CN111538901B - Article recommendation method and device, server and storage medium - Google Patents
Article recommendation method and device, server and storage medium Download PDFInfo
- Publication number
- CN111538901B CN111538901B CN202010294127.4A CN202010294127A CN111538901B CN 111538901 B CN111538901 B CN 111538901B CN 202010294127 A CN202010294127 A CN 202010294127A CN 111538901 B CN111538901 B CN 111538901B
- Authority
- CN
- China
- Prior art keywords
- preset
- target
- article
- articles
- target object
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012216 screening Methods 0.000 claims abstract description 32
- 230000006399 behavior Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 238000004904 shortening Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—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)
- 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 embodiment of the invention discloses an article recommending method, an article recommending device, a server and a storage medium, wherein the method comprises the following steps: screening preset articles in the preset article set according to preset screening rules, and selecting target articles; 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 greater than the first exposure threshold, sorting recall is performed in a preset group according to the click rate of the target object; and if the recommended times of the target articles are larger than a second exposure threshold, sorting and recalling the target articles and other preset articles in the preset article set according to a preset strategy. According to the technical scheme, the iteration period of the new article is shortened, the effect quality of the new article is quickly tested, and the high timeliness requirement of an information industry recommendation system on the article can be met.
Description
Technical Field
The embodiment of the invention relates to an artificial intelligence technology, in particular to an article recommending method, an article recommending device, a server and a storage medium.
Background
With the rapid development of propagation technology and the rapid increase of data volume, users have put forward higher requirements on timeliness and individuality in the information industry.
The iteration modes of the new article in the prior art mainly comprise the following two modes: one is to establish some association with the old article through the content of the article itself, and then expose the old article with the association. The further exposure of the new item is very dependent on the exposure level and click condition of the old item. If the old articles are clicked by the user less, the sorting is relatively back, the exposure period of the new articles is further prolonged, and the exposure times are also influenced by the recommended condition of the related old articles. And secondly, predicting the scores of the users on the articles through the model so as to carry out sequencing recall. However, in general, the user behavior data volume is large, the calculation period is long, and certain hysteresis exists, so that the iteration period of the article is prolonged. The iteration period of the new item is relatively long.
Meanwhile, the quality of the old articles can be obtained according to feedback of users due to sufficient exposure; and 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 the uniform sorting recall method, the new articles are generally in a disadvantage, so that the probability that the quality of the new articles with possibly high quality is 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 recommending method, an article recommending device, a server and a storage medium, which are used for shortening the iteration period of a new article and quickly probing out 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 the preset article set according to preset screening rules, and selecting target articles;
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 greater than the first exposure threshold, sorting recall is performed in a preset group according to the click rate of the target object;
and if the recommended times of the target articles are larger than a second exposure threshold, sorting and recalling the target articles 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 device, including:
the target article screening module is used for screening preset articles in the preset article set according to preset screening rules and selecting 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 times of the target article are smaller than a first exposure threshold value;
the first sorting recall module is used for sorting recall according to the click rate of the target object in the belonging category if the recommended number of times of the target object is larger than the first exposure threshold;
and the second sorting recall module is used for sorting recall of 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 are larger 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,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the item recommendation method as provided by any embodiment of the present 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 by any of the embodiments of the present invention.
According to the method and the device for searching the quality of the new article, the target article is 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 new article cannot be exposed in a short time due to the fact that the iteration period of the new article is relatively long is solved, and the effect of shortening the iteration period of the new article and quickly exploring the quality of the new article is achieved.
Drawings
FIG. 1 is a flow chart of a method of recommending items according to a first embodiment of the present invention;
FIG. 2 is a flow chart of a method for recommending items according to a second embodiment of the present invention;
FIG. 3 is a flow chart of a method for recommending items according to a second embodiment of the present invention;
FIG. 4 is a schematic view of an article recommendation device according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of a server according to a fourth 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.
Example 1
Fig. 1 is a flowchart of an item recommending method according to an embodiment of the present invention, where the method may be applied to a new item cold start recommending case, and the method may be performed by an item recommending apparatus, and the apparatus may be implemented by hardware and/or software, and the method specifically includes the following steps:
the method comprises the steps of acquiring a stored preset article set from a database, wherein preset articles are stored in the preset article set, the preset articles are required to be recommended to a user through a recommendation engine, and related information of the preset articles is acquired from the database. The screening target is to find a new article from the preset article set, and optionally, the screening is performed on the preset articles in the preset article set according to a preset screening rule, so as to select a target article, including: determining a preset object with the appearance time difference smaller than a first threshold value as a preselected target object; removing preselected target objects with the appearance time difference larger than a second threshold and the recommended times exceeding a preset exposure threshold; 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 a new article from an old article, and for a preset article with an appearance time difference greater than or equal to the first threshold, the preset article is considered to belong to the old article, and the first threshold is typically set to be 1 day and is automatically set according to timeliness requirements. In addition, for the range of the preselected target object, the exposure degree of which is larger than the second threshold value needs to be judged, if the exposure degree is more, that is, the recommended number of times exceeds the preset exposure threshold value, the exposure degree needs to be removed, and the exposure degree is not selected as the target object for recommendation. Illustratively, the second threshold may be set to 7200 seconds, and the longest 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 logic can be generally obtained. The preset screening rules screen out the target articles, and the rest preset articles are uniformly sequenced and recalled by adopting the same preset strategies as the old articles.
the first exposure threshold is a trial exposure threshold, the target object reaching the trial exposure threshold can be considered to be recommended to enough multiple users, and the target object with the recommended times smaller than the first exposure threshold needs to be forcedly recommended 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 category and/or label of the article, the information such as category and/or label of the article with clicking action recently of the user is obtained, the information is matched with the information of category and/or label of the new article to be exposed, and the user clicking the matched article is the preset user. A certain number of preset users are forced to recommend the target item.
130, if the recommended times of the target articles are greater than a first exposure threshold, sorting recall is performed in a preset group according to the click rate of the target articles;
and collecting clicking behaviors of the target articles with recommended times larger than a first exposure threshold, calculating the clicking rate of the target articles, and grouping the target articles according to the categories and/or labels of the target articles because the target articles belong to new articles, so that the target articles can be in a preset group, and sorting and recalling the target articles according to the clicking rate of the target articles in the same preset group from large to small.
And 140, if the recommended times of the target articles are greater than the second exposure threshold, sorting and recalling the target articles and other preset articles in the preset article set according to a preset strategy.
Wherein for a target item for which the recommended number of times has been greater than the second exposure threshold, it is considered that the range of the old item has been entered, for such target item, the sort recall may be performed using the same preset strategy as the old item. By way of example, old articles are subjected to sorting recall by adopting strategies such as collaborative filtering or Click-Through-Rate (CTR) sorting and the like, so that the distinguishing processing and final unification of new articles and old articles in a recall sorting mode are realized.
According to the technical scheme, the target articles are selected for recommendation, and the corresponding sorting recall strategy is selected according to the exposure, so that the problems that the iteration period of a new article is relatively long, the new article cannot be exposed in a short time, and the quality cannot be known are solved, the iteration period of the new article is shortened, and the quality of the new article is quickly tested.
Example two
Fig. 2 is a flowchart of an article recommending method according to a second embodiment of the present invention, where the technical solution of the present embodiment is further refined based on the technical solution, and the method specifically includes:
Wherein all_pv represents the sum of the daily exposure amounts of the preset articles, ucb _ratio represents the duty ratio of the tentative exposure, item_ ucb represents the number of new articles per day, and item_ ucb _ratio represents the duty ratio of the exposure of the new articles. The heuristic exposure ratio is generally between 5% and 10%, in this example 5% is chosen.
The preset attributes of the articles can be selected, the articles clicked by the user recently are matched with the articles of the new articles, the articles are recommended to the successfully matched preset users, and the articles are recommended to the preset users in total. According to the preference of the user, recommending new articles with the same category, so that the category effect of the new articles is easier and faster to explore.
Optionally, before recommending the target items to the preset number of preset users, the method further comprises:
determining a formula according to a preset number
And calculating a preset number, wherein ucb _max_pv represents a first exposure threshold value, and user_cnt represents the preset number of users.
wherein, optionally, the clicking action aiming at the target object is obtained, and a formula is determined according to the clicking rate
Calculating click rate of target object, wherein ctr i Indicating the click rate of the preset item i, pv i Indicating the exposure of the preset article i, ck i Indicating the click rate of a preset article i;
and in the preset group, sorting recall is carried out according to the click rate of the target object from big to small.
Fig. 3 is a flowchart of an article recommending method according to an embodiment of the present invention, where the flowchart shows a flowchart of a suitable implementation manner of a method for solving a problem of cold start of an article of a recommending system in the information industry, and the steps of the implementation manner are as follows:
1. given the set of all items, the screening conditions for the new item in this example are mainly spread out in the time dimension, so the item's time of appearance (item_product_time) must be obtained.
2. Screening out articles meeting the cold start of new articles according to screening conditions:
1) If the time difference (time_diff, the value is the current time-the time of appearance of the article) of the article exceeds a certain threshold (max_time_diff, the value is generally set to be 1 day and is set by oneself 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 article exceeds a threshold (choice_time_diff=7200, the longest running time of other recommended modules is generally selected), and the recommended number exceeds the exposure threshold (pv_max), although the article belongs to a new article, the article is sufficiently exposed, and can be recalled in a sorting way with the old article in a statistical way, and the step 9 is skipped;
3) And 3, carrying out the step 3, wherein the rest new articles meet the condition of cold starting of the new articles.
3. Information such as categories and labels of new articles (information in at least one dimension, and dimension with higher preparation rate are selected as much as possible) is acquired, and the categories are adopted in the case, because the recommended user group can be rapidly positioned through the categories, and the category information is more accurate in the case.
4. If the recommended number of articles reaches a tentative exposure threshold (ucb _max_pv), wherein the tentative exposure ratio is typically between 5% -10%, 5% is selected in this case), step 7 is performed, otherwise step 5 is performed.
5. Matching the category of the item clicked by the user recently with the category of the new item, recommending the item to the user, and recommending the item to ucb _num users in total. According to the user category preference, the system recommends new items of the same category, so that the category effect of the new items can be quickly and easily detected.
6. If the recommended number of new items reaches the tentative exposure threshold (ucb _max_pv), then go to step 7, otherwise go to step 5.
7. And collecting clicking behaviors of the new articles, calculating the clicking rate (ctr) of the new articles, and carrying out sorting recall according to the clicking rate (from large to small) under the same category.
8. If the recommended number of new articles reaches the exposure threshold (pv_max), step 9 is performed, otherwise step 7 is performed.
9. And the old articles are subjected to sorting recall in a unified calculation mode.
Because the new article is sufficiently exposed and evolves into an old article, the relevant features of the cold-start article are no longer present, thus completing a cold-start article-to-old article product cycle.
Example III
Fig. 4 is a schematic structural diagram of an article recommendation device according to a fourth embodiment of the present invention, where, as shown in fig. 4, the article recommendation device includes:
the target article screening module 410 is configured to screen preset articles in the preset article set according to a preset screening rule, and select a target article;
the target article recommending module 420 is configured to recommend the target article to a preset user searched according to the preset attribute of the target article if the recommended number of times of the target article is less than the first exposure threshold;
a first sorting recall module 430, configured to sort recalls according to the click rate of the target item in the category if the recommended number of times of the target item is greater than the first exposure threshold;
the second sorting recall module 440 is configured to sort and recall the target item and other preset items in the preset item set together according to a preset policy if the recommended number of times of the target item is greater than the second exposure threshold.
According to the technical scheme, the target articles are selected for recommendation, and the corresponding sorting recall strategy is selected according to the exposure, so that the problems that the iteration period of a new article is relatively long, the new article cannot be exposed in a short time, and the quality cannot be known are solved, the iteration period of the new article is shortened, and the quality of the new article is quickly tested.
Optionally, the target item screening module 410 includes:
a preselected target item determining unit configured to determine a preset item whose appearance time difference is smaller than a first threshold value as a preselected target item;
the rejecting unit is used for rejecting the preselected target articles of which the appearance time difference is larger 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 object determining unit is used for determining the remaining preselected target objects as target objects.
Optionally, the target item recommendation module 420 is specifically configured to:
if the recommended times of the target object are smaller than the first exposure threshold value, acquiring the object of the clicking action of the user within the preset time;
matching the object article with the target article in terms of preset attributes;
determining the users corresponding to the matched object articles as preset users;
recommending the target object to a preset number of preset users.
Optionally, the article recommendation device further includes:
a preset quantity determining module for determining a formula according to the preset quantity before recommending the target items to the preset quantity of preset users
And calculating a preset number, wherein ucb _max_pv represents a first exposure threshold value, and user_cnt represents the preset number of users.
Optionally, the article recommendation device further includes:
a first exposure threshold determining module for determining a formula according to a first exposure threshold before recommending the target object to a preset user searched according to preset attributes of the target object if the recommended number of times of the target object is smaller than the first exposure threshold
A first exposure threshold is calculated, wherein all_pv represents the sum of the daily exposure amounts of the preset articles, ucb _ratio represents the duty cycle of the heuristic exposure, item_ ucb represents the number of new articles per day, and item_ ucb _ratio represents the duty cycle of the exposure of the new articles.
Optionally, the first sorting recall module 430 is specifically configured to:
acquiring clicking behaviors aiming at target objects, and determining a formula according to the clicking rate
Calculating click rate of target object, wherein ctr i Indicating the click rate of the preset item i, pv i Indicating the exposure of the preset article i, ck i Indicating the click rate of a preset article i;
and in the preset group, sorting recall is carried out according to the click rate of the target object from big 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 IV
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 processors 510 in the server may be one or more, one processor 510 being taken as an example in fig. 5; the processor 510 and memory 520 in the server may be connected by a bus or otherwise, for example in fig. 5.
The memory 520 is used as a computer readable storage medium 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 (e.g., the target item screening module 410, the target item recommendation module 420, the first sort recall module 430, and the second sort recall module 440 in the item recommendation device). 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, i.e., implements the item recommendation method described above.
Example five
A fifth embodiment of the present invention also provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are for performing an item recommendation method, comprising:
screening preset articles in the preset article set according to preset screening rules, and selecting target articles;
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 greater than the first exposure threshold, sorting recall is performed in a preset group according to the click rate of the target object;
and when the recommended times of the target articles are larger than a second exposure threshold, sorting and recalling the target articles and other preset articles in the preset article set according to a preset strategy.
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 item recommendation 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 server, or a network device, etc.) to execute the method according to the embodiments of the present invention.
It should be noted that, in the embodiment of the article 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. An item recommendation method, comprising:
screening preset articles in the preset article set according to preset screening rules, and selecting target articles;
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 greater than the first exposure threshold, sorting recall is performed in a preset group according to the click rate of the target object;
and if the recommended times of the target articles are larger than a second exposure threshold, sorting and recalling the target articles and other preset articles in the preset article set according to a preset strategy.
2. The method of claim 1, wherein the screening the preset items in the set of preset items according to the preset screening rule, and selecting the target item comprises:
determining the preset article with the appearance time difference smaller than a first threshold value as a preselected target article;
removing the preselected target object with the appearance time difference larger than a second threshold and the recommended times exceeding a preset exposure threshold; wherein the first threshold is greater than the second threshold;
and determining the remaining preselected target items as the target items.
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, comprises:
if the recommended times of the target object are smaller than the first exposure threshold, acquiring the object of the clicking action of the user in the preset time;
matching the object article with the target article in terms of the preset attribute;
determining the matched user corresponding to the object article as the preset user;
recommending the target object to a preset number of preset users.
4. A method according to claim 3, further comprising, prior to said recommending said target item to a predetermined number of said predetermined users:
determining a formula according to a preset number
And calculating the preset number, wherein ucb _max_pv represents the first exposure threshold value, and the user_cnt represents the preset user number.
5. The method of claim 4, further comprising, 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 less than a first exposure threshold value:
determining a formula according to the first exposure threshold
Calculating the first exposure threshold, wherein all_pv represents the sum of the daily exposure amounts of the preset articles, ucb _ratio represents the duty ratio of heuristic exposure, item_ ucb represents the number of new articles per day, and item_ ucb _ratio represents the duty ratio of the new articles to be exposed.
6. The method of claim 1, wherein if the recommended number of times of the target item is greater than the first exposure threshold, sorting recalls in a preset group according to a click rate of the target item, comprising:
acquiring clicking behaviors aiming at the target object, and determining a formula according to the clicking rate
Calculating the click rate of the target object, wherein ctr i Indicating the click rate of the preset item i, pv i Indicating the exposure of the preset article i, ck i Indicating the click rate of a preset article i;
and in the preset group, sorting recalls according to the click rate of the target object from large to small.
7. An article recommendation device, comprising:
the target article screening module is used for screening preset articles in the preset article set according to preset screening rules and selecting 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 times of the target article are smaller than a first exposure threshold value;
the first sorting recall module is used for sorting recall according to the click rate of the target object in the belonging category if the recommended number of times of the target object is larger than the first exposure threshold;
and the second sorting recall module is used for sorting recall of 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 are larger than a second exposure threshold.
8. The apparatus of claim 7, wherein the target item screening module comprises:
a preselected target object determining unit for determining the preset object with the appearance time difference smaller than a first threshold value as a preselected target object;
the rejecting unit is used for rejecting the preselected target object, the appearing time difference of which is larger than a second threshold value, and the recommended times of which exceed a preset exposure threshold value; wherein the first threshold is greater than the second threshold;
and the target object determining unit is used for determining the remaining preselected target objects as the target objects.
9. A server, the server comprising:
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 item recommendation method of any one of claims 1-6.
10. A storage medium containing computer executable instructions which, when executed by a computer processor, are for performing the item recommendation method of any one of claims 1 to 6.
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 CN111538901A (en) | 2020-08-14 |
| CN111538901B true 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) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113781086B (en) * | 2021-01-21 | 2024-08-20 | 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 |
| CN113378068B (en) * | 2021-07-14 | 2023-07-18 | 聚好看科技股份有限公司 | Content recommendation method and server |
| CN113836404B (en) * | 2021-09-09 | 2024-08-16 | 武汉卓尔数字传媒科技有限公司 | Object recommendation method, device, electronic equipment and computer readable storage medium |
| CN113688295B (en) * | 2021-10-26 | 2022-03-25 | 北京达佳互联信息技术有限公司 | Data determination method and device, electronic equipment and storage medium |
| 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 |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5740814B2 (en) * | 2009-12-22 | 2015-07-01 | ソニー株式会社 | Information processing apparatus and method |
-
2020
- 2020-04-15 CN CN202010294127.4A patent/CN111538901B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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.电脑知识与技术.2017,(36),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111538901A (en) | 2020-08-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111538901B (en) | Article recommendation method and device, server and storage medium | |
| CN109190043B (en) | Recommendation method and device, storage medium, electronic device and recommendation system | |
| CN107526807B (en) | Information recommendation method and device | |
| CN105335391B (en) | The treating method and apparatus of searching request based on search engine | |
| CN107391509B (en) | Label recommending method and device | |
| CN109255586B (en) | Online personalized recommendation method for e-government affairs handling | |
| CN109189934A (en) | Public sentiment recommended method, device, computer equipment and storage medium | |
| CN109241451B (en) | Content combination recommendation method and device and readable storage medium | |
| WO2011028277A1 (en) | Information retrieval based on semantic patterns of queries | |
| CN112307762A (en) | Search result sorting method and device, storage medium and electronic device | |
| CN110597987A (en) | Search recommendation method and device | |
| CN112818230B (en) | Content recommendation method, device, electronic equipment and storage medium | |
| CN106547864A (en) | A kind of Personalized search based on query expansion | |
| CN112579854A (en) | Information processing method, device, equipment and storage medium | |
| CN110069629A (en) | House transaction task processing method, equipment, storage medium and device | |
| CN110046889A (en) | A kind of detection method, device and the server of abnormal behaviour main body | |
| CN114297505A (en) | Recommendation system, recommendation method, recommendation device and computer readable medium | |
| CN111160699A (en) | Expert recommendation method and system | |
| CN105389714B (en) | Method for identifying user characteristics from behavior data | |
| CN116610853A (en) | Search recommendation method, search recommendation system, computer device, and storage medium | |
| CN110427545B (en) | Information pushing method and system | |
| CN110377821A (en) | Generate method, apparatus, computer equipment and the storage medium of interest tags | |
| CN106844743B (en) | Emotion classification method and device for Uygur language text | |
| CN115098766B (en) | Bidding information recommendation method and system for electronic bidding transaction platform | |
| CN111435514B (en) | Feature calculation method and device, ranking method and device, and storage medium |
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 |