CN108804676A - A kind of model sort method, device, equipment and computer readable storage medium - Google Patents
A kind of model sort method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN108804676A CN108804676A CN201810596967.9A CN201810596967A CN108804676A CN 108804676 A CN108804676 A CN 108804676A CN 201810596967 A CN201810596967 A CN 201810596967A CN 108804676 A CN108804676 A CN 108804676A
- Authority
- CN
- China
- Prior art keywords
- model
- ranking
- details page
- page
- under
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Information Transfer Between Computers (AREA)
Abstract
Invention describes a kind of model sort method, device, equipment and computer readable storage medium, this method to include：According to behavioral data of the user in the details page of each model, fractional value of each model under each details page behavioral indicator is calculated；According to fractional value of all models under a details page behavioral indicator, ranking of each model under the details page behavioral indicator is calculated；According to ranking of each model under each details page behavioral indicator, minimum ranking of each model under all details page behavioral indicators is determined；According to the minimum ranking for each model determined, all models are ranked up.The present invention can eliminate model second-rate in ranking, improve the Experience Degree of user.
Description
Technical field
The present invention relates to Internet technical fields more particularly to a kind of model sort method, device, equipment and computer can
Read storage medium.
Background technology
With the continuous development of Internet technology, the data information in internet is increasingly huge, and user is frequently necessary to carry out
Search operation is to obtain desired information.In the prior art, the single sequence index of generally use is to the model in search result
It is ranked up, such as：Model is ranked up according to the time being posted by, or according to the clicking rate of model.But it is existing
Sortord in technology is single in the presence of sequence index, the poor problem of sequence effect；But also there are quality occur in ranking
The phenomenon that poor model, to influence user experience.
Invention content
The main purpose of the embodiment of the present invention is to propose a kind of model sort method, device, equipment and computer-readable
Storage medium can eliminate model second-rate in ranking, improve the Experience Degree of user.
To achieve the above object, an embodiment of the present invention provides a kind of model sort method, the method includes：
According to behavioral data of the user in the details page of each model, it is to refer to calculate each model in each details page line
Fractional value under mark；
According to fractional value of all models under a details page behavioral indicator, each model is calculated in the details
Ranking under page behavioral indicator；
According to ranking of each model under each details page behavioral indicator, determine each model in all details page lines
For the minimum ranking under index；
According to the minimum ranking for each model determined, all models are ranked up.
Optionally, it in the fractional value according to all models under a details page behavioral indicator, is calculated each
Before ranking of the model under the details page behavioral indicator, the method further includes：
Operation is merged to the same type of details page behavioral indicator of each model, and is calculated often according to preset algorithm
The fractional value of details page behavioral indicator after a model merging.
Optionally, the minimum ranking for each model determined in the basis, after being ranked up to all models, institute
The method of stating further includes：
According to ranking results, n model is filtered out according to default screening rule, and be presented in list page；Wherein, n is
Positive integer.
Optionally, the minimum ranking for each model determined in the basis, after being ranked up to all models, institute
The method of stating further includes：
According to ranking results, n model, and the institute of each model after calculating sifting are filtered out according to default screening rule
There is the total value of the fractional value of details page behavioral indicator；
According to user to the behavioral data of each model after screening in list page, each model after calculating sifting
The fractional value of list page behavioral indicator；
It is right according to the product value of the fractional value and corresponding total value of the list page behavioral indicator of each model after screening
All models after screening are ranked up, and ranking results are presented in list page.
Optionally, the details page behavioral indicator includes at least following one：Phone conversion ratio, short message conversion ratio, it is micro- chat
Conversion ratio, collection number, hop count, page residence time.
Optionally, the list page behavioral indicator includes：Clicking rate.
In addition, to achieve the above object, the embodiment of the present invention also proposes that a kind of model collator, described device include：
Computing module calculates each model each for the behavioral data according to user in the details page of each model
Fractional value under a details page behavioral indicator；
First sorting module is calculated for the fractional value according to all models under a details page behavioral indicator
Each ranking of the model under the details page behavioral indicator；
Determining module determines each model for the ranking according to each model under each details page behavioral indicator
Minimum ranking under all details page behavioral indicators；
Second sorting module is ranked up all models for the minimum ranking according to each model determined.
Optionally, described device further includes：
Module is presented, for according to ranking results, filtering out n model according to default screening rule, and be presented on list
In page；Wherein, n is positive integer.
In addition, to achieve the above object, the embodiment of the present invention also proposes that a kind of model sequencing equipment, the equipment include：
Processor, memory and communication bus；
The communication bus is for realizing the connection communication between the processor and the memory；
The processor is for executing the model collator stored in the memory, to realize the model of above-mentioned introduction
The step of sort method.
In addition, to achieve the above object, the embodiment of the present invention also proposes a kind of computer readable storage medium, the calculating
Machine readable storage medium storing program for executing is stored with model collator；
When the model collator is executed by least one processor, at least one processor is caused to execute
The step of giving an account of the model sort method to continue.
Model sort method, device, equipment and the computer readable storage medium that the embodiment of the present invention proposes introduce a variety of
Sort index, and the fractional value according to all models under single index, is ranked up to all models, obtains all models and exist
Ranking under single index.Minimum ranking of the model under multiple indexs, i.e. most backward ranking are determined again, and are based on
The minimum ranking of each model is ranked up all models.To eliminate model second-rate in ranking, only to user
It is presented in the higher model of composite score in each sequence index, improves the viewing experience of user.
Description of the drawings
Fig. 1 is the flow chart of the model sort method of first embodiment of the invention；
Fig. 2 is the flow chart of the model sort method of second embodiment of the invention；
Fig. 3 is the flow chart of the model sort method of third embodiment of the invention；
Fig. 4 is the flow chart of the model sort method of fourth embodiment of the invention；
Fig. 5 is the composed structure schematic diagram of the model collator of fifth embodiment of the invention；
Fig. 6 is the composed structure schematic diagram of the model sequencing equipment of sixth embodiment of the invention.
Specific implementation mode
Further to illustrate that the embodiment of the present invention is to reach the technological means and effect that predetermined purpose is taken, tie below
Attached drawing and preferred embodiment are closed, the embodiment of the present invention is described in detail as rear.
First embodiment of the invention, it is proposed that a kind of model sort method, as shown in Figure 1, the method specifically include with
Lower step：
Step S101：According to behavioral data of the user in the details page of each model, each model is calculated each detailed
Fractional value under feelings page behavioral indicator.
In embodiments of the present invention, model is a record in list page, and list page contains multiple models；Details page
To click the page entered after model in list page.For example, the result of page searching after being searched on search website
As list page, each search result presented in list page is model, and it is the note to click the page entered after model
The details page of son.
Specifically, step S101, including：
Step A1：Statistics is in set period of time, behavioral data of multiple users in the details page of each model.
Wherein, behavioral data of the user in the details page of each model, including：Click behavioral data, browsing time number
According to and input text data.
Step A2：According to statistical result, according to preset algorithm, it is to refer to calculate each model in each preset details page line
Fractional value under mark.
Further, step S101 further includes：According to following formula, the fractional value of each details page behavioral indicator is returned
One changes into certain numerical value：
Wherein, Score is according to the calculated fractional value of preset algorithm；
μ is the average mark numerical value under all models details page behavioral indicator in office；
σ is the standard deviation under all models details page behavioral indicator in office；
For the fractional value after normalization.
Step S102：According to fractional value of all models under a details page behavioral indicator, each model is calculated
Ranking under the details page behavioral indicator.
In embodiments of the present invention, in the way of step S102, a model is obtained in each details page behavioral indicator
Under ranking.For example, ranking of the model under each details page behavioral indicator is respectively：58,12,36,41,18.
Step S103：According to ranking of each model under each details page behavioral indicator, determine each model in institute
There is the minimum ranking under details page behavioral indicator.
The as most backward ranking of minimum ranking, but numerically it is the largest ranking.If for example, a model is each
Ranking under details page behavioral indicator is respectively：58,12,36,41,18, then the minimum ranking of the model is 58.
