CN106127551A - Item recommendation method and device - Google Patents
Item recommendation method and device Download PDFInfo
- Publication number
- CN106127551A CN106127551A CN201610458566.8A CN201610458566A CN106127551A CN 106127551 A CN106127551 A CN 106127551A CN 201610458566 A CN201610458566 A CN 201610458566A CN 106127551 A CN106127551 A CN 106127551A
- Authority
- CN
- China
- Prior art keywords
- credit
- recommendation
- candidate recommended
- item
- user accounts
- 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 51
- 238000011835 investigation Methods 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 22
- 238000010606 normalization Methods 0.000 claims description 20
- 230000000694 effects Effects 0.000 abstract description 10
- 238000010586 diagram Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 5
- 230000006399 behavior Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a kind of item recommendation method and device, belong to field of computer technology.Described method includes: obtain the credit value of the multiple user accounts relevant to Candidate Recommendation project, the credit value of each user account is for reflecting the credit rating of described user account, obtaining the recommendation index of described Candidate Recommendation project, described recommendation index is used for indicating the described recommended degree of Candidate Recommendation project；Credit value according to the plurality of user account adjusts the recommendation index of described Candidate Recommendation project；Candidate Recommendation project described in the described recommendation exponent pair after adjusting is utilized to recommend.Solve some projects publisher in correlation technique and take some cheatings for the recommendation index improving project, the problem causing recommending index no longer to possess reference value, reach to improve the effect of the reference value recommending index.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a project recommendation method and device.
Background
With the continuous development of the internet, various items on the internet are rapidly increasing. In order to enable a user to quickly obtain a high quality item therefrom, a recommendation system typically determines a recommendation index for each item based on user-related parameters of the item (e.g., sales volume, browsing volume, praise volume, etc.). Correspondingly, the recommendation system sorts and recommends the items according to the recommendation index, and the higher the ranking of the items is, the higher the recognition degree of the user of the item is, and the higher the quality is. Recommender systems typically recommend items with higher recommendation indices to users.
However, some item publishers take some cheating actions to improve the recommendation index of an item, for example, some recommendation systems recommend an item according to the sales volume of the item, some merchants hire some people to buy their own items to improve the sales volume of the item, and the recommendation index does not have a reference value any more.
Disclosure of Invention
In order to solve the problem that some item publishers take some cheating behaviors in order to improve the recommendation index of an item in the related art, and the recommendation index no longer has a reference value, the embodiment of the invention provides an item recommendation method and device. The technical scheme is as follows:
in a first aspect, a method for recommending items is provided, the method comprising: the method comprises the steps of obtaining credit values of a plurality of user accounts related to a candidate recommended item, wherein the credit value of each user account is used for reflecting the credit degree of the user account, and obtaining a recommendation index of the candidate recommended item, and the recommendation index is used for indicating the recommended degree of the candidate recommended item; adjusting the recommendation index of the candidate recommended item according to the credit values of the plurality of user accounts; and recommending the candidate recommended items by using the adjusted recommendation index. The recommendation index of the recommended item is adjusted according to the credit degrees of the users participating in the recommended item, and the credit degrees of the users participating in the recommended item are more authentic, so that the recommendation index of the recommended item has a reference value, the problem that the recommendation index does not have the reference value any more due to the fact that some item publishers take some cheating actions to improve the recommendation index of the item in the related art is solved, the recommendation is performed by using the adjusted recommendation index, and the effect of improving the reference value of the recommendation index is achieved.
Optionally, the obtaining credit values of a plurality of user accounts related to the candidate recommended item includes: acquiring a plurality of user accounts participating in the candidate recommended item by using a recommending system, and acquiring credit values of the user accounts by using a credit investigation system; or, acquiring a plurality of user accounts participating in the candidate recommended item within a predetermined time before the current time by using the recommending system, and acquiring credit values of the plurality of user accounts by using the credit investigation system. Acquiring a plurality of user accounts participating in the candidate recommended item within a preset time by using a recommendation system, and acquiring credit values of the user accounts; the calculation amount of the candidate recommended item recommendation index is reduced when the candidate recommended item recommendation index is adjusted according to the credit values of the plurality of user accounts in the subsequent process.
Optionally, the recommending the candidate recommended item by using the adjusted recommendation index includes: acquiring a credit value of a recommended user account; determining a recommendation index corresponding to the credit value of the recommended user account, wherein the credit value and the recommendation index are in positive correlation; and recommending the candidate recommended items with the determined recommendation indexes to the recommended user account.
Optionally, the obtaining credit values of a plurality of user accounts related to the candidate recommended item includes: acquiring credit values of a plurality of user accounts related to the candidate recommended item at a preset time or at preset intervals; or when the increment value of the number of the user accounts related to the candidate recommended item reaches a preset threshold value, acquiring credit values of a plurality of user accounts related to the candidate recommended item. Because the plurality of user accounts related to the candidate recommended item are changed, the credit values of the plurality of user accounts related to the candidate recommended item are acquired at a preset time or at preset intervals or when the increment of the number of the user accounts related to the candidate recommended item reaches a preset threshold, so that the problem that the credit values of the plurality of user accounts related to the candidate recommended item are frequently acquired is avoided, and the recommendation index of the candidate recommended item is adjusted only at the preset time or at the preset intervals or when the increment of the number of the user accounts related to the candidate recommended item reaches the preset threshold.
Optionally, the adjusting the recommendation index of the candidate recommended item according to the credit values of the plurality of user accounts includes: normalizing the credit values of the user accounts, determining the average value of the normalized credit values of the user accounts as a first average value, and multiplying the first average value by the recommendation index of the candidate recommended item to obtain an adjusted recommendation index, wherein the normalized credit values of the user accounts are within a range of [0,1 ]; or determining the average value of the credit values of the plurality of user account numbers as a second average value, and multiplying the value after the second average value normalization processing by the recommendation index of the candidate recommended item to obtain an adjusted recommendation index, wherein the value after the second average value normalization processing is within the range of [0,1 ].
In a second aspect, an item recommendation apparatus is provided, where the apparatus includes an obtaining module, configured to obtain credit values of a plurality of user accounts related to a candidate recommended item, where the credit value of each user account is used to reflect credit of the user account to obtain a recommendation index of the candidate recommended item, where the recommendation index is used to indicate a degree to which the candidate recommended item is recommended; the adjusting module is used for adjusting the recommendation indexes of the candidate recommended items acquired by the acquiring module according to the credit values of the plurality of user accounts acquired by the acquiring module; and the recommending module is used for recommending the candidate recommended items by utilizing the recommending index adjusted by the adjusting module.
Optionally, the obtaining module includes: the first obtaining unit is used for obtaining a plurality of user accounts participating in the candidate recommended item by using a recommending system and obtaining credit values of the user accounts by using a credit investigation system; and the second acquisition unit is used for acquiring a plurality of user accounts participating in the candidate recommended item within a preset time before the current time by using the recommendation system and acquiring credit values of the plurality of user accounts by using the credit investigation system.
Optionally, the recommending module includes: the third acquisition unit is used for acquiring the credit value of the recommended user account; the determining unit is used for determining a recommendation index corresponding to the credit value of the recommended user account, and the credit value and the recommendation index are in positive correlation; and the recommending unit is used for recommending the candidate recommended items with the recommendation indexes determined by the determining unit to the recommended user account.
Optionally, the obtaining module further includes: the fourth acquisition unit is used for acquiring credit values of a plurality of user accounts related to the candidate recommended item at a preset time or at preset time intervals; and the fifth acquisition unit is used for acquiring the credit values of the plurality of user accounts related to the candidate recommended item when the increment value of the number of the user accounts related to the candidate recommended item reaches a preset threshold value.
Optionally, the adjusting module includes: the first adjusting unit is used for carrying out normalization processing on the credit values of the user accounts, determining the average value of the values of the user accounts after the normalization processing as a first average value, and multiplying the first average value by the recommendation index of the candidate recommendation item to obtain an adjusted recommendation index, wherein the values of the user accounts after the normalization processing are located in the range of [0,1 ]; and the second adjusting unit is used for determining the average value of the credit values of the plurality of user accounts as a second average value, multiplying the value after the second average value normalization processing by the recommendation index of the candidate recommendation item to obtain the adjusted recommendation index, wherein the value after the second average value normalization processing is within the range of [0,1 ].
In a third aspect, a method for recommending items is provided, the method comprising: the method comprises the steps of obtaining credit values of a plurality of user accounts related to candidate recommended items, wherein the credit value of each user account is used for reflecting the credit degree of the user account; generating a recommendation index of the candidate recommended item by combining credit values of user accounts participating in the candidate recommended item, wherein the recommendation index is used for indicating the recommended degree of the candidate recommended item; and recommending the candidate recommended items by using the recommendation index. The recommendation index is generated by combining the credit values of the user accounts participating in the candidate recommended item, and the credit degrees of a plurality of users participating in the recommended item are more authentic, so that the recommendation index of the recommended item has more reference value, the problem that the recommendation index does not have reference value any more due to the fact that some item publishers take some cheating behaviors to improve the recommendation index of the item in the related art is solved, the recommendation index is generated by combining the credit values of the user accounts participating in the candidate recommended item for recommendation, and the effect of improving the reference value of the recommendation index is achieved.
Optionally, the obtaining credit values of a plurality of user accounts related to the candidate recommended item includes: acquiring credit values of a plurality of user accounts related to the candidate recommended item at a preset time or at preset intervals; or when the increment value of the number of the user accounts related to the candidate recommended item reaches a preset threshold value, acquiring credit values of a plurality of user accounts related to the candidate recommended item.
Optionally, the recommending the candidate recommended item by using the recommendation index includes: acquiring a credit value of a recommended user account; determining a recommendation index corresponding to the credit value of the recommended user account, wherein the credit value and the recommendation index are in positive correlation; and recommending the candidate recommended items with the determined recommendation indexes to the recommended user account.
In a fourth aspect, there is provided an item recommendation apparatus, the apparatus comprising: the acquisition module is used for acquiring credit values of a plurality of user accounts related to the candidate recommended item, wherein the credit value of each user account is used for reflecting the credit degree of the user account; the generation module is used for generating a recommendation index of the candidate recommended item by combining the credit value of the user account participating in the candidate recommended item, wherein the recommendation index is used for indicating the recommended degree of the candidate recommended item; and the recommending module is used for recommending the candidate recommended items by utilizing the recommending index.
Optionally, the obtaining module includes: the first acquisition unit is used for acquiring credit values of a plurality of user accounts related to the candidate recommended item at a preset time or at preset time intervals; the second obtaining unit is used for obtaining credit values of a plurality of user accounts related to the candidate recommended item when the increment value of the number of the user accounts related to the candidate recommended item reaches a preset threshold value.
Optionally, the recommending module includes: the third acquisition unit is used for acquiring the credit value of the recommended user account; the determining unit is used for determining a recommendation index corresponding to the credit value of the recommended user account, and the credit value and the recommendation index are in positive correlation; and the recommending unit is used for recommending the candidate recommended items with the determined recommendation indexes to the recommended user account.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1A is a block diagram of a server provided by one embodiment of the invention;
FIG. 1B is a flowchart of a method for item recommendation provided by one embodiment of the present invention;
FIG. 2 is a flow chart of a method for item recommendation provided by another embodiment of the present invention;
FIG. 3A is a block diagram of a server provided by another embodiment of the present invention;
FIG. 3B is a flowchart of a method for item recommendation provided by yet another embodiment of the present invention;
FIG. 4 is a block diagram of an item recommendation apparatus provided in one embodiment of the present invention;
FIG. 5 is a block diagram of an item recommendation apparatus provided in another embodiment of the present invention;
FIG. 6 is a block diagram of an item recommendation apparatus according to still another embodiment of the present invention;
FIG. 7 is a block diagram of an item recommendation apparatus according to still another embodiment of the present invention;
FIG. 8 is a block diagram of an apparatus for item recommendation provided in some embodiments of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
Fig. 1A is a block diagram of a server provided by one embodiment of the invention. As shown in fig. 1A, the server 110 includes a recommendation system 110a, a credit investigation system 110b and an adjustment system 110 c. The recommendation system 110a is configured to determine candidate recommended items to be recommended according to the recommendation index of each item, the credit investigation system 110b is configured to record a credit value of each user account, and the credit value of each user account is used for reflecting the credit degree of the user account. The adjusting system 110c obtains the candidate recommended item and the recommendation index of the candidate recommended article from the recommending system 110a, and obtains the credit value of the user account related to the candidate recommended item from the credit system 110 b. The adjusting system 110c adjusts the recommendation index of the candidate recommended item according to the credit value of the user account related to the candidate recommended item, which is acquired from the credit system 110 b.
Referring to fig. 1B, a flowchart of a method for recommending an item, according to an embodiment of the present invention, is shown, where the method for recommending an item is applied to the server 110 shown in fig. 1A, and the method for recommending an item may include the following steps:
and 102, acquiring credit values of a plurality of user accounts related to the candidate recommended item, wherein the credit value of each user account is used for reflecting the credit degree of the user account.
And 104, acquiring a recommendation index of the candidate recommended item, wherein the recommendation index is used for indicating the recommended degree of the candidate recommended item.
And 106, adjusting the recommendation index of the candidate recommended item according to the credit values of the plurality of user accounts.
And step 108, recommending the candidate recommended items by using the adjusted recommendation index.
In summary, according to the item recommendation method provided by this embodiment, the recommendation index of the recommended item is adjusted according to the credit degrees of the multiple users participating in the recommended item, and the credit degrees of the multiple users participating in the recommended item are more authentic, so that the recommendation index of the recommended item has a higher reference value, and therefore, the problem that some item publishers take some cheating behaviors to improve the recommendation index of the item and the recommendation index no longer has the reference value in the related art is solved, and recommendation is performed by using the adjusted recommendation index, so that an effect of improving the reference value of the recommendation index is achieved.
Referring to fig. 2, a flowchart of a method for recommending an item, which is applied to the server 110 shown in fig. 1A, according to another embodiment of the present invention is shown, and the method for recommending an item may include the following steps:
step 201, a candidate recommended item needing to be recommended is determined by using a recommendation system.
The recommendation system may recommend at least one candidate recommended item to the user, where the candidate recommended item may be a commodity, an article, or a Point of Interest (POI). In this embodiment, the type of the candidate recommended item is not particularly limited, and may be determined according to actual situations.
For example, when the recommendation system is applied to an online shopping platform, the candidate recommended item may be a commodity sold on the online shopping platform, and the candidate recommended item may also be a shop for selling the commodity on the online shopping platform. For another example, when the recommendation system is applied to a reader application platform, the candidate recommendation item may be an article or an e-book provided on the reader application platform.
The recommendation system according to this embodiment has a function of determining items to be recommended according to the user-related parameters. Specifically, the recommendation system obtains user-related parameters of each item in the system, determines items to be recommended according to the user-related parameters, and determines the items as candidate recommended items.
The user-related parameter mentioned herein is generally determined by the recommendation system according to the number of user accounts participating in the item, for example, the user-related parameter may be any one of a sales volume of the item, a browsing volume of the item, a praise volume of the item, and a collection volume of the item.
It should be noted that the determination of the item to be recommended by the recommendation system in step 201 may be implemented in various ways and can be implemented by a person of ordinary skill in the art, so the way that the recommendation system determines the item to be recommended is not specifically limited in this embodiment, and may be determined according to actual conditions, and the item that the recommendation system determines to be recommended is determined as a candidate recommended item.
For example, the recommendation system inquires that the user may be interested in the hallucinography-like novel, and the recommendation system takes the top 10 novel with the highest collection as candidate recommendation items. For another example, the user searches for commodity refrigerators on the online shopping platform, and the recommendation system recommends all commodity refrigerators sold on the online shopping platform to the user in the order from high sales volume to low sales volume, and then determines all commodity refrigerators sold on the online shopping platform as candidate recommended items.
Step 202, obtaining credit values of a plurality of user accounts related to the candidate recommended item, wherein the credit value of each user account is used for reflecting the credit degree of the user account.
The credit system is a system for recording credit programs of users, and generally speaking, credit values are used in the credit system to mark credit degrees of user accounts. The higher the credit value of the user account is, the higher the credit degree of the user account is; accordingly, a lower credit value for a user account indicates a lower credit rating for the user account.
It should be noted that, in actual implementation, the credit investigation system may be used to obtain the recommendation index of the user account, and the manner in which the credit investigation system obtains the recommendation index of the user account belongs to the technology that those skilled in the art can implement, and algorithms of different credit investigation systems in determining the credit value may be different, and are not described here again.
Generally, the user account related to the candidate recommended item refers to the user account which has picked up or redeemed or browsed the candidate recommended item. Specifically, the user account related to the candidate recommended item corresponds to the mode that the recommendation system determines the candidate recommended item.
For example, when the recommendation system determines a candidate recommended item according to the sales volume of the item, the user account which purchased the candidate recommended item is determined as the user account related to the candidate recommended item. For another example, when the recommendation system determines a candidate recommended item according to the browsing volume of the item, the user account that browses the candidate recommended item is determined as the user account related to the candidate recommended item.
Optionally, the user account related to the candidate recommended item may be the user account issuing the candidate recommended item. For example, when the candidate recommended item is a paper, the user account publishing the paper may be determined as the user account related to the paper. For another example, when the candidate recommended item is a commodity sold on the online shopping platform, the user account for selling the commodity may be determined as the user account related to the candidate recommended item.
Optionally, the user account related to the candidate recommended item may be a user account participating in the candidate recommended item, and specifically includes a user account which has picked up or redeemed or browsed the candidate recommended item and a user account which issues the candidate recommended item.
And step 203, for each candidate recommended item, acquiring a recommendation index of the candidate recommended item by using the recommendation system, wherein the recommendation index is used for indicating the recommended degree of the candidate recommended item.
Generally, for each item included in a recommendation system, the recommendation system determines a recommendation index for the item based on user-related parameters. The higher the recommendation index of the item is, the higher the recommendation degree of the item by the recommendation system is; correspondingly, the lower the recommendation index of an item, the lower the recommendation degree of the item by the recommendation system.
In practical implementation, the recommendation system may be used to obtain the recommendation index of the candidate recommended item, and the manner in which the recommendation system obtains the recommendation index of the candidate recommended item belongs to the technology that can be implemented by those skilled in the art, and algorithms of different recommendation systems in determining the recommendation index may be different, and are not described here again.
It should be noted that, the execution order of step 202 and step 203 is not sequential, and may also be executed simultaneously.
And 204, adjusting the recommendation index of the candidate recommended item according to the credit values of the plurality of user accounts.
Specifically, the present step can be implemented by the following two possible embodiments:
in a first possible implementation manner, the credit values of the plurality of user accounts are normalized, an average value of the normalized credit values of the plurality of user accounts is determined as a first average value, the first average value is multiplied by the recommendation index of the candidate recommendation item to obtain an adjusted recommendation index, and the normalized credit values of the plurality of user accounts are within a range of [0,1 ].
In a second possible implementation manner, the average value of the credit values of the plurality of user accounts is determined as a second average value, and the adjusted recommendation index is obtained by multiplying the value after the second average value normalization processing by the recommendation index of the candidate recommended item, where the value after the second average value normalization processing is within the range of [0,1 ].
The normalization processing method is not particularly limited in this embodiment, and may be determined according to actual conditions. For example, in the credit investigation system, the credit score is 100, the credit value of a certain user account is 80, and the normalized value obtained by dividing the credit value of the user account by the credit score is 0.8.
For another example, the credit values of all user accounts in the credit investigation system are obtained, a maximum value m and a minimum value n of the credit value of the credit investigation are determined, and if the credit value of the ith user account is represented by Di, the normalization processing formula can be
And step 205, recommending the candidate recommended items by using the adjusted recommendation index.
Specifically, the present step can be implemented by the following two possible embodiments:
in a first possible implementation manner, items needing to be recommended are determined again from the candidate recommended items according to the adjusted recommendation index, and the items are ranked and recommended according to the adjusted recommendation index.
In a second possible implementation, the candidate recommended items are reordered according to the adjusted recommendation index, and recommended according to the adjusted recommendation order.
In summary, according to the item recommendation method provided by this embodiment, the recommendation index of the recommended item is adjusted according to the credit degrees of the multiple users participating in the recommended item, and the credit degrees of the multiple users participating in the recommended item are more authentic, so that the recommendation index of the recommended item has a higher reference value, and therefore, the problem that some item publishers take some cheating behaviors to improve the recommendation index of the item and the recommendation index no longer has the reference value in the related art is solved, and recommendation is performed by using the adjusted recommendation index, so that an effect of improving the reference value of the recommendation index is achieved.
In addition, because the plurality of user accounts related to the candidate recommended item are changed, the credit values of the plurality of user accounts related to the candidate recommended item are acquired at a predetermined time or at predetermined intervals or when the increment of the number of the user accounts related to the candidate recommended item reaches a predetermined threshold, so that the problem of frequently acquiring the credit values of the plurality of user accounts related to the candidate recommended item is avoided, and the recommendation index of the candidate recommended item is adjusted only at the predetermined time or at predetermined intervals or when the increment of the number of the user accounts related to the candidate recommended item reaches the predetermined threshold.
Fig. 3A is a block diagram of a server provided by another embodiment of the present invention. As shown in fig. 3A, the server 310 includes a recommendation system 310a and a credit investigation system 310 b. The credit investigation system 310b is used for recording the credit value of each user account, and the credit value of each user account is used for reflecting the credit degree of the user account. For each candidate recommended item, the recommendation system 310a generates a recommendation index for the candidate recommended item in combination with a local recommendation policy and a credit value of a user in the credit investigation system related to the candidate recommended item.
Referring to fig. 3B, a flowchart of a method for recommending an item according to still another embodiment of the present invention is shown, where the method for recommending an item is applied to the server 310 shown in fig. 3A, and the method for recommending an item may include the following steps:
step 302, obtaining credit values of a plurality of user accounts related to the candidate recommended item, wherein the credit value of each user account is used for reflecting the credit degree of the user account.
Generally, the user account related to the candidate recommended item refers to the user account which has picked up or redeemed or browsed the candidate recommended item.
The credit system is a system for recording credit programs of users, and generally speaking, credit values are used in the credit system to mark credit degrees of user accounts. The higher the credit value of the user account is, the higher the credit degree of the user account is; accordingly, a lower credit value for a user account indicates a lower credit rating for the user account.
It should be noted that, in actual implementation, the credit investigation system may be used to obtain the recommendation index of the user account, and the manner in which the credit investigation system obtains the recommendation index of the user account belongs to the technology that those skilled in the art can implement, and algorithms of different credit investigation systems in determining the credit value may be different, and are not described here again.
And step 304, generating a recommendation index of the candidate recommended item by combining the credit values of the user accounts participating in the candidate recommended item, wherein the recommendation index is used for indicating the recommended degree of the candidate recommended item.
For example, the candidate recommended item may be a commodity sold on an online shopping platform, and the recommendation index of the commodity is determined according to the sales volume of the commodity and the credit data of the user account number of the purchased commodity. Specifically, the sales volume of the article a is 1000, and the average value of the credit values of the user accounts which have purchased the article a is 0.8. And multiplying the sales volume of the commodity A by the credit value average value of 0.8 of the user account number which purchased the commodity A to obtain the recommendation index of the commodity A, wherein the recommendation index is 800.
The recommendation system may select a plurality of recommendation strategies to generate recommendation indexes of the candidate recommended items, where the recommendation strategies at least include credit values of user accounts participating in the candidate recommended items, and this embodiment does not describe any more recommendation strategies except the credit values of the user accounts participating in the candidate recommended items one by one.
And step 306, recommending the candidate recommended items by using the recommendation index.
The explanation of this step can refer to the explanation of step 205, which is not described herein again.
In summary, according to the item recommendation method provided by this embodiment, the recommendation index is generated by combining the credit values of the user accounts participating in the candidate recommended item, and the credit degrees of the multiple users participating in the recommended item are more authentic, so that the recommendation index of the recommended item has a reference value, and therefore the problem that the recommendation index no longer has the reference value due to some cheating actions taken by some item publishers to improve the recommendation index of the item in the related art is solved, and the recommendation index is generated by combining the credit values of the user accounts participating in the candidate recommended item for recommendation, so that the effect of improving the reference value of the recommendation index is achieved.
Optionally, the credit values of a plurality of user accounts related to the candidate recommended item are obtained, and the method may also be implemented by the following two possible implementation manners:
in a first possible implementation manner, the credit values of a plurality of user accounts related to the candidate recommended item are acquired at a predetermined time or every predetermined time.
The predetermined time may be set by a system developer or by a user, and the predetermined time is not specifically limited in this embodiment and may be determined according to actual conditions. For example, the user may set the predetermined time as 12 pm every day, and then obtain credit values of a plurality of user accounts related to the candidate recommended item at 12 pm every day, and start a process of adjusting the recommendation index of the candidate recommended item.
The predetermined time may be set by a system developer or by a user, and may be set to any time period. For example, the predetermined time may be 24 hours or 1 hour.
In a second possible implementation manner, when the increase value of the number of the user accounts related to the candidate recommended item reaches a preset threshold value, the credit values of the plurality of user accounts related to the candidate recommended item are acquired.
Generally, the predetermined threshold is set by a system developer, and the predetermined threshold is not specifically limited in this embodiment and may be determined according to actual situations. Taking the user account related to the candidate recommended item as the user account for purchasing the candidate recommended item as an example, the predetermined threshold is 100, and when the sales volume of the candidate recommended item increases by 100, the credit values of the plurality of user accounts related to the candidate recommended item are acquired, and a process of adjusting the recommendation index of the candidate recommended item is started.
Optionally, the obtaining of the credit values of the plurality of user accounts related to the candidate recommended item may be implemented by the following two possible implementations.
In a first possible implementation manner, a plurality of user accounts participating in a candidate recommended item are acquired by a recommendation system, and credit values of the user accounts are acquired by a credit investigation system.
For example, when the recommendation system determines a candidate recommended item according to the sales volume of a commodity, the credit values of all user accounts which purchased the commodity are obtained.
In a second possible implementation manner, a plurality of user accounts participating in a candidate recommended item within a predetermined time before the current time are acquired by a recommendation system, and credit values of the plurality of user accounts are acquired by the credit investigation system.
The predetermined time period is usually set by a system developer, and the predetermined time period is not specifically limited in this embodiment and can be determined according to actual conditions.
For example, when the preset time set by the system developer is one month and the recommendation system determines the candidate recommended item according to the sales volume of the commodity, the credit value of the user account which purchased the candidate recommended item within one month is acquired.
Acquiring a plurality of user accounts participating in the candidate recommended item within a preset time by using a recommending system, and acquiring credit values of the user accounts by using a credit investigation system; the calculation amount of the candidate recommended item recommendation index is reduced when the candidate recommended item recommendation index is adjusted according to the credit values of the plurality of user accounts in the subsequent process.
The following are embodiments of the apparatus of the present invention that may be used to perform embodiments of the method of the present invention. For details which are not disclosed in the embodiments of the apparatus of the present invention, reference is made to the embodiments of the method of the present invention.
Referring to fig. 4, a block diagram of an item recommendation apparatus according to an embodiment of the present invention is shown, the item recommendation apparatus is applied to the server 110 shown in fig. 1A, and the item recommendation apparatus may include: an acquisition module 410, an adjustment module 420, and a recommendation module 430.
The obtaining module 410 is configured to obtain credit values of a plurality of user accounts related to a candidate recommended item, where the credit value of each user account is used to reflect the credit degree of the user account, and obtain a recommendation index of the candidate recommended item, where the recommendation index is used to indicate the degree to which the candidate recommended item is recommended.
The adjusting module 420 is configured to adjust the recommendation index of the candidate recommended item acquired by the acquiring module 410 according to the credit values of the plurality of user accounts acquired by the acquiring module 410.
And the recommending module 430 is configured to recommend the candidate recommended item by using the recommendation index adjusted by the adjusting module 420.
In summary, the item recommendation apparatus provided in this embodiment adjusts the recommendation index of the recommended item according to the credits of the users participating in the recommended item, and because the credits of the users participating in the recommended item are more authentic, the recommendation index of the recommended item has a higher reference value, so that a problem that some item publishers take some cheating actions to improve the recommendation index of the item and the recommendation index no longer has the reference value in the related art is solved, and recommendation is performed by using the adjusted recommendation index, thereby achieving an effect of improving the reference value of the recommendation index.
Referring to fig. 5, which shows a block diagram of an item recommendation apparatus according to another embodiment of the present invention, the item recommendation apparatus is applied to the server 110 shown in fig. 1A, and the item recommendation apparatus may include: an acquisition module 510, an adjustment module 520, and a recommendation module 530.
The obtaining module 510 is configured to obtain credit values of a plurality of user accounts related to a candidate recommended item, where the credit value of each user account is used to reflect the credit degree of the user account, and obtain a recommendation index of the candidate recommended item, where the recommendation index is used to indicate the degree to which the candidate recommended item is recommended.
An adjusting module 520, configured to adjust the recommendation index of the candidate recommended item acquired by the acquiring module 510 according to the credit values of the multiple user accounts acquired by the acquiring module 510.
And the recommending module 530 is configured to recommend the candidate recommended item by using the recommendation index adjusted by the adjusting module 520.
Optionally, the obtaining module 510 includes: a first acquisition unit 510a and a second acquisition unit 510 b.
The first obtaining unit 510a is configured to obtain, by using a recommendation system, a plurality of user accounts participating in the candidate recommended item, and obtain, by using a credit investigation system, credit values of the plurality of user accounts.
A second obtaining unit 510b, configured to obtain, by using the recommendation system, a plurality of user accounts participating in the candidate recommended item within a predetermined time before the current time, and obtain, by using the credit investigation system, credit values of the plurality of user accounts.
Optionally, the recommending module 530 includes: a third obtaining unit 530c, a determining unit 530d, and a recommending unit 530 e.
A third obtaining unit 530a, configured to obtain a credit value of the recommended user account.
The determining unit 530b is configured to determine a recommendation index corresponding to a credit value of the recommended user account, where the credit value and the recommendation index are in a positive correlation.
A recommending unit 530c, configured to recommend the candidate recommended item with the recommendation index determined by the determining unit 510b to the recommended user account.
Optionally, the obtaining module 510 includes: a third acquisition unit 510c and a fourth acquisition unit 510 d.
The fourth obtaining unit 510c is configured to obtain credit values of a plurality of user accounts related to the candidate recommended item at a predetermined time or at predetermined intervals.
A fifth obtaining unit 510d, configured to obtain credit values of multiple user accounts related to the candidate recommended item when an increase value of the number of user accounts related to the candidate recommended item reaches a predetermined threshold.
Optionally, the adjusting module 520 further includes: a first adjusting unit 520a and a second adjusting unit 520 b.
The first adjusting unit 520a is configured to normalize the credit values of the plurality of user accounts, determine an average value of the normalized credit values of the plurality of user accounts as a first average value, and multiply the first average value by the recommendation index of the candidate recommendation item to obtain an adjusted recommendation index, where the normalized credit values of the plurality of user accounts are within a range of [0,1 ];
the second adjusting unit 520b is configured to determine an average value of credit values of the plurality of user account numbers as a second average value, and multiply a value after the second average value normalization processing by the recommendation index of the candidate recommended item to obtain an adjusted recommendation index, where the value after the second average value normalization processing is within a range of [0,1 ].
In summary, the item recommendation apparatus provided in this embodiment adjusts the recommendation index of the recommended item according to the credits of the users participating in the recommended item, and because the credits of the users participating in the recommended item are more authentic, the recommendation index of the recommended item has a higher reference value, so that a problem that some item publishers take some cheating actions to improve the recommendation index of the item and the recommendation index no longer has the reference value in the related art is solved, and recommendation is performed by using the adjusted recommendation index, thereby achieving an effect of improving the reference value of the recommendation index.
Referring to fig. 6, which shows a block diagram of an item recommendation apparatus according to still another embodiment of the present invention, the item recommendation apparatus is applied in the server 310 shown in fig. 3A, and the item recommendation apparatus may include: an acquisition module 610, a generation module 620, and a recommendation module 630.
The obtaining module 610 is configured to obtain credit values of a plurality of user accounts related to the candidate recommended item, where the credit value of each user account is used to reflect the credit degree of the user account.
The generating module 620 is configured to generate a recommendation index of the candidate recommended item in combination with the credit value of the user account participating in the candidate recommended item, which is acquired by the acquiring module 610, where the recommendation index is used to indicate a degree to which the candidate recommended item is recommended.
And a recommending module 630, configured to recommend the candidate recommended item by using the recommendation index.
In summary, the item recommendation apparatus provided in this embodiment generates the recommendation index by combining the credit values of the user accounts participating in the candidate recommended item, and the credit degrees of the multiple users participating in the recommended item are more authentic, so that the recommendation index of the recommended item has a reference value, thereby solving the problem that the recommendation index no longer has the reference value due to some cheating actions taken by some item publishers to improve the recommendation index of the item in the related art, and generating the recommendation index for recommendation by combining the credit values of the user accounts participating in the candidate recommended item, thereby achieving an effect of improving the reference value of the recommendation index.
Referring to fig. 7, which shows a block diagram of an item recommendation apparatus according to still another embodiment of the present invention, the item recommendation apparatus is applied to the server 310 shown in fig. 3A, and the item recommendation apparatus may include: an acquisition module 710, a generation module 720, and a recommendation module 730.
The obtaining module 710 is configured to obtain credit values of a plurality of user accounts related to the candidate recommended item, where the credit value of each user account is used to reflect the credit degree of the user account.
The generating module 720 is configured to generate, in combination with the credit value of the user account participating in the candidate recommended item, which is acquired by the acquiring module 710, a recommendation index of the candidate recommended item, where the recommendation index is used to indicate a degree to which the candidate recommended item is recommended.
And the recommending module 730 is used for recommending the candidate recommended item by using the recommendation index.
Optionally, the obtaining module 710 includes: a first acquisition unit 710a and a second acquisition unit 710 b.
The first obtaining unit 710a obtains credit values of a plurality of user accounts related to the candidate recommended item at a predetermined time or at predetermined intervals.
The second obtaining unit 710b obtains credit values of a plurality of user accounts related to the candidate recommended item when an increase value of the number of user accounts related to the candidate recommended item reaches a predetermined threshold value.
In summary, the item recommendation apparatus provided in this embodiment,
optionally, the recommending module 730 includes: a third obtaining unit 730a, a determining unit 730b and a recommending unit 730 c.
A third obtaining unit 730a, configured to obtain a credit value of the recommended user account.
The determining unit 730b is configured to determine a recommendation index corresponding to the credit value of the recommended user account acquired by the third acquiring unit 730a, where the credit value and the recommendation index are in a positive correlation.
A recommending unit 730c, configured to recommend the candidate recommended item with the recommendation index determined by the determining unit 730b to the recommended user account.
In summary, the item recommendation apparatus provided in this embodiment generates the recommendation index by combining the credit values of the user accounts participating in the candidate recommended item, and the credit degrees of the multiple users participating in the recommended item are more authentic, so that the recommendation index of the recommended item has a reference value, thereby solving the problem that the recommendation index no longer has the reference value due to some cheating actions taken by some item publishers to improve the recommendation index of the item in the related art, and generating the recommendation index for recommendation by combining the credit values of the user accounts participating in the candidate recommended item, thereby achieving an effect of improving the reference value of the recommendation index.
FIG. 8 is a block diagram illustrating an apparatus for item recommendation in accordance with some embodiments. For example, the apparatus 800 may be provided as a network-side device, and the apparatus 800 is configured to implement the item recommendation method implemented by a server according to the foregoing embodiment. Referring to fig. 8, the apparatus 800 includes a processing component 802 that further includes one or more processors and memory resources, represented by memory 804, for storing instructions, such as applications, that are executable by the processing component 802. The application programs stored in memory 804 may include one or more modules that each correspond to a set of instructions. Further, the processing component 802 is configured to execute instructions to perform the item recommendation method described above.
The device 800 may also include a power component 806 configured to perform power management of the device 800, a wired or wireless network interface 808 configured to connect the device 800 to a network, and an input/output (I/O) interface 810. The apparatus 800 may operate based on an operating system stored in the memory 804, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.
It should be noted that: the item recommendation apparatus provided in the above embodiment only exemplifies the division of the above functional modules when recommending items, and in practical applications, the above function allocation may be completed by different functional modules as needed, that is, the internal structure of the server is divided into different functional modules to complete all or part of the above described functions. In addition, the item recommendation apparatus and the item recommendation method provided by the above embodiments belong to the same concept, and specific implementation processes thereof are detailed in the method embodiments and are not described herein again.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (16)
1. A method for recommending items, the method comprising:
the method comprises the steps of obtaining credit values of a plurality of user accounts related to a candidate recommended item, wherein the credit value of each user account is used for reflecting the credit degree of the user account, and obtaining a recommendation index of the candidate recommended item, and the recommendation index is used for indicating the recommended degree of the candidate recommended item;
adjusting the recommendation index of the candidate recommended item according to the credit values of the plurality of user accounts;
and recommending the candidate recommended items by using the adjusted recommendation index.
2. The method of claim 1, wherein obtaining credit values for a plurality of user accounts associated with the candidate recommended item comprises:
acquiring a plurality of user accounts participating in the candidate recommended item by using a recommending system, and acquiring credit values of the user accounts by using a credit investigation system; or,
and acquiring a plurality of user accounts participating in the candidate recommended item within a preset time before the current moment by using the recommending system, and acquiring credit values of the plurality of user accounts by using the credit investigation system.
3. The method of claim 1, wherein the recommending the candidate recommended item by using the adjusted recommendation index comprises:
acquiring a credit value of a recommended user account;
determining a recommendation index corresponding to the credit value of the recommended user account, wherein the credit value and the recommendation index are in positive correlation;
and recommending the candidate recommended items with the determined recommendation indexes to the recommended user account.
4. The method of claim 1, wherein obtaining credit values for a plurality of user accounts associated with the candidate recommended item comprises:
acquiring credit values of a plurality of user accounts related to the candidate recommended item at a preset time or at preset intervals;
or,
and when the increment value of the number of the user accounts related to the candidate recommended item reaches a preset threshold value, acquiring credit values of a plurality of user accounts related to the candidate recommended item.
5. The method of any one of claims 1 to 4, wherein the adjusting the recommendation index of the candidate recommended item according to the credit values of the plurality of user account numbers comprises:
normalizing the credit values of the user accounts, determining the average value of the normalized credit values of the user accounts as a first average value, and multiplying the first average value by the recommendation index of the candidate recommended item to obtain an adjusted recommendation index, wherein the normalized credit values of the user accounts are within a range of [0,1 ];
or,
and determining the average value of the credit values of the plurality of user account numbers as a second average value, and multiplying the value after the second average value normalization processing by the recommendation index of the candidate recommended item to obtain an adjusted recommendation index, wherein the value after the second average value normalization processing is within the range of [0,1 ].
6. A method for recommending items, the method comprising:
the method comprises the steps of obtaining credit values of a plurality of user accounts related to candidate recommended items, wherein the credit value of each user account is used for reflecting the credit degree of the user account;
generating a recommendation index of the candidate recommended item by combining credit values of user accounts participating in the candidate recommended item, wherein the recommendation index is used for indicating the recommended degree of the candidate recommended item;
and recommending the candidate recommended items by using the recommendation index.
7. The method of claim 6, wherein obtaining credit values for a plurality of user accounts associated with the candidate recommended item comprises:
acquiring credit values of a plurality of user accounts related to the candidate recommended item at a preset time or at preset intervals;
or,
and when the increment value of the number of the user accounts related to the candidate recommended item reaches a preset threshold value, acquiring credit values of a plurality of user accounts related to the candidate recommended item.
8. The method of claim 6 or 7, wherein the recommending the candidate recommended item by using the recommendation index comprises:
acquiring a credit value of a recommended user account;
determining a recommendation index corresponding to the credit value of the recommended user account, wherein the credit value and the recommendation index are in positive correlation;
and recommending the candidate recommended items with the determined recommendation indexes to the recommended user account.
9. An item recommendation apparatus, characterized in that the apparatus comprises:
the acquisition module is used for acquiring credit values of a plurality of user accounts related to a candidate recommended item, wherein the credit value of each user account is used for reflecting the credit degree of the user account, and acquiring a recommendation index of the candidate recommended item, and the recommendation index is used for indicating the recommended degree of the candidate recommended item;
the adjusting module is used for adjusting the recommendation indexes of the candidate recommended items acquired by the acquiring module according to the credit values of the plurality of user accounts acquired by the acquiring module;
and the recommending module is used for recommending the candidate recommended items by utilizing the recommending index adjusted by the adjusting module.
10. The apparatus of claim 9, wherein the obtaining module comprises:
the first obtaining unit is used for obtaining a plurality of user accounts participating in the candidate recommended item by using a recommending system and obtaining credit values of the user accounts by using a credit investigation system;
and the second acquisition unit is used for acquiring a plurality of user accounts participating in the candidate recommended item within a preset time before the current time by using the recommendation system and acquiring credit values of the plurality of user accounts by using the credit investigation system.
11. The apparatus of claim 9, wherein the recommendation module comprises:
the third acquisition unit is used for acquiring the credit value of the recommended user account;
the determining unit is used for determining a recommendation index corresponding to the credit value of the recommended user account, and the credit value and the recommendation index are in positive correlation;
and the recommending unit is used for recommending the candidate recommended items with the recommendation indexes determined by the determining unit to the recommended user account.
12. The apparatus of claim 9, wherein the obtaining module further comprises:
the fourth acquisition unit is used for acquiring credit values of a plurality of user accounts related to the candidate recommended item at a preset time or at preset time intervals;
and the fifth acquisition unit is used for acquiring the credit values of the plurality of user accounts related to the candidate recommended item when the increment value of the number of the user accounts related to the candidate recommended item reaches a preset threshold value.
13. The apparatus of any of claims 9 to 12, wherein the adjustment module comprises:
the first adjusting unit is used for carrying out normalization processing on the credit values of the user accounts, determining the average value of the values of the user accounts after the normalization processing as a first average value, and multiplying the first average value by the recommendation index of the candidate recommendation item to obtain an adjusted recommendation index, wherein the values of the user accounts after the normalization processing are located in the range of [0,1 ];
and the second adjusting unit is used for determining the average value of the credit values of the plurality of user accounts as a second average value, multiplying the value after the second average value normalization processing by the recommendation index of the candidate recommendation item to obtain an adjusted recommendation index, wherein the value after the second average value normalization processing is within the range of [0,1 ].
14. An item recommendation apparatus, characterized in that the apparatus comprises:
the acquisition module is used for acquiring credit values of a plurality of user accounts related to the candidate recommended item, wherein the credit value of each user account is used for reflecting the credit degree of the user account;
the generation module is used for generating a recommendation index of the candidate recommended item by combining the credit value of the user account participating in the candidate recommended item, wherein the recommendation index is used for indicating the recommended degree of the candidate recommended item;
and the recommending module is used for recommending the candidate recommended items by utilizing the recommending index.
15. The apparatus of claim 14, wherein the obtaining module comprises:
the first acquisition unit is used for acquiring credit values of a plurality of user accounts related to the candidate recommended item at a preset time or at preset time intervals;
and the second acquisition unit is used for acquiring credit values of a plurality of user accounts related to the candidate recommended item when the increment value of the number of the user accounts related to the candidate recommended item reaches a preset threshold value.
16. The apparatus of claim 14 or 15, wherein the recommendation module comprises:
the third acquisition unit is used for acquiring the credit value of the recommended user account;
the determining unit is used for determining a recommendation index corresponding to the credit value of the recommended user account, and the credit value and the recommendation index are in positive correlation;
and the recommending unit is used for recommending the candidate recommended items with the determined recommendation indexes to the recommended user account.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610458566.8A CN106127551A (en) | 2016-06-22 | 2016-06-22 | Item recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610458566.8A CN106127551A (en) | 2016-06-22 | 2016-06-22 | Item recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106127551A true CN106127551A (en) | 2016-11-16 |
Family
ID=57268420
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610458566.8A Pending CN106127551A (en) | 2016-06-22 | 2016-06-22 | Item recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106127551A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106528813A (en) * | 2016-11-18 | 2017-03-22 | 腾讯科技（深圳）有限公司 | Multimedia recommendation method and apparatus |
| CN108074158A (en) * | 2016-11-18 | 2018-05-25 | 腾讯科技（深圳）有限公司 | The user of shared lease platform recommends page display method, device and server |
| CN108416684A (en) * | 2017-02-10 | 2018-08-17 | 腾讯科技（深圳）有限公司 | A kind of credibility appraisal procedure, device and the server of account main body |
| CN108763318A (en) * | 2018-04-27 | 2018-11-06 | 达而观信息科技（上海）有限公司 | item recommendation method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101140651A (en) * | 2006-09-04 | 2008-03-12 | 腾讯科技（深圳）有限公司 | Display objects ordering method and system |
| CN102004979A (en) * | 2009-09-03 | 2011-04-06 | 叶克 | System and method for providing commodity matching and promoting services |
| CN103971256A (en) * | 2013-01-25 | 2014-08-06 | 阿里巴巴集团控股有限公司 | Information push method and device |
| CN105677831A (en) * | 2016-01-04 | 2016-06-15 | 拉扎斯网络科技（上海）有限公司 | Method and device for determining recommended merchants |
-
2016
- 2016-06-22 CN CN201610458566.8A patent/CN106127551A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101140651A (en) * | 2006-09-04 | 2008-03-12 | 腾讯科技（深圳）有限公司 | Display objects ordering method and system |
| CN102004979A (en) * | 2009-09-03 | 2011-04-06 | 叶克 | System and method for providing commodity matching and promoting services |
| CN103971256A (en) * | 2013-01-25 | 2014-08-06 | 阿里巴巴集团控股有限公司 | Information push method and device |
| CN105677831A (en) * | 2016-01-04 | 2016-06-15 | 拉扎斯网络科技（上海）有限公司 | Method and device for determining recommended merchants |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106528813A (en) * | 2016-11-18 | 2017-03-22 | 腾讯科技（深圳）有限公司 | Multimedia recommendation method and apparatus |
| CN108074158A (en) * | 2016-11-18 | 2018-05-25 | 腾讯科技（深圳）有限公司 | The user of shared lease platform recommends page display method, device and server |
| CN108074158B (en) * | 2016-11-18 | 2021-12-21 | 腾讯科技（深圳）有限公司 | User recommendation page display method and device of shared rental platform and server |
| CN108416684A (en) * | 2017-02-10 | 2018-08-17 | 腾讯科技（深圳）有限公司 | A kind of credibility appraisal procedure, device and the server of account main body |
| CN108416684B (en) * | 2017-02-10 | 2021-09-07 | 腾讯科技（深圳）有限公司 | Method and device for evaluating credibility of account main body and server |
| CN108763318A (en) * | 2018-04-27 | 2018-11-06 | 达而观信息科技（上海）有限公司 | item recommendation method and device |
| CN108763318B (en) * | 2018-04-27 | 2022-04-19 | 达而观信息科技（上海）有限公司 | Item recommendation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10409821B2 (en) | Search result ranking using machine learning | |
| US8484099B1 (en) | Method, medium, and system for behavior-based recommendations of product upgrades | |
| US8793154B2 (en) | Customer relevance scores and methods of use | |
| US8706716B2 (en) | Iterative and dynamic search of publicly available data based on augmentation of search terms and validation of data relevance | |
| US8666834B2 (en) | Item recommendation system, item recommendation method and program | |
| WO2018121700A1 (en) | Method and device for recommending application information based on installed application, terminal device, and storage medium | |
| US20150339759A1 (en) | Detecting product attributes associated with product upgrades based on behaviors of users | |
| US20140372203A1 (en) | Quality-weighted second-price auctions for advertisements | |
| EP2791832A1 (en) | Personalized information pushing method and device | |
| US20140258330A1 (en) | Search result ranking using query clustering | |
| US20130231975A1 (en) | Product cycle analysis using social media data | |
| US20120116875A1 (en) | Providing advertisements based on user grouping | |
| US20140032475A1 (en) | Systems And Methods For Determining Customer Brand Commitment Using Social Media Data | |
| US11216518B2 (en) | Systems and methods of providing recommendations of content items | |
| CN106127551A (en) | Item recommendation method and device | |
| WO2013089592A2 (en) | Information graph | |
| EP2766826B1 (en) | Searching information | |
| US10937070B2 (en) | Collaborative filtering to generate recommendations | |
| CN112149003B (en) | Commodity community recommendation method and device and computer equipment | |
| WO2022081267A1 (en) | Product evaluation system and method of use | |
| Le et al. | Explainable recommendation with comparative constraints on product aspects | |
| US20150278907A1 (en) | User Inactivity Aware Recommendation System | |
| US20160132902A1 (en) | Search and Rank Organizations | |
| CN111429214A (en) | Transaction data-based buyer and seller matching method and device | |
| KR101081947B1 (en) | Hybrid recommendation method and system for large scale data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161116 |
|
| RJ01 | Rejection of invention patent application after publication |