding the target account to the account candidate set if the target account does not reach a preset threshold.
In one embodiment, the apparatus further comprises:
the reverse index module is used for performing reverse index on the target account; wherein the inverted index comprises: the method comprises the steps of word segmentation, stop word removal, term normalization, stem reduction and word shape merging.
In the embodiment of the specification, by recalling the target account number meeting at least one recall rule according to the multiple recall rules, determining an account number candidate set according to the recalled target account number, and sending at least one target account number contained in the account number candidate set to the target user, compared with a single recommendation method in the prior art that recommendation is performed only according to user interest, because the target account number in the account number candidate set is recalled based on the multiple recall rules, account number recommendation to the user from multiple angles can be achieved, the diversity of account number recommendation is improved, and the range of account number recommendation is expanded.
An embodiment of this specification further provides an electronic device, and referring to fig. 4, in a hardware level, the electronic device includes a processor, and optionally further includes an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (peripheral component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 4, but that does not indicate only one bus or one type of bus.
And the memory is used for storing programs. In particular, the program may include program code comprising computer operating instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.
The processor reads the corresponding computer program from the nonvolatile memory to the memory and then runs the computer program to form the application account recommending device on a logic level. A processor executing the program stored in the memory and configured to perform at least the following:
recalling a target account number according to a multi-way recall rule, wherein the recall rule has an association relation with a target user to be recommended, and the target account number meets at least one recall rule in the multi-way recall rule;
determining an account candidate set according to the recalled target account; the account candidate set comprises at least one target account;
and sending a recommended account to the target user, wherein the recommended account is at least one target account in the account candidate set.
The method executed by the account recommendation device according to the embodiment shown in fig. 1 of the present application may be applied to or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a network Processor (FP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present specification may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present specification may be embodied directly in a hardware decoding processor, or in a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
The electronic device may further execute the method executed by the account recommendation device in fig. 1, and implement the functions of the account recommendation device in the embodiment shown in fig. 1, which are not described herein again in this specification.
The present specification further provides a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, which when executed by an electronic device including a plurality of application programs, enable the electronic device to perform the method performed by the account recommendation apparatus in the embodiment shown in fig. 1, and at least perform:
recalling a target account number according to a multi-way recall rule, wherein the recall rule has an association relation with a target user to be recommended, and the target account number meets at least one recall rule in the multi-way recall rule;
determining an account candidate set according to the recalled target account; the account candidate set comprises at least one target account;
and sending a recommended account to the target user, wherein the recommended account is at least one target account in the account candidate set.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the specification. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (14)
1. An account number recommendation method is characterized by comprising the following steps:
recalling a target account number according to a multi-way recall rule, wherein the recall rule has an association relation with a target user to be recommended, and the target account number meets at least one recall rule in the multi-way recall rule;
determining an account candidate set according to the recalled target account; the account candidate set comprises at least one target account;
and sending a recommended account to the target user, wherein the recommended account is at least one target account in the account candidate set.
2. The method of claim 1, wherein the multi-way recall rule comprises: at least one of a user collaborative recall rule, a user historical behavior recall rule, a tag recall rule, and a relationship recall rule.
3. The method of claim 2, wherein if the multi-way recall rule is the user collaborative recall rule, then,
the recalling the target account number according to the multi-path recalling rule comprises the following steps:
determining users with similar interests with the target user according to a collaborative filtering algorithm;
and recalling the target account corresponding to the user with similar interest to the target user.
4. The method of claim 2, wherein when the multi-way recall rule is the user historical behavior recall rule, then,
the recalling the target account number according to the multi-path recalling rule comprises the following steps:
and recalling the target account number which is advertised by the target user in a first preset historical time period.
5. The method of claim 2 or 4, wherein when the multi-way recall rule is the user historical behavior recall rule, then,
the recalling the target account number according to the multi-path recalling rule comprises the following steps:
determining account names contained in blog articles issued by the target user through a social network within a second preset historical time period;
and recalling the target account corresponding to the account name contained in the Bowen.
6. The method of claim 2, wherein if the multi-way recall rule is the tag recall rule, then,
the recalling the target account number according to the multi-path recalling rule comprises the following steps:
according to the first interest of the target user, determining an interest tag corresponding to the first interest;
and recalling a specified number of target account numbers with the interest tags according to the interest tags.
7. The method of claim 6, wherein if the multi-way recall rule is the tag recall rule, then,
the recalling the target account number according to the multi-path recalling rule further comprises:
determining a second interest generated by the target user except the first interest according to the user behavior of the target user; the user behavior comprises: at least one of a search behavior, a browse behavior, and a comment behavior;
and recalling the target account matched with the second interest.
8. The method of claim 2, wherein if the multi-way recall rule is the relationship recall rule, then,
the recalling the target account number according to the multi-path recalling rule comprises the following steps:
determining a target account number having a first type relationship with the target user, wherein the first type relationship comprises: at least one of an account number concerned by the target user and an account number concerned by the target user;
determining a target account number having a second type of relationship with the target user, wherein the second type of relationship comprises: paying attention to the account which has the first type relationship with the target user and not paying attention to the target user;
and recalling the target account number which has the first type relation with the target user and/or the target account number which has the second type relation with the target user.
9. The method of claim 1, wherein the determining a candidate set of account numbers from the recalled target account numbers comprises:
judging whether the target account is a blacklist account;
if the account number is a blacklist account number, screening out the target account number;
and if the account number is not the blacklist account number, adding the target account number to the account number candidate set.
10. The method of claim 1, wherein the determining a candidate set of account numbers from the recalled target account numbers comprises:
judging whether the number of target accounts in the account candidate set reaches a preset threshold value or not;
and if the target account number does not reach the preset threshold value, adding the target account number to the account number candidate set.
11. The method of claim 1, wherein after recalling the target account number according to the multi-recall rule, further comprising:
performing reverse indexing on the target account; wherein the inverted index comprises: the method comprises the steps of word segmentation, stop word removal, term normalization, stem reduction and word shape merging.
12. An account recommending apparatus, comprising:
the system comprises a recall module, a recall module and a recommendation module, wherein the recall module is used for recalling a target account according to a multi-way recall rule, the recall rule has an association relation with a target user to be recommended, and the target account meets at least one recall rule in the multi-way recall rule;
the determining module is used for determining an account candidate set according to the recalled target account; the account candidate set comprises at least one target account;
and the sending module is used for sending a recommended account to the target user, wherein the recommended account is at least one target account in the account candidate set.
13. An electronic device, comprising: memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the account recommendation method for social networks according to any one of claims 1 to 11.
14. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the account recommendation method for social networks according to any one of claims 1 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010256301.6A CN111597454A (en) | 2020-04-02 | 2020-04-02 | Account recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010256301.6A CN111597454A (en) | 2020-04-02 | 2020-04-02 | Account recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111597454A true CN111597454A (en) | 2020-08-28 |
Family
ID=72187361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010256301.6A Pending CN111597454A (en) | 2020-04-02 | 2020-04-02 | Account recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111597454A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112148972A (en) * | 2020-09-04 | 2020-12-29 | 北京明略昭辉科技有限公司 | Method and device for screening information to be recommended |
| TWI828139B (en) * | 2021-05-17 | 2024-01-01 | 韓商連加股份有限公司 | Method, computer device, and computer program to recommend account |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140297677A1 (en) * | 2013-03-29 | 2014-10-02 | Canon Kabushiki Kaisha | Recommendation apparatus, recommendation method, and storage medium |
| CN109190033A (en) * | 2018-08-23 | 2019-01-11 | 微梦创科网络科技（中国）有限公司 | A kind of user's friend recommendation method and system |
| CN109190043A (en) * | 2018-09-07 | 2019-01-11 | 北京三快在线科技有限公司 | Recommended method and device, storage medium, electronic equipment and recommender system |
| CN109544396A (en) * | 2019-01-10 | 2019-03-29 | 腾讯科技（深圳）有限公司 | Account recommended method, device, server, terminal and storage medium |
| CN109948023A (en) * | 2019-03-08 | 2019-06-28 | 腾讯科技（深圳）有限公司 | Recommended acquisition methods, device and storage medium |
-
2020
- 2020-04-02 CN CN202010256301.6A patent/CN111597454A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140297677A1 (en) * | 2013-03-29 | 2014-10-02 | Canon Kabushiki Kaisha | Recommendation apparatus, recommendation method, and storage medium |
| CN109190033A (en) * | 2018-08-23 | 2019-01-11 | 微梦创科网络科技（中国）有限公司 | A kind of user's friend recommendation method and system |
| CN109190043A (en) * | 2018-09-07 | 2019-01-11 | 北京三快在线科技有限公司 | Recommended method and device, storage medium, electronic equipment and recommender system |
| CN109544396A (en) * | 2019-01-10 | 2019-03-29 | 腾讯科技（深圳）有限公司 | Account recommended method, device, server, terminal and storage medium |
| CN109948023A (en) * | 2019-03-08 | 2019-06-28 | 腾讯科技（深圳）有限公司 | Recommended acquisition methods, device and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112148972A (en) * | 2020-09-04 | 2020-12-29 | 北京明略昭辉科技有限公司 | Method and device for screening information to be recommended |
| TWI828139B (en) * | 2021-05-17 | 2024-01-01 | 韓商連加股份有限公司 | Method, computer device, and computer program to recommend account |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109359244B (en) | Personalized information recommendation method and device | |
| US20200410515A1 (en) | Method, system and computer readable medium for creating a profile of a user based on user behavior | |
| CN107172151B (en) | Method and device for pushing information | |
| CN108121737B (en) | Method, device and system for generating business object attribute identifier | |
| US20200250732A1 (en) | Method and apparatus for use in determining tags of interest to user | |
| CN111178970B (en) | Advertisement putting method and device, electronic equipment and computer readable storage medium | |
| CN108509497B (en) | Information recommendation method and device and electronic equipment | |
| US9311413B1 (en) | Faceted application search | |
| CN108550046B (en) | Resource and marketing recommendation method and device and electronic equipment | |
| Aggrawal et al. | Brand analysis framework for online marketing: ranking web pages and analyzing popularity of brands on social media | |
| CN106940705A (en) | A kind of method and apparatus for being used to build user's portrait | |
| WO2019169978A1 (en) | Resource recommendation method and device | |
| CN110413872B (en) | Method and device for displaying information | |
| CN108563681B (en) | Content recommendation method and device, electronic equipment and system | |
| CN107633416B (en) | Method, device and system for recommending service object | |
| US20210263978A1 (en) | Intelligent interface accelerating | |
| CN108885624A (en) | Information recommendation system and method | |
| US20100205052A1 (en) | Self-uploaded indexing and data clustering method and apparatus | |
| CN107808346B (en) | Evaluation method and evaluation device for potential target object | |
| WO2017205156A1 (en) | Providing travel or promotion based recommendation associated with social graph | |
| Dias et al. | Automating the extraction of static content and dynamic behaviour from e-commerce websites | |
| CN111125566A (en) | Information acquisition method and device, electronic equipment and storage medium | |
| CN110659404A (en) | Information recommendation method and device and storage medium | |
| CN111597454A (en) | Account recommendation method and device | |
| Azzam et al. | Electronic word of mouth (E_WOM) adoption via social media and its impact on online shoppers’ purchasing intention during corona pandemic. A case of Jordan |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200828 |
|
| RJ01 | Rejection of invention patent application after publication |