Step S104：According to the minimum ranking for each model determined, all models are ranked up.
Specifically, being the minimum row according to each model under each details page behavioral indicator in embodiments of the present invention
Name carries out ascending sort to all models so that the model for coming front does not appear under some details page behavioral indicator
The extremely low situation of ranking, the comprehensive quality to ensure the model for coming front are higher.
Specifically, after step s 104, the method further includes：
According to ranking results, n model is filtered out according to default screening rule, and be presented in list page；Wherein, n is
Positive integer.
Further, if being to carry out ascending sort to all models in step S104, it is screening to preset screening rule
Go out n before coming models；If being to carry out descending sort to all models in step S104, it is screening to preset screening rule
Go out to come rear n models.
Compared with prior art, the behavioral data according to user in the details page of model in embodiments of the present invention, meter
Calculate fractional value of each model under multiple sequence indexs.According to fractional value of all models under individually sequence index, to institute
There is model to be ranked up, obtains ranking of all models under individually sequence index.Determine a model in multiple sequences again
Minimum ranking under index, i.e. most backward ranking, according to so the minimum ranking of model carries out ascending sort, and before coming
The model in face is presented in list page.It is the higher model of quality to ensure that the model being presented in list page all, it will not
There are the models of poor quality, and then improve the viewing experience of user.
Second embodiment of the invention, it is proposed that a kind of model sort method, as shown in Fig. 2, the method specifically include with
Lower step：
Step S201：According to behavioral data of the user in the details page of each model, each model is calculated each detailed
Fractional value under feelings page behavioral indicator.
In embodiments of the present invention, model is a record in list page, and list page contains multiple models；Details page
To click the page entered after model in list page.For example, the result of page searching after being searched on search website
As list page, each search result presented in list page is model, and it is the note to click the page entered after model
The details page of son.
Specifically, step S201, including：
Step A1：Statistics is in set period of time, behavioral data of multiple users in the details page of each model.
Wherein, behavioral data of the user in the details page of each model, including：Click behavioral data, browsing time number
According to and input text data.
Step A2：According to statistical result, according to preset algorithm, it is to refer to calculate each model in each preset details page line
Fractional value under mark.
Further, step S201 further includes：According to following formula, the fractional value of each details page behavioral indicator is returned
One changes into certain numerical value：
Wherein, Score is according to the calculated fractional value of preset algorithm；
μ is the average mark numerical value under all models details page behavioral indicator in office；
σ is the standard deviation under all models details page behavioral indicator in office；
For the fractional value after normalization.
Step S202：According to fractional value of all models under a details page behavioral indicator, each model is calculated
Ranking under the details page behavioral indicator.
In embodiments of the present invention, in the way of step S202, a model is obtained in each details page behavioral indicator
Under ranking.For example, ranking of the model under each details page behavioral indicator is respectively：58,12,36,41,18.
Step S203：According to ranking of each model under each details page behavioral indicator, determine each model in institute
There is the minimum ranking under details page behavioral indicator.
The as most backward ranking of minimum ranking, but numerically it is the largest ranking.If for example, a model is each
Ranking under details page behavioral indicator is respectively：58,12,36,41,18, then the minimum ranking of the model is 58.
Step S204：According to the minimum ranking for each model determined, all models are ranked up.
Step S205：According to ranking results, n model is filtered out according to default screening rule, and every after calculating sifting
The total value of the fractional value of all details page behavioral indicators of a model.
If specifically, being to carry out ascending sort to all models in step S204, default screening rule is to filter out
N models before coming；If being to carry out descending sort to all models in step S204, default screening rule is to filter out
Come rear n models.
Step S206：According to user to the behavioral data of each model after screening in list page, after calculating sifting
The fractional value of the list page behavioral indicator of each model.
Specifically, the user includes to the behavioral data of each model in list page：Click behavioral data；
The list page behavioral indicator includes：Clicking rate.
Step S207：According to the fractional value of the list page behavioral indicator of each model after screening and corresponding total value
Product value is ranked up all models after screening, and ranking results is presented in list page.
Preferably, descending sort is carried out to all models after screening in step S207.
In embodiments of the present invention, two minor sorts are carried out to model, is first to refer in each details page line according to each model
Minimum ranking under mark is tentatively sorted, to first screen the preferable part model of mass from numerous models；In root
Two minor sorts are carried out according to the list page behavioral indicator of each model filtered out and each details page behavioral indicator, to ensure to arrange
Model in front is not in second-rate situation.
Third embodiment of the invention, it is proposed that a kind of model sort method, as shown in figure 3, the method specifically include with
Lower step：
Step S301：According to behavioral data of the user in the details page of each model, each model is calculated each detailed
Fractional value under feelings page behavioral indicator.
In embodiments of the present invention, model is a record in list page, and list page contains multiple models；Details page
To click the page entered after model in list page.For example, the result of page searching after being searched on search website
As list page, each search result presented in list page is model, and it is the note to click the page entered after model
The details page of son.
Specifically, step S301, including：
Step A1：Statistics is in set period of time, behavioral data of multiple users in the details page of each model.
Wherein, behavioral data of the user in the details page of each model, including：Click behavioral data, browsing time number
According to and input text data.
Step A2：According to statistical result, according to preset algorithm, it is to refer to calculate each model in each preset details page line
Fractional value under mark.
Further, step S301 further includes：According to following formula, the fractional value of each details page behavioral indicator is returned
One changes into certain numerical value：
Wherein, Score is according to the calculated fractional value of preset algorithm；
μ is the average mark numerical value under all models details page behavioral indicator in office；
σ is the standard deviation under all models details page behavioral indicator in office；
For the fractional value after normalization.
Further, the details page behavioral indicator includes：Phone conversion ratio, micro- merely conversion ratio, is received short message conversion ratio
Hide number, hop count and page residence time.
Wherein, phone conversion ratio is frequency of the user by phone information and business contact in details page；Short message converts
Rate is user by the way that the frequency of the short message service in details page and business contact is arranged；Micro- conversion ratio of chatting is that user passes through setting
The frequency of instant messaging business and business contact in details page.
As shown in table 1, be it is calculated number be 001 to number be 350 model under each details page behavioral indicator
Fractional value：
Table 1
Step S302：Operation is merged to the same type of details page behavioral indicator of each model, and according to default
Algorithm calculates the fractional value of the details page behavioral indicator after each model merges.
Preferably, preset algorithm is arithmetic average algorithm.
For example, phone conversion ratio, short message conversion ratio in table 1 and micro- to chat conversion ratio be same type of details page line is finger
Mark, can be merged into communication conversion ratio, fractional value of each model after merging under each details page behavioral indicator such as 2 institute of table
Show：
Table 2
Step S303：According to fractional value of all models under a details page behavioral indicator, each model is calculated
Ranking under the details page behavioral indicator.
As shown in table 3, the ranking for all models under each details page behavioral indicator：
Table 3
Step S304：According to ranking of each model under each details page behavioral indicator, determine each model in institute
There is the minimum ranking under details page behavioral indicator.
For example, as shown in table 4, number be 001 to number be 350 minimum ranking be：
Table 4
Step S305：According to the minimum ranking for each model determined, ascending sort is carried out to all models.
For example, according to the minimum ranking of each model as shown in table 4, ascending sort result is：#349,#350,#
003、#001、#004、#002。
It should be noted that if there is the identical situation of the minimum ranking of model, such as：Model #001 and model #004
Minimum ranking be 5, then model #001 and model #004 in ascending sort result side by side, be randomly provided sequencing.
Step S306：According to ascending sort as a result, n models are presented in list page before coming；Wherein, n is just
Integer.
Fourth embodiment of the invention, it is proposed that a kind of model sort method, as shown in figure 4, the method specifically include with
Lower step：
Step S401：According to behavioral data of the user in the details page of each model, each model is calculated each detailed
Fractional value under feelings page behavioral indicator.
In embodiments of the present invention, model is a record in list page, and list page contains multiple models；Details page
To click the page entered after model in list page.For example, the result of page searching after being searched on search website
As list page, each search result presented in list page is model, and it is the note to click the page entered after model
The details page of son.
Specifically, step S401, including：
Step A1：Statistics is in set period of time, behavioral data of multiple users in the details page of each model.
Wherein, behavioral data of the user in the details page of each model, including：Click behavioral data, browsing time number
According to and input text data.
Step A2：According to statistical result, according to preset algorithm, it is to refer to calculate each model in each preset details page line
Fractional value under mark.
Further, step S401 further includes：According to following formula, the fractional value of each details page behavioral indicator is returned
One changes into certain numerical value：
Wherein, Score is according to the calculated fractional value of preset algorithm；
μ is the average mark numerical value under all models details page behavioral indicator in office；
σ is the standard deviation under all models details page behavioral indicator in office；
For the fractional value after normalization.
Further, in embodiments of the present invention, details page behavioral indicator includes：Phone conversion ratio, short message conversion ratio,
It is micro- to chat conversion ratio, collection number, hop count and page residence time.
Wherein, phone conversion ratio is frequency of the user by phone information and business contact in details page；Short message converts
Rate is user by the way that the frequency of the short message service in details page and business contact is arranged；Micro- conversion ratio of chatting is that user passes through setting
The frequency of instant messaging business and business contact in details page.
As shown in table 5, be it is calculated number be 001 to number be 350 model under each details page behavioral indicator
Fractional value：
Table 5
Step S402：Operation is merged to the same type of details page behavioral indicator of each model, and according to default
Algorithm calculates the fractional value of the details page behavioral indicator after each model merges.
Preferably, preset algorithm is arithmetic average algorithm.
For example, phone conversion ratio, short message conversion ratio in table 5 and micro- to chat conversion ratio be same type of details page line is finger
Mark, can be merged into communication conversion ratio, fractional value of each model after merging under each details page behavioral indicator such as 6 institute of table
Show：
Table 6
Step S403：The list page of each model is calculated to the behavioral data of each model in list page according to user
The fractional value of behavioral indicator.
Specifically, the user includes to the behavioral data of each model in list page：Click behavioral data；
The list page behavioral indicator includes：Clicking rate.
As shown in table 7, it is the fractional value of the clicking rate of each model：
Table 7
Step S404：According to fractional value of all models under a details page behavioral indicator, each model is obtained in institute
State the ranking under details page behavioral indicator.
Such as shown in table 8, for ranking of all models under each details page behavioral indicator：
Table 8
Step S405：According to ranking of each model under each details page behavioral indicator, determine each model in institute
There is the minimum ranking under details page behavioral indicator.
For example, as shown in table 9, number be 001 to number be 350 minimum ranking be：
Table 9
Step S406：According to the minimum ranking for each model determined, to all models progress ascending sort, and according to
Ascending sort comes preceding n models as a result, filtering out.
Step S407：The total value of the fractional value of all details page behavioral indicators of each model after calculating sifting.
As shown in table 10, it is the total value of n models before coming：
Table 10
Step S408：According to the fractional value of the list page behavioral indicator of each model after screening and corresponding total value
Product value carries out descending sort to all models after screening, and descending sort result is presented in list page.
As shown in table 11, it is the product value of the total value and clicking rate of n models before coming, and according to product value
Overall ranking：
Table 11
Fifth embodiment of the invention, it is proposed that a kind of model sort method, as shown in figure 5, described device specifically include with
Lower component part：
Computing module 501 calculates each model and exists for the behavioral data according to user in the details page of each model
Fractional value under each details page behavioral indicator；
First sorting module 502 is calculated for the fractional value according to all models under a details page behavioral indicator
To ranking of each model under the details page behavioral indicator；
Determining module 503 determines each note for the ranking according to each model under each details page behavioral indicator
Minimum ranking of the son under all details page behavioral indicators；
Second sorting module 504 arranges all models for the minimum ranking according to each model determined
Sequence.
