CN111506816B - Recommendation method, recommendation device, recommendation equipment and storage medium - Google Patents
Recommendation method, recommendation device, recommendation equipment and storage medium Download PDFInfo
- Publication number
- CN111506816B CN111506816B CN202010311448.0A CN202010311448A CN111506816B CN 111506816 B CN111506816 B CN 111506816B CN 202010311448 A CN202010311448 A CN 202010311448A CN 111506816 B CN111506816 B CN 111506816B
- Authority
- CN
- China
- Prior art keywords
- article
- item
- recommended
- historical
- favorite
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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—Recommending goods or services
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a recommendation method, a recommendation device, recommendation equipment and a storage medium, wherein the recommendation method comprises the following steps: according to the historical behaviors of the target user, a historical favorite article set of the target user is determined, a first pre-recommended article set corresponding to the historical favorite article set is determined according to the historical favorite article set and a predetermined related article set of each article, a second pre-recommended article set corresponding to the first pre-recommended article set is determined according to the first pre-recommended article set and the related article set of each article, and an intersection article of the first pre-recommended article set and the second pre-recommended article set is determined to be a target recommended article recommended to the target user. On the one hand, compared with the current recommendation mode which only adopts first-order information, the recommendation accuracy of the embodiment is higher, and on the other hand, the recommendation mode can improve the diversity of recommendation on the premise of ensuring the recommendation accuracy.
Description
Technical Field
The embodiment of the invention relates to the technical field of big data processing, in particular to a recommendation method, a recommendation device, recommendation equipment and a storage medium.
Background
With the continuous development of big data processing technology, recommendation systems for recommending items to users are increasingly widely used. The items herein may be multimedia items such as movies, music, albums, etc.
Currently, recommendation systems often use collaborative filtering methods to make recommendations: and calculating the related articles of the articles, and recommending the articles most related to the articles which are favorite by the user through the articles which are favorite by the user.
However, the above recommendation method uses only information on the related items of the items that the user prefers, and the recommendation accuracy is low because the information considered is relatively single.
Disclosure of Invention
The invention provides a recommendation method, a recommendation device, recommendation equipment and a storage medium, which are used for solving the technical problem of low recommendation precision in the existing recommendation method.
In a first aspect, an embodiment of the present invention provides a recommendation method, including:
according to the historical behaviors of the target user, determining a historical favorite article set of the target user;
determining a first pre-recommended article set corresponding to the historical favorite article set according to the historical favorite article set and a predetermined related article set of each article;
determining a second pre-recommended article set corresponding to the first pre-recommended article set according to the first pre-recommended article set and the related article set of each article;
and determining an intersection item of the first pre-recommended item set and the second pre-recommended item set as a target recommended item recommended to the target user.
In a second aspect, an embodiment of the present invention provides a recommendation apparatus, including:
the first determining module is used for determining a historical favorite article set of the target user according to the historical behavior of the target user;
the second determining module is used for determining a first pre-recommended article set corresponding to the historical favorite article set according to the historical favorite article set and a predetermined related article set of each article;
a third determining module, configured to determine a second pre-recommended article set corresponding to the first pre-recommended article set according to the first pre-recommended article set and the related article set of each article;
and a fourth determining module, configured to determine an intersection item of the first pre-recommended item set and the second pre-recommended item set as a target recommended item recommended to the target user.
In a third aspect, an embodiment of the present invention further provides a computer apparatus, including:
one or more processors;
a memory for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the recommended method as provided in the first aspect.
In a fourth aspect, embodiments of the present invention also provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the recommendation method as provided in the first aspect.
The embodiment provides a recommendation method, a recommendation device, recommendation equipment and a storage medium, wherein the recommendation method comprises the following steps: according to the historical behaviors of the target user, a historical favorite article set of the target user is determined, a first pre-recommended article set corresponding to the historical favorite article set is determined according to the historical favorite article set and a predetermined related article set of each article, a second pre-recommended article set corresponding to the first pre-recommended article set is determined according to the first pre-recommended article set and the related article set of each article, and an intersection article of the first pre-recommended article set and the second pre-recommended article set is determined to be a target recommended article recommended to the target user. The method has the following technical effects: when a target user is recommended, a first pre-recommended article set corresponding to a historical favorite article set of the user and a second pre-recommended article set corresponding to the first pre-recommended article set are combined to determine the target recommended article, in other words, first-order information and second-order information of the user are combined to recommend, on one hand, compared with the mode of recommending only the first-order information, the recommendation accuracy of the embodiment is higher, on the other hand, the recommendation mode can improve the recommendation diversity on the premise of guaranteeing the recommendation accuracy.
Drawings
FIG. 1 is a flowchart of a recommendation method according to an embodiment of the present invention;
FIG. 2A is a flow chart of a process for determining a first pre-recommended item set corresponding to a historical favorite item set;
FIG. 2B is a flow chart of a process for determining a second set of pre-recommended items corresponding to the first set of pre-recommended items;
FIG. 3 is a schematic diagram of a recommendation device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Fig. 1 is a flow chart of a recommendation method according to an embodiment of the invention. The method and the device are suitable for determining a scene of a target recommended article recommended to the target user according to the historical behavior of the target user. The present embodiment may be performed by a recommendation device, which may be implemented in software and/or hardware, which may be integrated in a computer device. As shown in fig. 1, the recommendation method provided in this embodiment includes the following steps:
step 101: and determining a historical favorite article set of the target user according to the historical behavior of the target user.
Specifically, the computer device in this embodiment may be a server or a terminal device. The terminal device may be a handheld device, a vehicle-mounted device, a wearable device, various types of User Equipment (UE), a Mobile Station (MS), a terminal (terminal), and the like. The terminal device of the embodiment of the invention can be a smart phone, a tablet computer, a smart television and the like. The items in this embodiment may be multimedia items such as music, album, movie, picture, article, etc., or may be physical items that may be purchased in a shopping website. This embodiment is not limited thereto. The target user in this embodiment refers to a user to whom an item needs to be recommended.
Optionally, when the object is a multimedia object, the historical behavior of the user is a play behavior. When the item is an entity item in a shopping website that can be purchased, the user's historical behavior is either browsing behavior or purchasing behavior.
In one implementation, the object user may play, browse or purchase the object in a preset time period, and determine that the object user likes the object in history.
In another implementation manner, in a preset time period, the object whose playing frequency, browsing frequency or purchasing frequency is greater than a preset frequency threshold value can be determined as the historic favorite object of the target user.
In still another implementation manner, an item whose playing time or browsing time of the target user is greater than a preset duration threshold in a preset time period may be determined as a historic favorite item of the target user.
The set of the historical favorite items of the target user is the set of the historical favorite items of the target user.
Step 102: and determining a first pre-recommended article set corresponding to the historical favorite article set according to the historical favorite article set and the predetermined related article set of each article.
Specifically, in this embodiment, the set of related articles for each article may be predetermined. The related article set of the article in this embodiment refers to a set of article compositions related to the article. An item associated with the item refers to an item that has some commonality with the item. The commonality here may be the same or similar as the type and style of the article, etc.
In one implementation, the recommending means may determine the set of related items of the first item according to a correlation coefficient of each other item except the first item in the database and the first item. The number of the related articles in the related article set is a first preset number, and the first articles are any articles in the database.
For convenience of description, any item in the database is referred to as a first item in this embodiment. When calculating the related article set of the first article, the related coefficient of each other article except the first article in the database and the first article can be calculated first, and then the related article set of the first article is determined according to the related coefficient. The specific process can be as follows: calculating the Jacquard coefficient or cosine similarity of each other object and the first object, and taking the Jacquard coefficient or cosine similarity as a correlation coefficient; and arranging the correlation coefficients in order from large to small, and determining the set of the first preset number of articles with the corresponding correlation coefficients arranged in front as a correlation article set of the first articles. The first preset number here may be, for example, 30.
The above-described process is performed to obtain a set of related items for each first item in the database, i.e., a set of related items for each item. All items are included in the database in this embodiment.
More specifically, when the items are multimedia objects, the jaccard coefficient of the second item and the first item may be determined according to the number of users playing the first item and the number of users playing the second item in the other items. Wherein the second article is any one of other articles.
Illustratively, according to the formula
The Jaccard coefficient of the second article is determined with respect to the first article. Wherein w is ij The Jaccard coefficient of the second article and the first article is represented, N (j) represents the number of users playing the second article, N (i) N (j) represents the number of users simultaneously playing the first article and the second article, N (i) N (j) represents the number of users playing the first article or the second article, alpha is a first preset parameter, and beta is a second preset parameter.
Alternatively, α may take a value between 0.1 and 0.3, with α acting to inhibit hot objects. The value of beta can be between 5 and 100, and the beta acts as a cold door article inhibition.
Illustratively, the formula may also be based on
The Jaccard coefficient of the second article is determined with respect to the first article.
FIG. 2A is a flow chart of a process for determining a first pre-recommended item set corresponding to a historical favorite item set. As shown in fig. 2A, one possible implementation of step 102 includes the following steps:
step 1021: and determining the first related item set of each historical favorite item and the related coefficient of each first related item in the first related item set and the historical favorite item in the historical favorite item set according to the historical favorite item set and the related item set of each item.
As indicated previously, the set of related items for each item has been predetermined. After the historical favorite article sets of the target user are determined, a first related article set of each historical favorite article in the historical favorite article sets can be determined. The history of the target user likes how many items there are, where it can be determined how many first sets of related items are.
For each first set of related items, each first related item in the first set of related items has a correlation coefficient with the historical like items.
Step 1022: and adding the correlation coefficients corresponding to the same first correlation items in the first correlation item sets of all the historical favorite items, keeping the correlation coefficients corresponding to different first correlation items unchanged, and determining the updated correlation coefficient of each first correlation item and the historical favorite item.
Because the same first related item may exist in the plurality of first related item sets, in step 1022, the correlation coefficients corresponding to the same first related item in all the first related item sets are added, and the correlation coefficients corresponding to different first related items remain unchanged, so that updated correlation coefficients of each first related item and the historical favorite items may be determined.
Step 1023: and arranging updated correlation coefficients of all the first correlation articles and the historical favorite articles in order from large to small, arranging the corresponding updated correlation coefficients in a set of first correlation articles with a second preset number, and determining the set as a first pre-recommended article set corresponding to the historical favorite article set.
The above-described procedure is described below with a specific example. Suppose the historical favorite items set of the target user is { A, B, C }.
The predetermined set of related articles A is { H, I, J, K }, and the correlation coefficient of H and A is 0.1, the correlation coefficient of I and A is 0.2, the correlation coefficient of J and A is 0.8, and the correlation coefficient of K and A is 0.78. The predetermined set of related articles B is { M, N, J, K }, and the correlation coefficient of M and B is 0.3, the correlation coefficient of N and B is 0.4, the correlation coefficient of J and B is 0.8, and the correlation coefficient of K and B is 0.7. The predetermined set of related articles of C is { M, H, S, Y }, and the correlation coefficient of M and C is 0.3, the correlation coefficient of H and C is 0.1, the correlation coefficient of S and C is 0.5, and the correlation coefficient of Y and C is 0.6.
Based on the historical favorite article sets, the determined first related article sets of each historical favorite article are respectively: the first related item set of A is { H, I, J, K }, and the correlation coefficient of each first related item and A is respectively: {0.1,0.2,0.8,0.78}; the first related item set of B is { M, N, J, K }, and the correlation coefficient of each first related item and B is respectively: {0.3,0.4,0.8,0.7}; the first related article set of C is { M, H, S, Y }, and the correlation coefficient of each first related article and C is respectively: {0.3,0.1,0.5,0.6}.
It can be seen that the same first related item H, J, K, M exists in the three first related item sets. Adding the correlation coefficients corresponding to the same first correlation article, namely adding the correlation coefficient 0.1 of H and A and the correlation coefficient 0.1 of H and C to obtain 0.2; adding the correlation coefficient 0.8 of J and A and the correlation coefficient 0.8 of J and B to obtain 1.6; adding the correlation coefficient 0.78 of K and A with the correlation coefficient 0.7 of K and B to obtain 1.48; the correlation coefficient of M and B is added to the correlation coefficient of M and C of 0.3 to obtain 0.6. The correlation coefficients of the other first related items I, N, S, Y remain unchanged, and it can be determined that the updated correlation coefficients of each first related item and the historical favorite items are as follows: the correlation coefficient of H with the history favorite article is 0.2, the correlation coefficient of J with the history favorite article is 1.6, the correlation coefficient of K with the history favorite article is 1.48, the correlation coefficient of M with the history favorite article is 0.6, the correlation coefficient of I with the history favorite article is 0.2, the correlation coefficient of N with the history favorite article is 0.4, the correlation coefficient of S with the history favorite article is 0.5, and the correlation coefficient of Y with the history favorite article is 0.6.
And then, arranging updated correlation coefficients of all the first related articles and the historical favorite articles in a sequence from large to small, wherein the arranged sequence is {1.6,1.48,0.6,0.6,0.5,0.4,0.2,0.2}, and the corresponding first related articles are { J, K, M, Y, S, N, H, I }. And arranging the corresponding updated correlation coefficient in a second preset quantity, for example, the first 5 first sets of related articles { J, K, M, Y, S } are determined as the first pre-recommended article set corresponding to the historical favorite article set.
Step 103: and determining a second pre-recommended article set corresponding to the first pre-recommended article set according to the first pre-recommended article set and the related article set of each article.
Specifically, fig. 2B is a schematic flow chart of a process for determining a second pre-recommended article set corresponding to the first pre-recommended article set. As shown in fig. 2B, in step 103, one possible implementation includes the following steps:
step 1031: and determining a second related item set of each first pre-recommended item and a related coefficient of each second related item in the second related item set and the first pre-recommended item in the first pre-recommended item set according to the first pre-recommended item set and the related item set of each item.
After determining the first set of pre-recommended items, a second set of related items for each of the first set of pre-recommended items may be determined. How many first pre-recommended items are, and how many second sets of related items can be determined.
For each second set of related items, each second related item in the second set of related items has a coefficient of correlation with the first pre-recommended item.
Step 1032: and adding the correlation coefficients corresponding to the same second correlation articles in the second correlation article sets of all the first pre-recommended articles, keeping the correlation coefficients corresponding to different second correlation articles unchanged, and determining the updated correlation coefficient of each second article and the first pre-recommended article.
Since the same second related item may exist in the plurality of second related item sets, in step 1032, the correlation coefficients corresponding to the same second related item in all the second related item sets are added, and the correlation coefficients corresponding to different second related items remain unchanged, so that updated correlation coefficients of each second related item and the first pre-recommended item may be determined.
Step 1033: and arranging updated correlation coefficients of all the second correlation articles and the first pre-recommended articles in the sequence from large to small, and determining the corresponding second pre-recommended article set corresponding to the first pre-recommended article set as a set of second correlation articles with the third preset number of the corresponding updated correlation coefficients.
The following is a detailed description of the above procedure, following the example in step 102. Based on step 102, the first set of pre-recommended items is { J, K, M, Y, S }.
For convenience of description, assume that the second related item set of J is { O, P, L, K }, and the correlation coefficient of each second related item and J is: {0.1,0.2,0.3,0.4}; let K be { X, P, N, L }, and each second correlation item has a correlation coefficient with K of: {0.3,0.5,0.8,0.78}; let M's second related item set be { O, X, N, K }, and each second related item has a correlation coefficient with M of: {0.32,0.2,0.8,0.6}; assume that the second set of related items of Y is { H, I, S, T }, and that the correlation coefficients of each second related item and Y are respectively: {0.1,0.3,0.8,0.5}; let S' S second related item set be { O, P, J, K }, and each second related item has a correlation coefficient with S of: {0.4,0.2,0.3,0.5}.
Of the five second related item sets, there is the same second related item O, P, L, K, X, N. And adding the correlation coefficients corresponding to the same first correlation article. The correlation coefficients of the other second related items H, I, S, T, J remain unchanged, and the updated correlation coefficients of each second related item and the first pre-recommended item can be determined as follows: the updated correlation coefficients of O, P, L, K, X, N, H, I, S, T, J and the first pre-recommended item are respectively as follows: {0.82,0.9,1.08,1.5,0.5,1.6,0.1,0.3,0.8,0.5,0.3}.
And then, arranging updated correlation coefficients of all the second correlation articles and the first pre-recommended articles in the sequence from large to small, wherein the arranged sequence is {1.6,1.5,1.08,0.9,0.82,0.8,0.5,0.5,0.3,0.3,0.1}, and the corresponding second correlation articles are { N, K, L, P, O, S, T, X, I, J and H }. The corresponding updated correlation coefficients are ranked a third, pre-set number, e.g., the first 5, sets of second correlation items { N, K, L, P, O } are determined as the second set of pre-recommended items corresponding to the first set of pre-recommended items.
Step 104: and determining the intersection item of the first pre-recommended item set and the second pre-recommended item set as a target recommended item recommended to the target user.
Specifically, after the first pre-recommended item set and the second pre-recommended item set are determined, the intersection item in the two sets is determined as a target recommended item recommended to the target user.
With continued reference to steps 102 and 103, for example, the first set of pre-recommended items is { J, K, M, Y, S }, the second set of pre-recommended items is { N, K, L, P, O }, and the intersection item is K. K is determined as the target recommended item recommended to the target user.
Optionally, after determining the target recommended item, the target recommended item may be recommended to the target user.
In this embodiment, the historical favorite article set of the target user is zero-order information of the target user. And according to the zero-order information of the target user and the related item set, the obtained first pre-recommended item set is the first-order information of the target user. And according to the first pre-recommended article set and the related article set, the obtained second pre-recommended article set is the second-order information of the target user. And finally, taking the intersection of the first-order information and the second-order information of the target user, and recommending the articles in the intersection preferentially.
In order to avoid recommending items that the user has liked to the user, if the intersection item of the first pre-recommended item set and the second pre-recommended item set is a historical favorite item of the user, the historical favorite item is filtered out.
The recommendation method provided in this embodiment includes: according to the historical behaviors of the target user, a historical favorite article set of the target user is determined, a first pre-recommended article set corresponding to the historical favorite article set is determined according to the historical favorite article set and a predetermined related article set of each article, a second pre-recommended article set corresponding to the first pre-recommended article set is determined according to the first pre-recommended article set and the related article set of each article, and an intersection article of the first pre-recommended article set and the second pre-recommended article set is determined to be a target recommended article recommended to the target user. The method has the following technical effects: when a target user is recommended, a first pre-recommended article set corresponding to a historical favorite article set of the user and a second pre-recommended article set corresponding to the first pre-recommended article set are combined to determine the target recommended article, in other words, first-order information and second-order information of the user are combined to recommend, on one hand, compared with the mode of recommending only the first-order information, the recommendation accuracy of the embodiment is higher, on the other hand, the recommendation mode can improve the recommendation diversity on the premise of guaranteeing the recommendation accuracy.
Fig. 3 is a schematic structural diagram of a recommendation device according to an embodiment of the present invention. As shown in fig. 3, the recommendation device provided in this embodiment includes: the first determination module 31, the second determination module 32, the third determination module 33, and the fourth determination module 34.
The first determining module 31 is configured to determine a set of historic favorite objects of the target user according to the historic behavior of the target user.
Optionally, the apparatus further comprises: and a fifth determining module, configured to determine a set of related items of the first item according to the correlation coefficient of each other item except the first item in the database and the first item. The number of the related articles in the related article set is a first preset number, and the first articles are any articles in the database.
In one implementation, the fifth determining module is specifically configured to: calculating the Jacquard coefficient or cosine similarity of each other object and the first object, and taking the Jacquard coefficient or cosine similarity as a correlation coefficient; and arranging the correlation coefficients in order from large to small, and determining the set of the first preset number of articles with the corresponding correlation coefficients arranged in front as a correlation article set of the first articles.
More specifically, in calculating the jaccard coefficient of each other item and the first item, the fifth determining module specifically includes a determining submodule for determining the jaccard coefficient of the second item and the first item according to the number of users playing the first item and the number of users playing the second item in the other items. Wherein the second article is any one of other articles.
Optionally, the determining submodule is specifically configured to determine the value of the value according to the formula
The Jaccard coefficient of the second article is determined with respect to the first article. Wherein w is ij The Jaccard coefficient of the second article and the first article is represented, N (j) represents the number of users playing the second article, N (i) N (j) represents the number of users simultaneously playing the first article and the second article, N (i) N (j) represents the number of users playing the first article or the second article, alpha is a first preset parameter, and beta is a second preset parameter.
The second determining module 32 is configured to determine a first pre-recommended article set corresponding to the historical favorite article set according to the historical favorite article set and a predetermined related article set of each article.
In one implementation, the second determining module 32 is specifically configured to: according to the historical favorite article sets and the related article sets of each article, determining a first related article set of each historical favorite article in the historical favorite article sets and a related coefficient of each first related article in the first related article set and the historical favorite article; adding the correlation coefficients corresponding to the same first correlation articles in the first correlation article sets of all the historical favorite articles, keeping the correlation coefficients corresponding to different first correlation articles unchanged, and determining updated correlation coefficients of each first correlation article and the historical favorite articles; and arranging updated correlation coefficients of all the first correlation articles and the historical favorite articles in order from large to small, arranging the corresponding updated correlation coefficients in a set of first correlation articles with a second preset number, and determining the set as a first pre-recommended article set corresponding to the historical favorite article set.
The third determining module 33 is configured to determine a second pre-recommended article set corresponding to the first pre-recommended article set according to the first pre-recommended article set and the related article set of each article.
In one implementation, the third determining module 33 is specifically configured to: determining a second related item set of each first pre-recommended item and a related coefficient of each second related item in the second related item set and the first pre-recommended item in the first pre-recommended item set according to the first pre-recommended item set and the related item set of each item; adding the correlation coefficients corresponding to the same second correlation items in the second correlation item sets of all the first pre-recommended items, keeping the correlation coefficients corresponding to different second correlation items unchanged, and determining updated correlation coefficients of each second item and the first pre-recommended item; and arranging updated correlation coefficients of all the second correlation articles and the first pre-recommended articles in the sequence from large to small, and determining the corresponding second pre-recommended article set corresponding to the first pre-recommended article set as a set of second correlation articles with the third preset number of the corresponding updated correlation coefficients.
A fourth determining module 34 is configured to determine an intersection item of the first set of pre-recommended items and the second set of pre-recommended items as a target recommended item recommended to the target user.
The recommending device provided by the embodiment of the invention can execute the recommending method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.
Fig. 4 is a schematic structural diagram of a computer device according to an embodiment of the present invention. As shown in fig. 4, the computer device includes a processor 40 and a memory 41. The number of processors 40 in the computer device may be one or more, one processor 40 being taken as an example in fig. 4; the processor 40 and the memory 41 of the computer device may be connected by a bus or otherwise, for example in fig. 4.
The memory 41 is a computer-readable storage medium, and may be used to store a software program, a computer-executable program, and modules, such as program instructions and modules corresponding to the recommendation method in the embodiment of the present invention (for example, the first determining module 31, the second determining module 32, the third determining module 33, and the fourth determining module 34 in the recommendation device). The processor 40 executes various functional applications and recommendations of the computer device by running software programs, instructions and modules stored in the memory 41, i.e. implements the recommendation method described above.
The memory 41 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for functions; the storage data area may store data created according to the use of the computer device, etc. In addition, memory 41 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 41 may further comprise memory located remotely from processor 40, which may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The present invention also provides a storage medium containing computer executable instructions which, when executed by a computer processor, are for performing a recommendation method comprising:
according to the historical behaviors of the target user, determining a historical favorite article set of the target user;
determining a first pre-recommended article set corresponding to the historical favorite article set according to the historical favorite article set and a predetermined related article set of each article;
determining a second pre-recommended article set corresponding to the first pre-recommended article set according to the first pre-recommended article set and the related article set of each article;
and determining an intersection item of the first pre-recommended item set and the second pre-recommended item set as a target recommended item recommended to the target user.
Of course, the storage medium containing the computer executable instructions provided in the embodiments of the present invention is not limited to the method operations described above, and may also perform the related operations in the recommended method provided in any embodiment of the present invention.
From the above description of embodiments, it will be clear to a person skilled in the art that the present invention may be implemented by means of software and necessary general purpose hardware, but of course also by means of hardware, although in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, etc., and include several instructions for causing a computer device (which may be a personal computer, a computer device, or a network device, etc.) to execute the recommended method according to the embodiments of the present invention.
It should be noted that, in the embodiment of the recommendation device, each unit and module included are only divided according to the functional logic, but not limited to the above division, so long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present invention.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (10)
1. A recommendation method, comprising:
according to the historical behaviors of the target user, determining a historical favorite article set of the target user;
determining a first pre-recommended article set corresponding to the historical favorite article set according to the historical favorite article set and a predetermined related article set of each article;
determining a second pre-recommended article set corresponding to the first pre-recommended article set according to the first pre-recommended article set and the related article set of each article;
and determining an intersection item of the first pre-recommended item set and the second pre-recommended item set as a target recommended item recommended to the target user.
2. The method of claim 1, wherein before determining the first pre-recommended item set corresponding to the historical favorite item set according to the historical favorite item set and the predetermined related item set for each item, the method further comprises:
determining a related article set of the first article according to the related coefficient of each other article except the first article in the database and the first article; the number of the related articles in the related article set is a first preset number, and the first articles are any articles in the database.
3. The method of claim 2, wherein the determining the set of related items for the first item based on the correlation coefficients for each other item in the database other than the first item, comprises:
calculating the Jacquard coefficient or cosine similarity of each other object and the first object, and taking the Jacquard coefficient or cosine similarity as the correlation coefficient;
and arranging the correlation coefficients in order from large to small, and determining the set of the first preset number of articles with the corresponding correlation coefficients arranged in front as the set of the correlation articles of the first article.
4. The method of claim 2, wherein the determining the first pre-recommended item set corresponding to the historical favorite item set according to the historical favorite item set and the predetermined related item set for each item comprises:
according to the historical favorite article sets and the related article sets of each article, determining a first related article set of each historical favorite article in the historical favorite article sets and a related coefficient of each first related article in the first related article set and the historical favorite article;
adding the correlation coefficients corresponding to the same first correlation articles in the first correlation article sets of all the historical favorite articles, keeping the correlation coefficients corresponding to different first correlation articles unchanged, and determining updated correlation coefficients of each first correlation article and the historical favorite articles;
and arranging updated correlation coefficients of all the first correlation objects and the historical favorite objects in a sequence from large to small, arranging the corresponding updated correlation coefficients in a set of first correlation objects with a second preset number, and determining the set as a first pre-recommended object set corresponding to the historical favorite object set.
5. The method of claim 2, wherein the determining a second set of pre-recommended items corresponding to the first set of pre-recommended items from the first set of pre-recommended items and the related set of items for each item comprises:
determining a second related item set of each first pre-recommended item and a related coefficient of each second related item in the second related item set and the first pre-recommended item in the first pre-recommended item set according to the first pre-recommended item set and the related item set of each item;
adding the correlation coefficients corresponding to the same second correlation articles in the second correlation article sets of all the first pre-recommended articles, keeping the correlation coefficients corresponding to different second correlation articles unchanged, and determining updated correlation coefficients of each second article and the first pre-recommended articles;
and arranging updated correlation coefficients of all the second correlation articles and the first pre-recommended articles in a sequence from large to small, arranging the corresponding updated correlation coefficients in a set of second correlation articles with a third preset number, and determining the set of second correlation articles as a second pre-recommended article set corresponding to the first pre-recommended article set.
6. A method according to claim 3, wherein the item is a multimedia item;
said calculating a jaccard coefficient for each of said other items and said first item, comprising:
determining Jaccard coefficients of a second object and a first object according to the number of users playing the first object and the number of users playing the second object in other objects; wherein the second article is any one of the other articles.
7. The method of claim 6, wherein determining the jaccard coefficient for the second item and the first item based on the number of users playing the first item and the number of users playing the second item in the other items, comprises:
according to the formula
Determining a jaccard coefficient for the second article and the first article; wherein w is ij The Jaccard coefficient of the second article and the first article is represented, N (j) represents the number of users playing the second article, N (i) N (j) represents the number of users simultaneously playing the first article and the second article, N (i) N (j) represents the number of users playing the first article or the second article, alpha is a first preset parameter, and beta is a second preset parameter.
8. A recommendation device, comprising:
the first determining module is used for determining a historical favorite article set of the target user according to the historical behavior of the target user;
the second determining module is used for determining a first pre-recommended article set corresponding to the historical favorite article set according to the historical favorite article set and a predetermined related article set of each article;
a third determining module, configured to determine a second pre-recommended article set corresponding to the first pre-recommended article set according to the first pre-recommended article set and the related article set of each article;
and a fourth determining module, configured to determine an intersection item of the first pre-recommended item set and the second pre-recommended item set as a target recommended item recommended to the target user.
9. A computer device, the computer device comprising:
one or more processors;
a memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the recommendation method of any one of claims 1-7.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the recommendation method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010311448.0A CN111506816B (en) | 2020-04-20 | 2020-04-20 | Recommendation method, recommendation device, recommendation equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010311448.0A CN111506816B (en) | 2020-04-20 | 2020-04-20 | Recommendation method, recommendation device, recommendation equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111506816A CN111506816A (en) | 2020-08-07 |
| CN111506816B true CN111506816B (en) | 2023-05-09 |
Family
ID=71876190
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010311448.0A Active CN111506816B (en) | 2020-04-20 | 2020-04-20 | Recommendation method, recommendation device, recommendation equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111506816B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112634009B (en) * | 2020-12-14 | 2024-05-14 | 中国建设银行股份有限公司 | Product pushing method and device, storage medium and electronic equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107609201A (en) * | 2017-10-25 | 2018-01-19 | 广东工业大学 | A kind of recommended models generation method and relevant apparatus based on commending system |
| CN109495770A (en) * | 2018-11-23 | 2019-03-19 | 武汉斗鱼网络科技有限公司 | A kind of direct broadcasting room recommended method, device, equipment and medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103970785A (en) * | 2013-01-31 | 2014-08-06 | 国际商业机器公司 | Online recommendation method and system |
-
2020
- 2020-04-20 CN CN202010311448.0A patent/CN111506816B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107609201A (en) * | 2017-10-25 | 2018-01-19 | 广东工业大学 | A kind of recommended models generation method and relevant apparatus based on commending system |
| CN109495770A (en) * | 2018-11-23 | 2019-03-19 | 武汉斗鱼网络科技有限公司 | A kind of direct broadcasting room recommended method, device, equipment and medium |
Non-Patent Citations (1)
| Title |
|---|
| 曹夏琳 ; 周健勇 ; .基于物品的协同过滤算法对"宁波地铁go"用户个性化推荐系统研究.物流科技.2019,(06),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111506816A (en) | 2020-08-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104809154B (en) | The method and device recommended for information | |
| CN107609198B (en) | Recommendation method and device and computer readable storage medium | |
| US7685200B2 (en) | Ranking and suggesting candidate objects | |
| Shaikh et al. | Recommendation system in e-commerce websites: a graph based approached | |
| CN102184199A (en) | Network information recommending method and system | |
| US9699490B1 (en) | Adaptive filtering to adjust automated selection of content using weightings based on contextual parameters of a browsing session | |
| US9727906B1 (en) | Generating item clusters based on aggregated search history data | |
| CN107704560B (en) | Information recommendation method, device and equipment | |
| US20150193863A1 (en) | Method and system for searching and displaying product images | |
| WO2012092196A1 (en) | Recommendation of search keywords based on indication of user intention | |
| CN104053023B (en) | A kind of method and device of determining video similarity | |
| CN107341245A (en) | Data processing method, device and server | |
| CN110110206B (en) | Method, device, computing equipment and storage medium for mining and recommending relationships among articles | |
| CN111104606A (en) | Weight-based conditional wandering chart recommendation method | |
| CN110825977A (en) | A data recommendation method and related equipment | |
| CN106850750A (en) | A method and device for pushing information in real time | |
| CN102968418A (en) | Website information search method and system | |
| CN111010592A (en) | Video recommendation method and device, electronic equipment and storage medium | |
| Pyo et al. | Automatic and personalized recommendation of TV program contents using sequential pattern mining for smart TV user interaction | |
| AU2021385976A1 (en) | Product recommendation method and apparatus, computer storage medium, and system | |
| CN109587527B (en) | Personalized video recommendation method and device | |
| CN110309410B (en) | Information recommendation method, platform and computer-readable storage medium | |
| CN111506816B (en) | Recommendation method, recommendation device, recommendation equipment and storage medium | |
| CN107730271B (en) | Similar user determination method and device based on virtual interaction object and electronic equipment | |
| WO2023168856A1 (en) | Associated scene recommendation method and device, storage medium, and electronic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |