CN111881365A - Content recommendation method and device - Google Patents
Content recommendation method and device Download PDFInfo
- Publication number
- CN111881365A CN111881365A CN202010719289.8A CN202010719289A CN111881365A CN 111881365 A CN111881365 A CN 111881365A CN 202010719289 A CN202010719289 A CN 202010719289A CN 111881365 A CN111881365 A CN 111881365A
- Authority
- CN
- China
- Prior art keywords
- content
- recommended
- click rate
- recommendation
- weight value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 19
- 230000006399 behavior Effects 0.000 claims abstract description 15
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000005484 gravity Effects 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000014759 maintenance of location Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Medical Informatics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Mathematical Physics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention discloses a content recommendation method and device. Wherein, the method comprises the following steps: the method comprises the steps of predetermining a weighted click rate and a pre-estimated recommendation weight value of the content to be recommended, wherein the weighted click rate is an index for measuring the quality of the content to be recommended according to user behaviors, and the pre-estimated recommendation weight value is a weight value distributed for the content to be recommended according to a recommendation algorithm; determining a current recommendation weight value based on the pre-estimated recommendation weight value and the weighted click rate; and recommending the content to be recommended according to the current recommendation weight value. The invention solves the technical problem that the content recommendation scheme in the prior art can not carry out content recommendation according to the content quality of the content issued by the user.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a content recommendation method and device.
Background
With the rapid development of the internet technology, content community APPs with various large topics appear in sequence, and vast users gather based on the positioning of the content communities, so that recommendation of community contents is a main problem that each content community faces, high-quality content recommendation can increase the retention and activity degree of the users in the content communities, low-quality recommendation can reduce the retention and activity degree of the users in the content communities, and even the APP failure of the whole content community is caused.
Because most of recommendation algorithms in the prior art are recommendation algorithms based on machine learning, when contents are recommended, content-related information, author-related information, information of recommended users and the like are used as feature codes and then are sent to an algorithm model for calculation, and optimal topN contents are obtained for recommendation, so that the recommended times of the contents are higher as the concerned numbers of similar contents (which are popular in internet reprinting, similar contents are very common), identical audiences and authors are more, on one hand, the weight given to 'large V' in the algorithm is higher than that of ordinary people, on the other hand, most of community APPs have the concerned tab, and the exposure number of the contents is also increased), and the praise number is higher. In the past, most users have the same level and even better quality of content, and the exposure and feedback number of the content is not as large as that of a large V (namely, few users with more attention numbers) so that the enthusiasm of most users for releasing the content is weakened. So for most communities, large V will be more and more active, while ordinary users are more dominated by other interactive behaviors (like praise, comment on other people's content) and publish a smaller amount of content.
Although the common recommendation logic in the prior art does have the reason, the popularity of the platform for the content distributed by the large V is higher than that of the common user, so that the platform is more likely to be accepted by the wide range of users. However, if the adjustment is not properly performed, the situation that "the rich person is richer and the poor person is poorer" is caused, so that the flow is close to a large V instead of the high-quality content, which is not beneficial to the construction of the content community in the long run, and some platforms consider the problem, but perform the auditing and scoring of the content in a manual mode, manually fish the high-quality content out of the content pool, so that the labor cost is very high, and when the user quantity is large, the user cannot perform the transverse expansion in a short time.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a content recommendation method and device, which at least solve the technical problem that a content recommendation scheme in the prior art cannot recommend content according to the content quality of content issued by a user.
According to an aspect of an embodiment of the present invention, there is provided a content recommendation method including: the method comprises the steps of predetermining a weighted click rate and a pre-estimated recommendation weight value of the content to be recommended, wherein the weighted click rate is an index for measuring the quality of the content to be recommended according to user behaviors, and the pre-estimated recommendation weight value is a weight value distributed for the content to be recommended according to a recommendation algorithm; determining a current recommendation weight value based on the pre-estimated recommendation weight value and the weighted click rate; and recommending the content to be recommended according to the current recommendation weight value.
Optionally, the weighted click rate is determined at least as follows: determining concerned users and non-concerned users corresponding to the content to be recommended, and distributing the content to be recommended to the concerned users and the non-concerned users; acquiring a first click rate of a to-be-recommended content of an attention user and a second click rate of a to-be-recommended content of a non-attention user; and determining a weighted click rate according to the first click rate and the second click rate.
Alternatively, the weighted click rate ctr (c) is determined by the following calculation formula:
wherein the first click rate is
The second click rate is
nf，i(c) The number of contents to be recommended received for the concerned user, nf，c(c) Number of clicks on contents to be recommended, n, for a user of interests，c(c) The number of contents to be recommended, n, received for the non-concerned users，i(c) And (3) the number of the contents to be recommended clicked by the non-concerned user is represented by i, the identifier of each content to be recommended and alpha is a preset positive value which is used for adjusting the contribution specific gravity value of the concerned user and the non-concerned user to the weighted click rate.
Optionally, the current recommended weight value c (c) is determined by the following calculation formula: c (c) ═ β ctr (c) + f (c);
wherein, f (c) is the estimated recommended weight value, and β is the preset correction parameter value.
Optionally, recommending the content to be recommended according to the current recommendation weight value includes: sequencing a plurality of contents to be recommended according to the current recommendation weight value to obtain a recommendation list; determining the arrangement sequence of a plurality of contents to be recommended in a recommendation list; and recommending the contents to be recommended according to the arrangement sequence.
According to another aspect of the embodiments of the present invention, there is also provided a content recommendation apparatus including: the device comprises a first determining module, a second determining module and a third determining module, wherein the first determining module is used for determining the weighted click rate of the content to be recommended in advance and estimating the recommendation weight value, the weighted click rate is an index for measuring the quality of the content to be recommended according to user behaviors, and the estimated recommendation weight value is a weight value distributed to the content to be recommended according to a recommendation algorithm; the second determination module is used for determining the current recommendation weight value based on the pre-estimated recommendation weight value and the weighted click rate; and the recommending module is used for recommending the content to be recommended according to the current recommending weight value.
Optionally, the weighted click rate is determined at least as follows: the system comprises a first determining unit, a second determining unit and a third determining unit, wherein the first determining unit is used for determining concerned users and non-concerned users corresponding to the content to be recommended and distributing the content to be recommended to the concerned users and the non-concerned users; the device comprises an acquisition unit, a recommendation unit and a recommendation unit, wherein the acquisition unit is used for acquiring a first click rate of a to-be-recommended content of an attention user and a second click rate of a to-be-recommended content of a non-attention user; and the second determining unit is used for determining the weighted click rate according to the first click rate and the second click rate.
Alternatively, the weighted click rate ctr (c) is determined by the following calculation formula:
wherein the first click rate is
The second click rate is
nf，i(c) The number of contents to be recommended received for the concerned user, nf，c(c) Number of clicks on contents to be recommended, n, for a user of interests，c(c) The number of contents to be recommended, n, received for the non-concerned users，i(c) And (3) the number of the contents to be recommended clicked by the non-concerned user is represented by i, the identifier of each content to be recommended and alpha is a preset positive value which is used for adjusting the contribution specific gravity value of the concerned user and the non-concerned user to the weighted click rate.
According to another aspect of the embodiments of the present invention, there is also provided a non-volatile storage medium including a stored program, wherein the program, when executed, controls a device in which the non-volatile storage medium is located to execute any one of the content recommendation methods.
According to another aspect of the embodiments of the present invention, there is also provided a processor for executing a program stored in a memory, wherein the program executes to perform any one of the content recommendation methods.
In the embodiment of the invention, the weighted click rate of the content to be recommended and the estimated recommendation weight value are determined in advance, wherein the weighted click rate is an index for measuring the quality of the content to be recommended according to user behaviors, and the estimated recommendation weight value is a weight value distributed for the content to be recommended according to a recommendation algorithm; determining a current recommendation weight value based on the pre-estimated recommendation weight value and the weighted click rate; the content to be recommended is recommended according to the current recommendation weight value, the purposes of extracting high-quality content issued by the user and recommending the content according to the content quality are achieved, the technical effect of improving the enthusiasm of the content issued by the user is achieved, and the technical problem that content recommendation cannot be performed according to the content quality of the content issued by the user in the content recommendation scheme in the prior art is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a flowchart of a content recommendation method according to an embodiment of the present invention;
FIG. 2 is a flow diagram of an alternative method of content recommendation in accordance with embodiments of the present invention;
fig. 3 is a schematic structural diagram of a content recommendation apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
In accordance with an embodiment of the present invention, there is provided an embodiment of a content recommendation method, it should be noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.
Fig. 1 is a flowchart of a content recommendation method according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
step S102, predetermining a weighted click rate and an estimated recommendation weight value of the content to be recommended, wherein the weighted click rate is an index for measuring the quality of the content to be recommended according to user behaviors, and the estimated recommendation weight value is a weight value distributed to the content to be recommended according to a recommendation algorithm;
step S104, determining a current recommendation weight value based on the pre-estimated recommendation weight value and the weighted click rate;
and step S106, recommending the content to be recommended according to the current recommendation weight value.
In the embodiment of the invention, the weighted click rate of the content to be recommended and the estimated recommendation weight value are determined in advance, wherein the weighted click rate is an index for measuring the quality of the content to be recommended according to user behaviors, and the estimated recommendation weight value is a weight value distributed for the content to be recommended according to a recommendation algorithm; determining a current recommendation weight value based on the pre-estimated recommendation weight value and the weighted click rate; the content to be recommended is recommended according to the current recommendation weight value, the purposes of extracting high-quality content issued by the user and recommending the content according to the content quality are achieved, the technical effect of improving the enthusiasm of the content issued by the user is achieved, and the technical problem that content recommendation cannot be performed according to the content quality of the content issued by the user in the content recommendation scheme in the prior art is solved.
Optionally, the weighted click-through rate is an index for measuring quality of a content to be recommended according to user behavior, in an optional embodiment, if a certain user in the community platform publishes a piece of content, the community platform may execute a cold start algorithm on the content, that is, push the content to a small number of community users to determine a popularity of the content, and determine the weighted click-through rate according to the popularity of the content.
As an optional embodiment, after the ranking result of the recommended content is obtained through a recommendation algorithm, most recommendation algorithms automatically generate an estimated weight value of the content to be recommended, for example, the estimated click rate of the content obtained through machine learning, or the similarity degree between the content and the user, the estimated recommendation weight value and the weighted click rate are fused to obtain an adjusted current weight value, the plurality of contents to be recommended are ranked according to the current weight value to obtain a final recommendation list, and the contents to be recommended are recommended according to the ranking sequence of the plurality of contents to be recommended in the recommendation list, so that the click rate of the contents to be recommended in a cold start stage is considered, and the problem that the content quality is judged due to the influence of the number of fans of community users is reduced.
According to the method for identifying the high-quality content to be recommended, the click rate of the concerned user and the click rate of the non-concerned user are calculated respectively, the evaluation of the content love degree of the non-concerned user is more objective compared with the fan, so that the weight value of the click rate of the non-concerned user to the content to be recommended is increased, the pressing of the concerned user on the click rate of the content is pressed, the current weight value of the recommended high-quality content can be increased under the condition that the number of the high-quality content issued by the non-large V user is small, and the technical effect that the high-quality content stands out rather than the large V content stands out is achieved.
As an alternative embodiment, fig. 2 is a flowchart of an alternative content recommendation method according to an embodiment of the present invention, and as shown in fig. 2, a weighted click rate is determined at least by the following steps:
step S202, determining concerned users and non-concerned users corresponding to the content to be recommended, and distributing the content to be recommended to the concerned users and the non-concerned users;
step S204, acquiring a first click rate of a to-be-recommended content of an attention user and a second click rate of a to-be-recommended content of a non-attention user;
and step S206, determining a weighted click rate according to the first click rate and the second click rate.
It should be noted that, after the steps S202 to S206 are performed, the steps S208 to S212 are performed, and the differences between the steps S208 to S212 and the steps S102 to S106 are that the specific implementation steps of how to determine the weighted click rate are described separately in the steps S202 to S206.
Optionally, the number of concerned users of the community users is different, so that the number of the pointed-back users and the click rate are different, and therefore, a certain gap is opened for the content to be recommended with the same quality in the cold start stage, and therefore, the indexes of the concerned users and the non-concerned users need to be reconciled.
As an alternative embodiment, different weighted click rates are given to users who are interested by the author of the content c to be recommended according to whether other community users are in the cold start stage: ctr (c), the weighted click rate is determined according to the following two parts: the first click rate of the concerned user (also called fan) to the content to be recommended and the second click rate of the unconcerned user (also called passerby) to the content to be recommended are shown in the following table 1, wherein the number of the other community users receiving the content c to be recommended and the number of the users clicking the content to be recommended are as follows:
TABLE 1
| Paying attention to user | Non-attentive users | |
| Receiving the number of contents to be recommended | nf,i(c) | ns,i(c) |
| Clicking the number of contents to be recommended | nf,c(c) | ns,c(c) |
In an alternative embodiment, the weighted click rate Ctr (c) is determined by the following calculation: :
wherein the first click rate is
The second click rate is
nf，i(c) The number of contents to be recommended received for the concerned user, nf，c(c) Number of clicks on contents to be recommended, n, for a user of interests，c(c) The number of contents to be recommended, n, received for the non-concerned users，i(c) And (3) the number of the contents to be recommended clicked by the non-concerned user is represented by i, the identifier of each content to be recommended and alpha is a preset positive value which is used for adjusting the contribution specific gravity value of the concerned user and the non-concerned user to the weighted click rate.
It should be noted that, α is introduced into the above calculation formula to adjust the contribution specific gravity value of the concerned user and the non-concerned user to the weighted click rate, and in the calculation process, α takes a predetermined positive value, for example, but not limited to, a value smaller than 0.5, so as to increase the influence of the non-concerned user on the click rate of the content to be recommended (i.e., the content quality of the content to be recommended is distinguished without wearing colored glasses), and reduce the influence of the click rate of the concerned user on the content to be recommended.
In addition, in order to ensure that the detection quantity of the concerned user and the non-concerned user is convincing, the number of the concerned user and the non-concerned user receiving the content to be recommended is ensured to be as close as possible to be greater than a preset threshold, and the value range of the preset threshold is specifically limited according to the embodiment.
As another alternative embodiment, the current recommendation weight value c (c) is determined by the following calculation formula:
C(c)＝βCtr(c)+F(c)；
wherein, f (c) is the estimated recommended weight value, and β is the preset correction parameter value.
In an optional embodiment, recommending the content to be recommended according to the current recommendation weight value includes:
step S302, sequencing a plurality of contents to be recommended according to the current recommendation weight value to obtain a recommendation list;
step S304, determining the arrangement sequence of a plurality of contents to be recommended in a recommendation list;
and step S306, recommending the contents to be recommended according to the arrangement sequence.
In the above optional embodiment, the plurality of contents to be recommended are ranked according to the current recommendation weight value, so as to obtain a recommendation list; and determining the arrangement sequence of the plurality of contents to be recommended in the recommendation list, and recommending the contents to be recommended according to the arrangement sequence.
In the embodiment of the application, the specific click rate calculation and adjustment method can be replaced according to actual conditions, and the click rate can be replaced by other indexes such as praise rate and collection rate, which can measure the content quality through user behaviors.
Example 2
According to an embodiment of the present invention, an embodiment of an apparatus for implementing the content recommendation method is further provided, fig. 3 is a schematic structural diagram of a content recommendation apparatus according to an embodiment of the present invention, and as shown in fig. 3, the content recommendation apparatus includes: a first determination module 30, a second determination module 32, and a recommendation module 34, wherein:
the first determining module 30 is configured to determine a weighted click rate and an estimated recommendation weight value of the content to be recommended in advance, where the weighted click rate is an index for measuring the quality of the content to be recommended according to a user behavior, and the estimated recommendation weight value is a weight value assigned to the content to be recommended according to a recommendation algorithm; a second determining module 32, configured to determine a current recommendation weight value based on the pre-estimated recommendation weight value and the weighted click rate; and the recommending module 34 is configured to recommend the content to be recommended according to the current recommendation weight value.
It should be noted that the above modules may be implemented by software or hardware, for example, for the latter, the following may be implemented: the modules can be located in the same processor; alternatively, the modules may be located in different processors in any combination.
It should be noted here that the first determining module 30, the second determining module 32 and the recommending module 34 correspond to steps S102 to S106 in embodiment 1, and the modules are the same as the corresponding steps in implementation examples and application scenarios, but are not limited to the disclosure in embodiment 1. It should be noted that the modules described above may be implemented in a computer terminal as part of an apparatus.
In an alternative embodiment, the weighted click-through rate is determined by at least: the system comprises a first determining unit, a second determining unit and a third determining unit, wherein the first determining unit is used for determining concerned users and non-concerned users corresponding to the content to be recommended and distributing the content to be recommended to the concerned users and the non-concerned users; the device comprises an acquisition unit, a recommendation unit and a recommendation unit, wherein the acquisition unit is used for acquiring a first click rate of a to-be-recommended content of an attention user and a second click rate of a to-be-recommended content of a non-attention user; and the second determining unit is used for determining the weighted click rate according to the first click rate and the second click rate.
In an alternative embodiment, the weighted click rate Ctr (c) is determined by the following calculation:
wherein the first click rate is
The second click rate is
nf，i(c) The number of contents to be recommended received for the concerned user, nf，c(c) Number of clicks on contents to be recommended, n, for a user of interests，c(c) The number of contents to be recommended, n, received for the non-concerned users，i(c)And (3) the number of the contents to be recommended clicked by the non-concerned user is represented by i, the identifier of each content to be recommended and alpha is a preset positive value which is used for adjusting the contribution specific gravity value of the concerned user and the non-concerned user to the weighted click rate.
It should be noted that, reference may be made to the relevant description in embodiment 1 for alternative or preferred embodiments of this embodiment, and details are not described here again.
The content recommendation device may further include a processor and a memory, where the first determining module 30, the second determining module 32, the recommendation module 34, and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions.
The processor comprises a kernel, and the kernel calls a corresponding program unit from the memory, wherein one or more than one kernel can be arranged. The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
According to the embodiment of the application, the embodiment of the nonvolatile storage medium is also provided. Optionally, in this embodiment, the nonvolatile storage medium includes a stored program, and the apparatus where the nonvolatile storage medium is located is controlled to execute any one of the content recommendation methods when the program runs.
Optionally, in this embodiment, the nonvolatile storage medium may be located in any one of a group of computer terminals in a computer network, or in any one of a group of mobile terminals, and the nonvolatile storage medium includes a stored program.
Optionally, the apparatus in which the non-volatile storage medium is controlled to perform the following functions when the program is executed: the method comprises the steps of predetermining a weighted click rate and a pre-estimated recommendation weight value of the content to be recommended, wherein the weighted click rate is an index for measuring the quality of the content to be recommended according to user behaviors, and the pre-estimated recommendation weight value is a weight value distributed for the content to be recommended according to a recommendation algorithm; determining a current recommendation weight value based on the pre-estimated recommendation weight value and the weighted click rate; and recommending the content to be recommended according to the current recommendation weight value.
According to the embodiment of the application, the embodiment of the processor is also provided. Optionally, in this embodiment, the processor is configured to execute a program, where the program executes the content recommendation method.
The embodiment of the application provides equipment, the equipment comprises a processor, a memory and a program which is stored on the memory and can run on the processor, and the following steps are realized when the processor executes the program: the method comprises the steps of predetermining a weighted click rate and a pre-estimated recommendation weight value of the content to be recommended, wherein the weighted click rate is an index for measuring the quality of the content to be recommended according to user behaviors, and the pre-estimated recommendation weight value is a weight value distributed for the content to be recommended according to a recommendation algorithm; determining a current recommendation weight value based on the pre-estimated recommendation weight value and the weighted click rate; and recommending the content to be recommended according to the current recommendation weight value.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device: the method comprises the steps of predetermining a weighted click rate and a pre-estimated recommendation weight value of the content to be recommended, wherein the weighted click rate is an index for measuring the quality of the content to be recommended according to user behaviors, and the pre-estimated recommendation weight value is a weight value distributed for the content to be recommended according to a recommendation algorithm; determining a current recommendation weight value based on the pre-estimated recommendation weight value and the weighted click rate; and recommending the content to be recommended according to the current recommendation weight value.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable non-volatile storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a non-volatile storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned nonvolatile storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A content recommendation method, comprising:
the method comprises the steps of predetermining a weighted click rate and a pre-estimated recommendation weight value of the content to be recommended, wherein the weighted click rate is an index for measuring the quality of the content to be recommended according to user behaviors, and the pre-estimated recommendation weight value is a weight value distributed to the content to be recommended according to a recommendation algorithm;
determining a current recommendation weight value based on the pre-estimated recommendation weight value and the weighted click rate;
and recommending the content to be recommended according to the current recommendation weight value.
2. The method of claim 1, wherein the weighted click-through rate is determined by at least:
determining concerned users and non-concerned users corresponding to the content to be recommended, and distributing the content to be recommended to the concerned users and the non-concerned users;
acquiring a first click rate of the concerned user on the content to be recommended and a second click rate of the non-concerned user on the content to be recommended;
and determining the weighted click rate according to the first click rate and the second click rate.
3. The method according to claim 2, wherein the weighted click rate ctr (c) is determined by the following calculation:
wherein the first click rate is
The second click rate is
N isf，i(c) The number of the contents to be recommended received for the concerned user, nf，c(c) The number of the contents to be recommended clicked for the concerned user, ns，c(c) The number of the contents to be recommended received for the non-concerned user, ns，i(c) And the alpha is a preset positive value and is used for adjusting the contribution specific gravity value of the concerned user and the non-concerned user to the weighted click rate for the number of the non-concerned users clicking the content to be recommended.
4. The method of claim 3, wherein the current recommendation weight value C (c) is determined by the following calculation:
C(c)＝βCtr(c)+F(c)；
wherein f (c) is the estimated recommended weight value, and β is a preset correction parameter value.
5. The method according to claim 1, wherein recommending the content to be recommended according to the current recommendation weight value comprises:
sequencing a plurality of contents to be recommended according to the current recommendation weight value to obtain a recommendation list;
determining the arrangement sequence of a plurality of contents to be recommended in the recommendation list;
and recommending the contents to be recommended according to the arrangement sequence.
6. A content recommendation apparatus characterized by comprising:
the device comprises a first determining module, a second determining module and a third determining module, wherein the first determining module is used for determining a weighted click rate and a pre-estimated recommendation weight value of the content to be recommended in advance, the weighted click rate is an index for measuring the quality of the content to be recommended according to user behaviors, and the pre-estimated recommendation weight value is a weight value distributed to the content to be recommended according to a recommendation algorithm;
the second determination module is used for determining the current recommendation weight value based on the pre-estimated recommendation weight value and the weighted click rate;
and the recommending module is used for recommending the content to be recommended according to the current recommending weight value.
7. The apparatus of claim 6, wherein the weighted click-through rate is determined by at least:
a first determining unit, configured to determine an interested user and a non-interested user corresponding to the content to be recommended, and distribute the content to be recommended to the interested user and the non-interested user;
the obtaining unit is used for obtaining a first click rate of the concerned user on the content to be recommended and a second click rate of the non-concerned user on the content to be recommended;
and the second determining unit is used for determining the weighted click rate according to the first click rate and the second click rate.
8. The apparatus of claim 7, wherein the weighted click rate Ctr (c) is determined by the following calculation:
wherein the first click rate is
The second click rate is
N isf，i(c) Receiving the wait for the interested userNumber of recommended contents, nf，c(c) The number of the contents to be recommended clicked for the concerned user, ns，c(c) The number of the contents to be recommended received for the non-concerned user, ns，i(c) And the number of the contents to be recommended clicked by the non-concerned user is i, the identifier of each content to be recommended is i, and the alpha is a preset positive value and is used for adjusting the contribution specific gravity value of the concerned user and the non-concerned user to the weighted click rate.
9. A non-volatile storage medium, comprising a stored program, wherein when the program runs, a device where the non-volatile storage medium is located is controlled to execute the content recommendation method according to any one of claims 1 to 5.
10. A processor for executing a program stored in a memory, wherein the program when executed performs the content recommendation method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010719289.8A CN111881365A (en) | 2020-07-23 | 2020-07-23 | Content recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010719289.8A CN111881365A (en) | 2020-07-23 | 2020-07-23 | Content recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111881365A true CN111881365A (en) | 2020-11-03 |
Family
ID=73155401
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010719289.8A Pending CN111881365A (en) | 2020-07-23 | 2020-07-23 | Content recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111881365A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112633321A (en) * | 2020-11-26 | 2021-04-09 | 北京瑞友科技股份有限公司 | Artificial intelligence recommendation system and method |
| CN113268583A (en) * | 2021-07-20 | 2021-08-17 | 三诺生物传感股份有限公司 | Knowledge recommendation method based on community content |
| CN113987353A (en) * | 2021-10-29 | 2022-01-28 | 掌阅科技股份有限公司 | Book recommendation method, computing device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140149425A1 (en) * | 2012-11-23 | 2014-05-29 | Mobitv, Inc. | View count weighted content recommendation |
| CN106251174A (en) * | 2016-07-26 | 2016-12-21 | 北京小米移动软件有限公司 | Information recommendation method and device |
| CN106649482A (en) * | 2016-09-30 | 2017-05-10 | 网易（杭州）网络有限公司 | Information push method and device |
| CN110309418A (en) * | 2018-04-26 | 2019-10-08 | 腾讯科技（北京）有限公司 | Recommendation determines method, apparatus, storage medium and computer equipment |
| CN110674406A (en) * | 2019-09-29 | 2020-01-10 | 百度在线网络技术（北京）有限公司 | Recommendation method and device, electronic equipment and storage medium |
-
2020
- 2020-07-23 CN CN202010719289.8A patent/CN111881365A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140149425A1 (en) * | 2012-11-23 | 2014-05-29 | Mobitv, Inc. | View count weighted content recommendation |
| CN106251174A (en) * | 2016-07-26 | 2016-12-21 | 北京小米移动软件有限公司 | Information recommendation method and device |
| CN106649482A (en) * | 2016-09-30 | 2017-05-10 | 网易（杭州）网络有限公司 | Information push method and device |
| CN110309418A (en) * | 2018-04-26 | 2019-10-08 | 腾讯科技（北京）有限公司 | Recommendation determines method, apparatus, storage medium and computer equipment |
| CN110674406A (en) * | 2019-09-29 | 2020-01-10 | 百度在线网络技术（北京）有限公司 | Recommendation method and device, electronic equipment and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112633321A (en) * | 2020-11-26 | 2021-04-09 | 北京瑞友科技股份有限公司 | Artificial intelligence recommendation system and method |
| CN113268583A (en) * | 2021-07-20 | 2021-08-17 | 三诺生物传感股份有限公司 | Knowledge recommendation method based on community content |
| CN113987353A (en) * | 2021-10-29 | 2022-01-28 | 掌阅科技股份有限公司 | Book recommendation method, computing device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020048084A1 (en) | Resource recommendation method and apparatus, computer device, and computer-readable storage medium | |
| CN111881365A (en) | Content recommendation method and device | |
| US8799814B1 (en) | Automated targeting of content components | |
| CN103678518B (en) | Method and device for adjusting recommendation lists | |
| WO2017121314A1 (en) | Information recommendation method and apparatus | |
| Godinho de Matos et al. | Culling the herd: Using real-world randomized experiments to measure social bias with known costly goods | |
| CN107526810B (en) | Method and device for establishing click rate estimation model and display method and device | |
| US10282758B1 (en) | Pricing control in a real-time network-based bidding environment | |
| US20140244667A1 (en) | Method and Apparatuses for Enabling Recommendations | |
| CN107301247B (en) | Method and device for establishing click rate estimation model, terminal and storage medium | |
| CN112364202A (en) | Video recommendation method and device and electronic equipment | |
| CN105654198B (en) | Brand advertisement effect optimization method capable of realizing optimal threshold value selection | |
| CN111311332A (en) | User data processing method and device | |
| WO2023000491A1 (en) | Application recommendation method, apparatus and device, and computer-readable storage medium | |
| CN106294601B (en) | Data processing method and device | |
| CN110933472A (en) | Method and device for realizing video recommendation | |
| US20190050890A1 (en) | Video dotting placement analysis system, analysis method and storage medium | |
| CN111865753B (en) | Method and device for determining parameters of media information, storage medium and electronic device | |
| CN116739665A (en) | Information delivery method and device, electronic equipment and storage medium | |
| CN106919609B (en) | Product information pushing method and device | |
| CN111210274A (en) | Advertisement recommendation method and system | |
| CN114387041B (en) | Multimedia data acquisition method and system | |
| KR101394309B1 (en) | Method and apparatus for providing advertisement | |
| CN109086813A (en) | Determination method, apparatus, equipment and the storage medium of main broadcaster's similarity | |
| CN115063178A (en) | Method and device for determining sensitivity degree of target group to service scene |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Li Dongjun Inventor after: Chen Yingxiang Inventor after: Wang Ran Inventor before: Chen Yingxiang Inventor before: Wang Ran Inventor before: Li Dongjun |