Specifically, described device further includes：
Merging module, in the fractional value according to all models under a details page behavioral indicator, calculating
To before ranking of each model under the details page behavioral indicator, the same type of details page line to each model is to refer to
Mark merges operation, and the fractional value of the details page behavioral indicator after each model merges is calculated according to preset algorithm.
Further, described device further includes：
Module is presented, for according to ranking results, filtering out n model according to default screening rule, and be presented on list
In page；Wherein, n is positive integer.
Further, described device further includes：
Processing module, for according to ranking results, filtering out n model according to default screening rule, and after calculating sifting
Each model all details page behavioral indicators fractional value total value；According to user to every after screening in list page
The behavioral data of a model, the fractional value of the list page behavioral indicator of each model after calculating sifting；According to every after screening
The product value of the fractional value and corresponding total value of the list page behavioral indicator of a model arranges all models after screening
Sequence, and ranking results are presented in list page.
Further, the details page behavioral indicator includes at least following one：Phone conversion ratio, short message conversion ratio,
It is micro- to chat conversion ratio, collection number, hop count, page residence time.
The list page behavioral indicator includes：Clicking rate.
Sixth embodiment of the invention, it is proposed that a kind of model sequencing equipment, as shown in fig. 6, the equipment includes：Processor
601, memory 602 and communication bus；
The communication bus is for realizing the connection communication between processor 601 and memory 602；
Processor 601 is for executing the model collator stored in memory 602, to realize following steps：
According to behavioral data of the user in the details page of each model, it is to refer to calculate each model in each details page line
Fractional value under mark；
According to fractional value of all models under a details page behavioral indicator, each model is calculated in the details
Ranking under page behavioral indicator；
According to ranking of each model under each details page behavioral indicator, determine each model in all details page lines
For the minimum ranking under index；
According to the minimum ranking for each model determined, all models are ranked up.
Seventh embodiment of the invention, it is proposed that a kind of computer readable storage medium, the computer readable storage medium
It is stored with model collator；
When the model collator is executed by least one processor, cause at least one processor to execute with
Lower step operation：
According to behavioral data of the user in the details page of each model, it is to refer to calculate each model in each details page line
Fractional value under mark；
According to fractional value of all models under a details page behavioral indicator, each model is calculated in the details
Ranking under page behavioral indicator；
According to ranking of each model under each details page behavioral indicator, determine each model in all details page lines
For the minimum ranking under index；
According to the minimum ranking for each model determined, all models are ranked up.
Model sort method, device, equipment and the computer readable storage medium introduced in the embodiment of the present invention introduce more
Kind sequence index, and the fractional value according to all models under single index, are ranked up all models, obtain all models
Ranking under single index.Minimum ranking of the model under multiple indexs, i.e. most backward ranking, and base are determined again
All models are ranked up in the minimum ranking of each model.To eliminate model second-rate in ranking, only to
Family is presented in the higher model of composite score in each sequence index, improves the viewing experience of user.
Should be able to be the technology reached predetermined purpose and taken to the embodiment of the present invention by the explanation of specific implementation mode
Means and effect are able to more go deep into and specifically understand, however appended diagram is only to provide reference and description and is used, and not uses
To be limited to the embodiment of the present invention.
Claims (10)
1. a kind of model sort method, which is characterized in that the method includes：
According to behavioral data of the user in the details page of each model, each model is calculated under each details page behavioral indicator
Fractional value；
According to fractional value of all models under a details page behavioral indicator, each model is calculated in the details page line
For the ranking under index；
According to ranking of each model under each details page behavioral indicator, determine that each model in all details page lines is to refer to
Minimum ranking under mark；
According to the minimum ranking for each model determined, all models are ranked up.
2. model sort method according to claim 1, which is characterized in that it is described according to all models in a details
Fractional value under page behavioral indicator, is calculated before ranking of each model under the details page behavioral indicator, the side
Method further includes：
Operation is merged to the same type of details page behavioral indicator of each model, and each note is calculated according to preset algorithm
The fractional value of details page behavioral indicator after son merging.
3. model sort method according to claim 1, which is characterized in that in each model that the basis is determined
Minimum ranking, after being ranked up to all models, the method further includes：
According to ranking results, n model is filtered out according to default screening rule, and be presented in list page；Wherein, n is just whole
Number.
4. model sort method according to claim 1, which is characterized in that in each model that the basis is determined
Minimum ranking, after being ranked up to all models, the method further includes：
According to ranking results, n model is filtered out according to default screening rule, and each model after calculating sifting is all detailed
The total value of the fractional value of feelings page behavioral indicator；
According to user to the behavioral data of each model after screening in list page, the list of each model after calculating sifting
The fractional value of page behavioral indicator；
According to the product value of the fractional value and corresponding total value of the list page behavioral indicator of each model after screening, to screening
All models afterwards are ranked up, and ranking results are presented in list page.
5. model sort method according to claim 1, which is characterized in that the details page behavioral indicator include at least with
It is one of lower：Phone conversion ratio, short message conversion ratio, micro- merely conversion ratio, collection number, hop count, page residence time.
6. model sort method according to claim 4, which is characterized in that the list page behavioral indicator includes：It clicks
Rate.
7. a kind of model collator, which is characterized in that described device includes：
Computing module calculates each model each detailed for the behavioral data according to user in the details page of each model
Fractional value under feelings page behavioral indicator；
First sorting module is calculated each for the fractional value according to all models under a details page behavioral indicator
Ranking of the model under the details page behavioral indicator；
Determining module determines each model in institute for the ranking according to each model under each details page behavioral indicator
There is the minimum ranking under details page behavioral indicator；
Second sorting module is ranked up all models for the minimum ranking according to each model determined.
8. model collator according to claim 7, which is characterized in that described device further includes：
Module is presented, for according to ranking results, filtering out n model according to default screening rule, and be presented in list page；
Wherein, n is positive integer.
9. a kind of model sequencing equipment, which is characterized in that the equipment includes：Processor, memory and communication bus；
The communication bus is for realizing the connection communication between the processor and the memory；
The processor is any in claim 1 to 6 to realize for executing the model collator stored in the memory
Described in model sort method the step of.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has model sequence
Program；
When the model collator is executed by least one processor, at least one processor perform claim is caused to be wanted
The step of seeking the model sort method described in any one of 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810596967.9A CN108804676B (en) | 2018-06-11 | 2018-06-11 | Post sorting method, device and equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810596967.9A CN108804676B (en) | 2018-06-11 | 2018-06-11 | Post sorting method, device and equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108804676A true CN108804676A (en) | 2018-11-13 |
| CN108804676B CN108804676B (en) | 2022-01-28 |
Family
ID=64088404
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810596967.9A Active CN108804676B (en) | 2018-06-11 | 2018-06-11 | Post sorting method, device and equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108804676B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110825939A (en) * | 2019-09-19 | 2020-02-21 | 五八有限公司 | Method and device for generating and sorting scores of posts, electronic equipment and storage medium |
| CN111144973A (en) * | 2019-11-29 | 2020-05-12 | 深圳市嘀哒知经科技有限责任公司 | Question ranking method and computer-readable storage medium |
| CN112115334A (en) * | 2020-09-28 | 2020-12-22 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for distinguishing hot content of network community |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130117107A1 (en) * | 2011-11-05 | 2013-05-09 | Jon C. Evans | System and method for building advertisements from imported data |
| CN105027123A (en) * | 2013-03-01 | 2015-11-04 | 谷歌公司 | Recommending content based on proxy-based preference indications |
| CN105917364A (en) * | 2013-12-31 | 2016-08-31 | 微软技术许可有限责任公司 | Ranking of discussion threads in a question-and-answer forum |
| CN106294363A (en) * | 2015-05-15 | 2017-01-04 | 厦门美柚信息科技有限公司 | A kind of forum postings evaluation methodology, Apparatus and system |
| CN106406882A (en) * | 2016-09-14 | 2017-02-15 | 百度在线网络技术（北京）有限公司 | Method and device for displaying post background in forum |
| US9715532B1 (en) * | 2016-10-10 | 2017-07-25 | Tinder, Inc. | Systems and methods for content object optimization |
-
2018
- 2018-06-11 CN CN201810596967.9A patent/CN108804676B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130117107A1 (en) * | 2011-11-05 | 2013-05-09 | Jon C. Evans | System and method for building advertisements from imported data |
| CN105027123A (en) * | 2013-03-01 | 2015-11-04 | 谷歌公司 | Recommending content based on proxy-based preference indications |
| CN105917364A (en) * | 2013-12-31 | 2016-08-31 | 微软技术许可有限责任公司 | Ranking of discussion threads in a question-and-answer forum |
| CN106294363A (en) * | 2015-05-15 | 2017-01-04 | 厦门美柚信息科技有限公司 | A kind of forum postings evaluation methodology, Apparatus and system |
| CN106406882A (en) * | 2016-09-14 | 2017-02-15 | 百度在线网络技术（北京）有限公司 | Method and device for displaying post background in forum |
| US9715532B1 (en) * | 2016-10-10 | 2017-07-25 | Tinder, Inc. | Systems and methods for content object optimization |
Non-Patent Citations (1)
| Title |
|---|
| 任丽芸等: "搜索引擎网页排序算法研究综述", 《电脑与电信》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110825939A (en) * | 2019-09-19 | 2020-02-21 | 五八有限公司 | Method and device for generating and sorting scores of posts, electronic equipment and storage medium |
| CN110825939B (en) * | 2019-09-19 | 2023-10-13 | 五八有限公司 | Post score generation and ordering method and device, electronic equipment and storage medium |
| CN111144973A (en) * | 2019-11-29 | 2020-05-12 | 深圳市嘀哒知经科技有限责任公司 | Question ranking method and computer-readable storage medium |
| CN111144973B (en) * | 2019-11-29 | 2023-07-25 | 深圳市嘀哒知经科技有限责任公司 | Question ranking method and computer-readable storage medium |
| CN112115334A (en) * | 2020-09-28 | 2020-12-22 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for distinguishing hot content of network community |
| CN112115334B (en) * | 2020-09-28 | 2023-07-21 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for distinguishing network community hot content |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108804676B (en) | 2022-01-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107423355B (en) | Information recommendation method and device, electronic equipment | |
| TWI582619B (en) | Method and apparatus for providing referral words | |
| WO2013085564A2 (en) | Methods and systems to filter and display electronic messages | |
| EP3061017A1 (en) | Systems and methods for determining influencers in a social data network | |
| EP2635960A1 (en) | Determination of category information using multiple stages | |
| JP2013535747A (en) | Data recommendation method and data recommendation device | |
| CN110020176A (en) | A kind of resource recommendation method, electronic equipment and computer readable storage medium | |
| CN107896153B (en) | Traffic package recommendation method and device based on mobile user internet surfing behavior | |
| CN108259638A (en) | Personal group list intelligent sorting method, intelligent terminal and storage medium | |
| CN108804676A (en) | A kind of model sort method, device, equipment and computer readable storage medium | |
| CN109558384A (en) | Log classification method, device, electronic equipment and storage medium | |
| CN103218368B (en) | A kind of method and apparatus excavating hot word | |
| CN108717469B (en) | Post sorting method, device and equipment and computer readable storage medium | |
| CN111563198B (en) | Material recall method, device, equipment and storage medium | |
| US20160316004A1 (en) | Information processing apparatus, information processing method, and program | |
| CN109819128A (en) | A kind of quality detecting method and device of telephonograph | |
| CN111611786B (en) | Text similarity calculation method and device | |
| CN114780606B (en) | Big data mining method and system | |
| CN104615681B (en) | Text selection method and device | |
| CN104462448B (en) | A kind of packet name classification method and device | |
| CN111090805B (en) | Recommendation index attribution method and device and electronic equipment | |
| CN108804674A (en) | A kind of model sort method, device, equipment and computer readable storage medium | |
| CN116955817A (en) | Content recommendation method, device, electronic equipment and storage medium | |
| US20220292127A1 (en) | Information management system | |
| CN103631832A (en) | Service object ordering method, service object searching method and related device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |