CN111538901A - Article recommendation method and device, server and storage medium - Google Patents
Article recommendation method and device, server and storage medium Download PDFInfo
- Publication number
- CN111538901A CN111538901A CN202010294127.4A CN202010294127A CN111538901A CN 111538901 A CN111538901 A CN 111538901A CN 202010294127 A CN202010294127 A CN 202010294127A CN 111538901 A CN111538901 A CN 111538901A
- Authority
- CN
- China
- Prior art keywords
- preset
- target
- article
- item
- articles
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses an article recommendation method, an article recommendation device, a server and a storage medium, wherein the method comprises the following steps: screening preset articles in a preset article set according to a preset screening rule to select a target article; if the recommended times of the target object are smaller than a first exposure threshold value, recommending the target object to a preset user searched according to the preset attribute of the target object; if the recommended times of the target object are larger than the first exposure threshold value, sorting and recalling in a preset group according to the click rate of the target object; and if the recommended times of the target article is greater than a second exposure threshold value, sorting and recalling the target article and other preset articles in the preset article set according to a preset strategy. According to the technical scheme of the embodiment, the iteration cycle of the new article is shortened, the effect quality of the new article is rapidly found out in a trial mode, and the requirement of the information industry recommendation system for high timeliness of the article can be met.
Description
Technical Field
The embodiment of the invention relates to an artificial intelligence technology, in particular to an article recommendation method, an article recommendation device, a server and a storage medium.
Background
With the rapid development of the transmission technology and the dramatic increase of the data volume, users put higher requirements on timeliness and individuation on the information industry.
The iteration mode of the new article in the prior art mainly comprises the following two modes: one is to establish some relationship with the old article through the content of the article itself, and then to expose the article according to the relationship. The further exposure of the new item is then very dependent on the degree of exposure and the click of the old item. If the old article is clicked less by the user, the ranking is relatively backward, the exposure period of the new article is further prolonged, and the exposure times are also influenced by the recommendation condition of the related old article. And secondly, predicting the scoring of the user to the articles through the model so as to perform sorting recall. However, generally, the amount of user behavior data is large, the calculation period is long, and the product iteration period is prolonged due to certain hysteresis. The iteration cycle for a new article is relatively long.
Meanwhile, the quality of the old article can be obtained according to the feedback of the user because the old article is fully exposed; the new article cannot be exposed in a short time, and the quality of the new article cannot be known. In the prior art, according to a uniform sorting recall method, new articles are generally in a disadvantage, so that the probability that the new articles with possibly high quality are recommended to a user is greatly reduced, and the new articles cannot be exposed.
Disclosure of Invention
The embodiment of the invention provides an article recommendation method, an article recommendation device, a server and a storage medium, which are used for shortening an iteration cycle of a new article and rapidly exploring the effect quality of the new article.
In a first aspect, an embodiment of the present invention provides an item recommendation method, including:
screening preset articles in a preset article set according to a preset screening rule to select a target article;
if the recommended times of the target object are smaller than a first exposure threshold value, recommending the target object to a preset user searched according to the preset attribute of the target object;
if the recommended times of the target object are larger than the first exposure threshold value, sorting and recalling in a preset group according to the click rate of the target object;
and if the recommended times of the target article is greater than a second exposure threshold value, sorting and recalling the target article and other preset articles in the preset article set according to a preset strategy.
In a second aspect, an embodiment of the present invention further provides an article recommendation apparatus, including:
the target article screening module is used for screening preset articles in the preset article set according to preset screening rules to select the target articles;
the target article recommending module is used for recommending the target article to a preset user searched according to the preset attribute of the target article if the recommending frequency of the target article is smaller than a first exposure threshold value;
the first sequencing recall module is used for sequencing and recalling according to the click rate of the target item in the category to which the target item belongs if the recommended times of the target item is greater than the first exposure threshold;
and the second sorting recall module is used for sorting and recalling the target object and other preset objects in the preset object set according to a preset strategy if the recommended times of the target object is greater than a second exposure threshold.
In a third aspect, an embodiment of the present invention further provides a server, where the server includes:
one or more processors;
a memory for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method of item recommendation as provided in any embodiment of the invention.
In a fourth aspect, embodiments of the present invention also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are used to perform an item recommendation method as provided in any of the embodiments of the present invention.
According to the embodiment of the invention, the target articles are selected for recommendation, and the corresponding sorting recall strategy is selected according to the exposure, so that the problem that the quality cannot be known due to the fact that the iteration cycle of the new articles is relatively long and the new articles cannot be exposed in a short time is solved, the iteration cycle of the new articles is shortened, and the quality of the new articles is rapidly found out.
Drawings
FIG. 1 is a flow chart of a method for recommending items according to a first embodiment of the present invention;
FIG. 2 is a flowchart of an item recommendation method according to a second embodiment of the present invention;
FIG. 3 is a flowchart of an item recommendation method according to a second embodiment of the present invention;
fig. 4 is a schematic structural diagram of an article recommendation device in a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of a server in the fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of an article recommendation method according to an embodiment of the present invention, where this embodiment is applicable to a case of cold start recommendation of a new article, and the method may be executed by an article recommendation apparatus, where the apparatus may be implemented by hardware and/or software, and the method specifically includes the following steps:
110, screening preset articles in a preset article set according to a preset screening rule to select a target article;
the method includes the steps of obtaining a stored preset article set from a database, wherein preset articles are stored in the preset article set, the preset articles need to be recommended to a user through a recommendation engine, and obtaining relevant information of the preset articles from the database. The target of screening is from predetermineeing article and concentrating and finding new article, and optional, predetermineeing article in article set and select target article according to predetermineeing the screening rule, include: determining a preset article with the time difference of appearance smaller than a first threshold value as a preselected target article; removing the preselected target articles with the apparent time difference larger than a second threshold value and the recommended times exceeding a preset exposure threshold value; wherein the first threshold is greater than the second threshold; the remaining preselected target items are determined to be target items. The first threshold is a limit time for distinguishing the new article from the old article, and for a preset article with a time difference of more than or equal to the first threshold, the article is considered as the old article, and exemplarily, the first threshold is generally set to 1 day and is set by the user according to timeliness requirements. In addition, for the preselected target object, the time difference of appearance is greater than the second threshold, the exposure degree needs to be judged, if the preselected target object obtains more exposure, namely the recommended times exceeds the preset exposure threshold, the preselected target object needs to be removed, and the preselected target object is not selected as the target object for recommendation. For example, the second threshold may be set to 7200 seconds, and the maximum run time of other recommended modules may be generally selected. The preset exposure threshold is mainly analyzed, and the average exposure value of other recommended logics can be generally taken. And screening the target articles by the preset screening rule, and uniformly sorting and recalling the rest preset articles by adopting a preset strategy the same as that of the old articles.
the first exposure threshold is a tentative exposure threshold, the target object reaching the tentative exposure threshold can be considered to have been recommended to enough multiple users, and the target object whose recommended number is less than the first exposure threshold needs to be recommended forcibly to increase the exposure, so that the quality effect of the new object can be determined according to the feedback of the user. The preset attribute can be information such as categories and/or labels of the articles, information such as categories and/or labels of the articles on which the user has clicked recently is obtained, the information is matched with the information such as categories and/or labels of new articles to be exposed, and the user who clicks the matched articles is the preset user. And forcing a certain number of preset users to recommend the target articles.
and for the target articles of which the recommended times are greater than the first exposure threshold, collecting click behaviors of the target articles, calculating the click rate of the target articles, grouping the target articles according to the categories and/or labels of the target articles because the target articles belong to new articles, and sorting and recalling the target articles according to the click rate of the target articles in the same preset group from large to small.
And 140, if the recommended times of the target item are greater than the second exposure threshold, sorting and recalling the target item and other preset items in the preset item set according to a preset strategy.
And considering that the target item with the recommended times greater than the second exposure threshold value enters the range of the old item, and performing sorting recall on the target item by adopting the same preset strategy as the old item. Illustratively, old articles are sorted and recalled by adopting strategies such as collaborative filtering or Click Through Rate (CTR) sorting, so that the distinguishing processing and final unification of the new article and the old article in the sorting mode are realized.
According to the technical scheme, the target articles are selected for recommendation, the corresponding sorting recall strategy is selected according to the exposure, the problem that the quality cannot be known due to the fact that the iteration cycle of the new articles is relatively long and the new articles cannot be exposed in a short time is solved, the iteration cycle of the new articles is shortened, and the quality of the new articles is rapidly found out.
Example two
Fig. 2 is a flowchart of an article recommendation method provided in the second embodiment of the present invention, and the technical solution of the present embodiment is further detailed on the basis of the above technical solution, where the method specifically includes:
Wherein all _ pv represents the sum of exposure of the preset item per day, ucb _ ratio represents the proportion of tentative exposure, item _ ucb represents the number of new items per day, and item _ ucb _ ratio represents the proportion of new items exposed. The percentage of tentative exposures is typically between 5% and 10%, with 5% being chosen in this example.
and step 260, recommending the target items to a preset number of preset users.
The preset attributes of the articles can be selected from categories, the categories of the articles clicked by the user recently are matched with the categories of the new articles, and are recommended to the preset users who are successfully matched, and the categories are recommended to the preset users in the preset number. According to the user category preference, the new articles of the same category are recommended, so that the category effect of the new articles can be more easily and quickly found out.
Optionally, before recommending the target item to a preset number of preset users, the method further includes:
determining a formula according to a predetermined number
A preset number is calculated, wherein ucb _ max _ pv represents the first exposure threshold and user _ cnt represents the preset number of users.
optionally, click behaviors for the target object are acquired, and a formula is determined according to the click rate
Calculating click rate of target item, wherein ctriIndicating the click rate, pv, of a predetermined item iiIndicating the exposure, ck, of a predetermined item iiRepresenting the click rate of a preset article i;
and in the preset grouping, the recall is performed according to the click rate of the target item from large to small.
And step 280, if the recommended times of the target article is greater than the second exposure threshold, sorting and recalling the target article and other preset articles in the preset article set according to a preset strategy.
Fig. 3 is a flowchart of an article recommendation method according to an embodiment of the present invention, where the flowchart shows a flowchart of a more suitable implementation manner of a method for solving a problem of cold start of an article of a recommendation system in an information industry, and the implementation manner includes the following steps:
1. given a set of all items, the filtering condition for the new item in this example is mainly spread out in the time dimension, so the time of appearance (item _ product _ time) of the item must be obtained.
2. Screening out the articles which meet the cold start of the new articles according to the screening conditions:
1) if the time difference (time _ diff, which is the current time-the time when the article appears) of the article exceeds a certain threshold (max _ time _ diff, which is generally set to 1 day and is set by the user according to the timeliness requirement), the article does not belong to a new article, a conventional sorting recall method is selected, and the step 9 is skipped;
2) if the time difference (time _ diff) of the item exceeds a threshold (choice _ time _ diff is 7200, the longest running time of other recommending modules is generally selected), and the recommending number exceeds the exposure threshold (pv _ max), although the item belongs to a new item, the item obtains enough exposure, and can be statistically recalled in a sorting mode with an old item, and the step 9 is skipped;
3) and (4) the remained new articles meet the condition of cold start of the new articles, and the step 3 is carried out.
3. The category and the label of the new article are obtained (information on at least one dimension is selected as much as possible, the dimension with the higher preparation rate is selected), and the category is adopted in the case, because the recommended user group can be quickly positioned through the category, and the category information is more accurate in the case.
4. If the recommended quantity of items reaches the tentative exposure threshold (ucb _ max _ pv, where the tentative exposure percentage is typically between 5% and 10%, in this case 5% is selected), proceed to step 7, otherwise proceed to step 5.
5. And matching the category of the item which is clicked by the user recently with the category of the new item, recommending the item to the user, and recommending ucb _ num users in total. The system recommends new articles of the same category according to the preference of the user category, so that the category effect of the new articles can be more easily and quickly explored.
6. If the recommended number of new items reaches the tentative exposure threshold (ucb _ max _ pv), then step 7 is skipped, otherwise step 5 is skipped.
7. And collecting click behaviors of the new items, calculating click rate (ctr) of the new items, and performing sorting recall according to the click rate (from large to small) under the same category.
8. If the recommended number of new items reaches the exposure threshold (pv _ max), go to step 9, otherwise go to step 7.
9. And the old articles are sorted and recalled in a unified calculation mode.
Because the new article is exposed enough and becomes an old article, the related characteristics of the cold-start article are not provided, and the product cycle from the cold-start article to the old article is completed.
EXAMPLE III
Fig. 4 is a schematic structural diagram of an article recommendation device according to a fourth embodiment of the present invention, and as shown in fig. 4, the article recommendation device includes:
the target article screening module 410 is configured to screen preset articles in a preset article set according to preset screening rules to select target articles;
the target item recommending module 420 is configured to recommend a target item to a preset user searched according to a preset attribute of the target item if the recommended number of times of the target item is smaller than a first exposure threshold;
the first sorting recall module 430 is configured to, if the recommended times of the target items are greater than a first exposure threshold, perform sorting recall according to the click rate of the target items in the category to which the target items belong;
and a second sorting recall module 440, configured to, if the recommended number of times of the target item is greater than the second exposure threshold, sort and recall the target item and other preset items in the preset item set according to a preset policy.
According to the technical scheme, the target articles are selected for recommendation, the corresponding sorting recall strategy is selected according to the exposure, the problem that the quality cannot be known due to the fact that the iteration cycle of the new articles is relatively long and the new articles cannot be exposed in a short time is solved, the iteration cycle of the new articles is shortened, and the quality of the new articles is rapidly found out.
Optionally, the target item screening module 410 includes:
a preselected target article determining unit for determining a preset article having a time difference of appearance smaller than a first threshold value as a preselected target article;
the removing unit is used for removing the preselected target articles of which the surface time difference is greater than a second threshold value and the recommended times exceed a preset exposure threshold value; wherein the first threshold is greater than the second threshold;
and the target item determining unit is used for determining the remaining preselected target items as the target items.
Optionally, the target item recommendation module 420 is specifically configured to:
if the recommended times of the target object are smaller than a first exposure threshold value, acquiring the object of the user click behavior within the preset time;
matching the object article with the target article in the aspect of preset attributes;
determining the user corresponding to the matched object article as a preset user;
and recommending the target articles to a preset number of preset users.
Optionally, the article recommending apparatus further includes:
a preset quantity determining module for determining a formula according to a preset quantity before recommending target articles to a preset quantity of preset users
A preset number is calculated, wherein ucb _ max _ pv represents the first exposure threshold and user _ cnt represents the preset number of users.
Optionally, the article recommending apparatus further includes:
a first exposure threshold determination module, configured to determine a formula according to a first exposure threshold before recommending the target item to a preset user searched according to the preset attribute of the target item if the recommended number of times of the target item is smaller than the first exposure threshold
Calculating a first exposure threshold, wherein all _ pv represents the sum of exposure of the preset item per day, ucb _ ratio represents the proportion of tentative exposures, item _ ucb represents the number of new items per day, and item _ ucb _ ratio represents the proportion of new items exposed.
Optionally, the first ordering recall module 430 is specifically configured to:
obtaining click behaviors aiming at target objects, and determining a formula according to click rate
Calculating click rate of target item, wherein ctriIndicating the click rate, pv, of a predetermined item iiIndicating the exposure, ck, of a predetermined item iiRepresenting the click rate of a preset article i;
and in the preset grouping, the recall is performed according to the click rate of the target item from large to small.
The article recommending device provided by the embodiment of the invention can execute the article recommending method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.
Example four
Fig. 5 is a schematic structural diagram of a server according to a fourth embodiment of the present invention, as shown in fig. 5, the server includes a processor 510 and a memory 520; the number of the processors 510 in the server may be one or more, and one processor 510 is taken as an example in fig. 5; the processor 510 and the memory 520 in the server may be connected by a bus or other means, and fig. 5 illustrates the connection by a bus as an example.
The memory 520 is a computer-readable storage medium and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the item recommendation method in the embodiment of the present invention (for example, the target item screening module 410, the target item recommendation module 420, the first sorting recall module 430, and the second sorting recall module 440 in the item recommendation apparatus). The processor 510 executes various functional applications of the server and data processing by executing software programs, instructions, and modules stored in the memory 520, thereby implementing the item recommendation method described above.
The memory 520 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 520 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 examples, memory 520 may further include memory located remotely from processor 510, which may be connected to a server over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
EXAMPLE five
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a method for recommending items, including:
screening preset articles in a preset article set according to a preset screening rule to select a target article;
if the recommended times of the target object are smaller than a first exposure threshold value, recommending the target object to a preset user searched according to the preset attribute of the target object;
if the recommended times of the target object are larger than the first exposure threshold value, sorting and recalling in a preset group according to the click rate of the target object;
and when the recommended times of the target item is greater than a second exposure threshold value, sorting and recalling the target item and other preset items in the preset item set according to a preset strategy.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the method operations described above, and may also perform related operations in the item recommendation method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied 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 (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the article recommendation device, the included units and modules are merely divided according to the functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. 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, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. An item recommendation method, comprising:
screening preset articles in a preset article set according to a preset screening rule to select a target article;
if the recommended times of the target object are smaller than a first exposure threshold value, recommending the target object to a preset user searched according to the preset attribute of the target object;
if the recommended times of the target object are larger than the first exposure threshold value, sorting and recalling in a preset group according to the click rate of the target object;
and if the recommended times of the target article is greater than a second exposure threshold value, sorting and recalling the target article and other preset articles in the preset article set according to a preset strategy.
2. The method according to claim 1, wherein the screening the preset items in the preset item set according to the preset screening rule to select the target item comprises:
determining the preset article with the time difference of appearance smaller than a first threshold value as a preselected target article;
rejecting the preselected target articles with the time difference of appearance larger than a second threshold and the recommended times exceeding a preset exposure threshold; wherein the first threshold is greater than the second threshold;
determining the remaining preselected target item as the target item.
3. The method according to claim 1, wherein if the recommended number of times of the target item is smaller than a first exposure threshold, recommending the target item to a preset user searched according to a preset attribute of the target item, comprising:
if the recommended times of the target object are smaller than the first exposure threshold, acquiring a target object of a user click behavior within a preset time;
matching the object article with the target article in the aspect of the preset attribute;
determining the user corresponding to the matched object article as the preset user;
recommending the target object to a preset number of the preset users.
4. The method of claim 3, further comprising, prior to said recommending said target item to a preset number of said preset users:
determining a formula according to a predetermined number
And calculating the preset number, wherein ucb _ max _ pv represents the first exposure threshold value, and user _ cnt represents the preset number of users.
5. The method according to claim 4, wherein before recommending the target item to a preset user searched according to a preset attribute of the target item if the recommended number of times of the target item is smaller than a first exposure threshold, further comprising:
determining a formula based on a first exposure threshold
Calculating the first exposure threshold, wherein all _ pv represents the sum of exposure of the preset item per day, ucb _ ratio represents the proportion of tentative exposure, item _ ucb represents the number of new items per day, and item _ ucb _ ratio represents the proportion of new items exposed.
6. The method of claim 1, wherein the performing a recall of the target item in a predetermined grouping according to the click through rate of the target item if the recommended number of times of the target item is greater than the first exposure threshold comprises:
obtaining click behaviors aiming at the target object, and determining a formula according to click rate
Calculating click rate of the target item, wherein ctriIndicating the click rate, pv, of a predetermined item iiIndicating the exposure, ck, of a predetermined item iiRepresenting the click rate of a preset article i;
and in the preset grouping, sorting and recalling according to the click rate of the target object from large to small.
7. An item recommendation device, comprising:
the target article screening module is used for screening preset articles in the preset article set according to preset screening rules to select the target articles;
the target article recommending module is used for recommending the target article to a preset user searched according to the preset attribute of the target article if the recommending frequency of the target article is smaller than a first exposure threshold value;
the first sequencing recall module is used for sequencing and recalling according to the click rate of the target item in the category to which the target item belongs if the recommended times of the target item is greater than the first exposure threshold;
and the second sorting recall module is used for sorting and recalling the target object and other preset objects in the preset object set according to a preset strategy if the recommended times of the target object is greater than a second exposure threshold.
8. The apparatus of claim 7, wherein the target item screening module comprises:
a preselected target article determining unit, configured to determine the preset article with the time difference of appearance smaller than a first threshold as a preselected target article;
the removing unit is used for removing the preselected target articles of which the time difference of appearance is greater than a second threshold value and the recommended times exceed a preset exposure threshold value; wherein the first threshold is greater than the second threshold;
a target item determination unit for determining the remaining preselected target items as the target items.
9. A server, characterized in that the server comprises:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the item recommendation method of any one of claims 1-6.
10. A storage medium containing computer-executable instructions for performing the item recommendation method of any one of claims 1-6 when executed by a computer processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010294127.4A CN111538901B (en) | 2020-04-15 | 2020-04-15 | Article recommendation method and device, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010294127.4A CN111538901B (en) | 2020-04-15 | 2020-04-15 | Article recommendation method and device, server and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111538901A true CN111538901A (en) | 2020-08-14 |
| CN111538901B CN111538901B (en) | 2023-06-06 |
Family
ID=71974921
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010294127.4A Active CN111538901B (en) | 2020-04-15 | 2020-04-15 | Article recommendation method and device, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111538901B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112818237A (en) * | 2021-02-05 | 2021-05-18 | 上海明略人工智能(集团)有限公司 | Content pushing method, device, equipment and storage medium |
| CN113378068A (en) * | 2021-07-14 | 2021-09-10 | 聚好看科技股份有限公司 | Content recommendation method and server |
| CN113688295A (en) * | 2021-10-26 | 2021-11-23 | 北京达佳互联信息技术有限公司 | Data determination method and device, electronic equipment and storage medium |
| CN113744021A (en) * | 2021-02-08 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Recommendation method, recommendation device, computer storage medium and recommendation system |
| CN113781086A (en) * | 2021-01-21 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Article recommendation method, device, medium and electronic equipment |
| CN113836404A (en) * | 2021-09-09 | 2021-12-24 | 武汉卓尔数字传媒科技有限公司 | Object recommendation method and device, electronic equipment and computer-readable storage medium |
| CN114662008A (en) * | 2022-05-26 | 2022-06-24 | 上海二三四五网络科技有限公司 | Click position factor improvement-based CTR hot content calculation method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110153598A1 (en) * | 2009-12-22 | 2011-06-23 | Kamimaeda Naoki | Information Processing Apparatus and Method |
| CN109190043A (en) * | 2018-09-07 | 2019-01-11 | 北京三快在线科技有限公司 | Recommended method and device, storage medium, electronic equipment and recommender system |
| CN110532468A (en) * | 2019-08-26 | 2019-12-03 | 北京齐尔布莱特科技有限公司 | A kind of recommended method of site resource, device and calculate equipment |
-
2020
- 2020-04-15 CN CN202010294127.4A patent/CN111538901B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110153598A1 (en) * | 2009-12-22 | 2011-06-23 | Kamimaeda Naoki | Information Processing Apparatus and Method |
| CN109190043A (en) * | 2018-09-07 | 2019-01-11 | 北京三快在线科技有限公司 | Recommended method and device, storage medium, electronic equipment and recommender system |
| CN110532468A (en) * | 2019-08-26 | 2019-12-03 | 北京齐尔布莱特科技有限公司 | A kind of recommended method of site resource, device and calculate equipment |
Non-Patent Citations (1)
| Title |
|---|
| 郝胜男;赵领杰;: "一种基于ElasticSearch的推荐系统架构" * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113781086A (en) * | 2021-01-21 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Article recommendation method, device, medium and electronic equipment |
| CN112818237A (en) * | 2021-02-05 | 2021-05-18 | 上海明略人工智能(集团)有限公司 | Content pushing method, device, equipment and storage medium |
| CN113744021A (en) * | 2021-02-08 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Recommendation method, recommendation device, computer storage medium and recommendation system |
| CN113378068A (en) * | 2021-07-14 | 2021-09-10 | 聚好看科技股份有限公司 | Content recommendation method and server |
| CN113836404A (en) * | 2021-09-09 | 2021-12-24 | 武汉卓尔数字传媒科技有限公司 | Object recommendation method and device, electronic equipment and computer-readable storage medium |
| CN113688295A (en) * | 2021-10-26 | 2021-11-23 | 北京达佳互联信息技术有限公司 | Data determination method and device, electronic equipment and storage medium |
| CN114662008A (en) * | 2022-05-26 | 2022-06-24 | 上海二三四五网络科技有限公司 | Click position factor improvement-based CTR hot content calculation method and device |
| CN114662008B (en) * | 2022-05-26 | 2022-10-21 | 上海二三四五网络科技有限公司 | Click position factor improvement-based CTR hot content calculation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111538901B (en) | 2023-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111538901A (en) | Article recommendation method and device, server and storage medium | |
| CN109241415B (en) | Project recommendation method and device, computer equipment and storage medium | |
| CN109190043B (en) | Recommendation method and device, storage medium, electronic device and recommendation system | |
| CN108090208A (en) | Fused data processing method and processing device | |
| CN110543598B (en) | Information recommendation method and device and terminal | |
| CN111080413A (en) | E-commerce platform commodity recommendation method and device, server and storage medium | |
| CN111026971A (en) | Content pushing method and device and computer storage medium | |
| CN109241451B (en) | Content combination recommendation method and device and readable storage medium | |
| CN110287420B (en) | Training method and device of information recommendation system | |
| CN110647683B (en) | Information recommendation method and device | |
| CN105205188A (en) | Method and device for recommending purchase material suppliers | |
| CN107423430B (en) | Data processing method, device and computer readable storage medium | |
| CN106951527B (en) | Song recommendation method and device | |
| CN111931053A (en) | Item pushing method and device based on clustering and matrix decomposition | |
| CN110992124A (en) | House resource recommendation method and system | |
| CN111639255A (en) | Search keyword recommendation method and device, storage medium and electronic equipment | |
| CN110083766B (en) | Query recommendation method and device based on meta-path guiding embedding | |
| CN108595526A (en) | Resource recommendation method and device | |
| CN110377821A (en) | Generate method, apparatus, computer equipment and the storage medium of interest tags | |
| CN114780606A (en) | Big data mining method and system | |
| CN110442789B (en) | User behavior based association result determination method and device and electronic equipment | |
| CN112565902B (en) | Video recommendation method and device and electronic equipment | |
| CN111553762A (en) | Method, system and terminal equipment for improving search quality | |
| CN110705889A (en) | Enterprise screening method, device, equipment and storage medium | |
| CN109165282A (en) | A kind of network data grasping means and system |
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 |