CN107885886A - To the method, apparatus and server of information recommendation sort result - Google Patents
To the method, apparatus and server of information recommendation sort result Download PDFInfo
- Publication number
- CN107885886A CN107885886A CN201711288419.1A CN201711288419A CN107885886A CN 107885886 A CN107885886 A CN 107885886A CN 201711288419 A CN201711288419 A CN 201711288419A CN 107885886 A CN107885886 A CN 107885886A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- information recommendation
- recommendation results
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention proposes a kind of method, apparatus and server to information recommendation sort result, and methods described includes:Information characteristics in Given information recommendation results build the order models for being ranked up to information recommendation result;Information characteristics corresponding with Given information recommendation results in sequencing information are treated in acquisition;According to the described information feature treated in sequencing information, treat that sequencing information is ranked up to described using the order models, the information recommendation result after sequence is then sent to user.A technical scheme in above-mentioned technical proposal has the following advantages that or beneficial effect:According to the information characteristics included in Given information recommendation results, the order models for being ranked up to information recommendation result are built, various dimensions information characteristics can be increased, and the combination between feature, reduce feature complexity, by rational feature calculation, substantially increase sequence performance.
Description
Technical field
The present invention relates to technical field of information processing, more particularly to a kind of method, apparatus to information recommendation sort result
And server.
Background technology
Based on the development of big data technology, information flow (FEED) is recommended as the mode for improving Consumer's Experience, extensively should
Used in every field.For example, when user screens commodity by e-commerce platform, commending system can be clear according to the history of user
Look at record, recommend similar commodity for user;Or during user's viewing film, commending system can be that user's recommendation is similar
Film etc..
Generally, commending system is being visited the history access information of user or user to before user's recommendation information
The information asked is analyzed and calculated, and using result of calculation as foundation, the information for meeting user interest is screened from bulk information
As recommendation information.Conventional recommendation method includes the methods of user's portrait method, collaborative filtering method and association rule mining.
The multiple recommendation results obtained by these methods are usually personalized, it is also necessary to enter rearrangement to these recommendation results
Sequence, user is then pushed to again.The regular sequence of traditional method that recommendation results are ranked up and deep learning modeling row
Sequence etc., but correlation of these methods when sorting calculating with user is with reference to not accurate enough.
The content of the invention
The embodiment of the present invention provides a kind of method, apparatus and server to information recommendation sort result, at least to solve
Above technical problem of the prior art.
In a first aspect, the embodiments of the invention provide a kind of method to information recommendation sort result, methods described includes:
Information characteristics in Given information recommendation results build the sequence for being ranked up to information recommendation result
Model;
Information characteristics corresponding with Given information recommendation results in sequencing information are treated in acquisition;
According to the described information feature treated in sequencing information, treat that sequencing information enters to described using the order models
Row sequence, is then sent to user by the information recommendation result after sequence.
With reference in a first aspect, the present invention in the first embodiment of first aspect, according to Given information recommendation results
In information characteristics build order models for being ranked up to information recommendation result, including:
Obtain user's reading conditions in the Given information recommendation results;
According to user's reading conditions determine the information characteristics in the Given information recommendation results characteristic value and
Weights corresponding with the characteristic value;
According to the weights of described information feature, the order models are built.
With reference to the first embodiment of first aspect, the user obtained in the Given information recommendation results reads feelings
Condition, including:
Judge whether user has read the Given information recommendation results;
If so, user's reading value of the Given information recommendation results is then labeled as the first default value;Otherwise, by
Know that user's reading value of information recommendation result is labeled as the second default value.
With reference to the first embodiment of first aspect,
According to user's reading conditions determine the information characteristics in the Given information recommendation results characteristic value and
Weights corresponding with the characteristic value, including:
Extract the information characteristics of the Given information recommendation results;
It is that described information feature is assigned to characteristic value according to user's reading value of the Given information recommendation results;
Initialize the weights of the described information feature in the Given information recommendation results;
According to the initial user reading value of Given information recommendation results described in the characteristic value and the weight computing;
Compare the difference of first default value and the initial user reading value;
If the difference of first default value and the initial user reading value is more than predetermined threshold value, according to the difference
The weights of value adjustment described information feature, and according to the weights after adjustment, build row's model;Otherwise, according to described initial
Weights, build the order models.
Second aspect, the embodiments of the invention provide a kind of device to information recommendation sort result, including:
First structure module, is configured to the information characteristics in Given information recommendation results and builds for information recommendation
As a result the order models being ranked up;
First acquisition module, it is configured to obtain and treats that information corresponding with Given information recommendation results in sequencing information is special
Sign;
Sending module, it is configured to treat the described information feature in sequencing information according to, utilizes the order models pair
It is described to treat that sequencing information is ranked up, the information recommendation result after sequence is then sent to user.
With reference to second aspect, in the first embodiment of second aspect, the structure module includes the present invention:
Second acquisition module, it is configured to obtain user's reading conditions in the Given information recommendation results;
First processing module, it is configured to determine the letter in the Given information recommendation results according to user's reading conditions
Cease the characteristic value of feature and weights corresponding with the characteristic value;
Second structure module, is configured to the weights according to described information feature, builds the order models.
With reference to the first embodiment of second aspect, second acquisition module includes:
Judge module, it is configured to judge whether user has read the Given information recommendation results;
First assignment module, be configured to when user has read the Given information recommendation results, then will be described known
User's reading value of information recommendation result is labeled as the first default value;Or recommend knot when user does not read the Given information
During fruit, user's reading value of Given information recommendation results is labeled as the second default value.
With reference to the first embodiment of second aspect, the first processing module includes:
Extraction module, it is configured to extract the information characteristics of the Given information recommendation results;
Second assignment module, it is described information feature to be configured to according to user's reading value of the Given information recommendation results
It is assigned to characteristic value;
Second processing module, it is configured to initialize the weights of the described information feature in the Given information recommendation results;
Computing module, it is configured to the initial of according to the characteristic value and weight computing Given information recommendation results
User's reading value;
Comparison module, it is configured to the difference of the first default value described in comparison and the initial user reading value;
Adjusting module, if the difference for being configured to first default value and the initial user reading value is more than default threshold
Value, then adjust the weights of described information feature according to the difference, and according to the weights after adjustment, builds row's model;It is no
Then, according to the initial weight, the order models are built.
The third aspect, the embodiment of the present invention provide a kind of server, one or more processors;
Storage device, for storing one or more programs;
When one or more of programs are by one or more of computing devices so that one or more of places
Reason device realizes method as described above.
Fourth aspect, the embodiments of the invention provide a kind of computer-readable recording medium, for storing to information recommendation
Computer software instructions used in the device of sort result, it includes being used to perform in above-mentioned first aspect to information recommendation result
The method of sequence is to the program involved by the device of information recommendation sort result.
A technical scheme in above-mentioned technical proposal has the following advantages that or beneficial effect:Recommend to tie according to Given information
The information characteristics included in fruit, the order models for being ranked up to information recommendation result are built, various dimensions letter can be increased
The combination between feature, and feature is ceased, reduces feature complexity, by rational feature calculation, substantially increases sequence
Performance.
Another technical scheme in above-mentioned technical proposal has the following advantages that or beneficial effect:The statistics of order models is special
Sign, it is possible to achieve daily record on real-time logs stream parsing line, then accumulate the information of each statistical dimension, spy corresponding to off-line calculation
Sign, so most feature calculation can be completed under off-line state, time-consuming smaller in line ordering, when saving sequence
Between.
Above-mentioned general introduction is merely to illustrate that the purpose of book, it is not intended to is limited in any way.Except foregoing description
Schematical aspect, outside embodiment and feature, it is further by reference to accompanying drawing and the following detailed description, the present invention
Aspect, embodiment and feature would is that what is be readily apparent that.
Brief description of the drawings
In the accompanying drawings, unless specified otherwise herein, otherwise represent same or analogous through multiple accompanying drawing identical references
Part or element.What these accompanying drawings were not necessarily to scale.It should be understood that these accompanying drawings depict only according to the present invention
Some disclosed embodiments, and should not serve to limit the scope of the present invention.
Fig. 1 is the flow chart of the method to information recommendation sort result of the embodiment of the present invention one;
Fig. 2 is the schematic diagram of the characteristic Design to information recommendation sort result of the embodiment of the present invention one;
Fig. 3 is the flow chart of the method to information recommendation sort result of the embodiment of the present invention two;
Fig. 4 is the schematic diagram of the device to information recommendation sort result of the embodiment of the present invention three;
Fig. 5 is the schematic diagram of the server of the embodiment of the present invention four.
Embodiment
Hereinafter, some exemplary embodiments are simply just described.As one skilled in the art will recognize that
Like that, without departing from the spirit or scope of the present invention, described embodiment can be changed by various different modes.
Therefore, accompanying drawing and description are considered essentially illustrative rather than restrictive.
Embodiment one
The embodiment of the present invention provides a kind of method to information recommendation sort result.As shown in figure 1, it is the embodiment of the present invention
The method to information recommendation sort result flow chart.The method to information recommendation sort result of the embodiment of the present invention, bag
Include following steps:
S101, the information characteristics in Given information recommendation results are built for being ranked up to information recommendation result
Order models.
In information flow, the information of user is pushed to, for example, news documents, music file and advertising message etc., it is likely that
Because meeting the hobby of user, and opened and check by user, it is also possible to because not meeting the hobby of user, without quilt
User opens.Therefore, the present embodiment collects some actual information for being pushed to user, by these information in specific embodiment
Recommendation results, i.e. Given information recommendation results, as sample, order models are established using deep learning modeling method.
Information characteristics corresponding with Given information recommendation results in sequencing information are treated in S102, acquisition.
Specifically, the present embodiment treats that sequencing information can include the information such as news documents, music file and advertising message.
S103, according to the described information feature treated in sequencing information, wait to sort to described using the order models
Information is ranked up, and the information recommendation result after sequence then is sent into user.
Because in constructed order models, most important is exactly Feature Engineering, therefore to ensure the performance of order models,
The technical scheme of the present embodiment contains the information characteristics of a variety of dimensions.
Information characteristics in wherein described Given information recommendation results include:Content characteristic, user characteristics, degree of correlation feature
And statistical nature.
Specifically, the content characteristic comprises at least:Content quality, content-length, ageing, classification and keyword;Institute
User characteristics is stated to comprise at least:User's keyword preference, class of subscriber preference, age, sex and region;The statistical nature is extremely
Include less:The click of statistical content, show, stay time information, and content and user combination after click, show information.
In addition, the degree of correlation is characterized in matching user characteristics and content characteristic, it is related to content characteristic to obtain user characteristics
Degrees of data.
Wherein, when building order models, a sample is corresponding with a user and an information, can in a sample
With including multiple content characteristics, user characteristics and statistical nature and combinations thereof.It is exemplified below, content and user's group
Cooperate to include following feature for the situation of a sample, the information characteristics of sample 1:User characteristics includes:Location is characterized as
Beijing, sex character are man, and content characteristic includes category feature, is physical culture, and keyword feature is Guoan;The information of sample 2 is special
Sign includes following feature:User characteristics includes:Location is characterized as Beijing, and sex character is man, and content characteristic includes classification
Physical culture is characterized as, keyword feature is Guoan.It is specific as shown in table 1:
Table 1:
As shown in Fig. 2 the schematic diagram of the characteristic Design to information recommendation sort result for the embodiment of the present invention.
A technical scheme in above-mentioned technical proposal has the following advantages that or beneficial effect:Recommend to tie according to Given information
The information characteristics included in fruit, the order models for being ranked up to information recommendation result are built, various dimensions letter can be increased
The combination between feature, and feature is ceased, reduces feature complexity, by rational feature calculation, substantially increases sequence
Performance.
Embodiment two
On the basis of embodiment one, the embodiment of the present invention provides a kind of method to information recommendation sort result.Such as Fig. 3
It is shown, it is the flow chart of the method to information recommendation sort result of the embodiment of the present invention.The embodiment of the present invention pushes away to information
The method for recommending sort result, comprises the following steps:
S301, obtain user's reading conditions in the Given information recommendation results.
Specifically, step S301 includes:A, judges whether user has read the Given information recommendation results, if so,
Step B is then performed, otherwise performs step C;B, then it is pre- user's reading value of the Given information recommendation results to be entered as first
If numerical value;C, user's reading value of Given information recommendation results is entered as the second default value.
Obviously, when information is pushed into user, if user opens the link of the information, checked, illustrate user
This information is interested in, if user is not turned on the link of the information, illustrates that user is little to the information interest.Therefore, may be used
With according to the reading conditions of Given information, to determine which of user and information feature is related, user is to information in other words
Which of feature it is interested.Further, for the ease of more intuitively being drawn a conclusion with the method for quantitative analysis, this implementation pair
User's reading conditions are represented with numerical value, for example, the first default value is 1, the second default value is 0, then the letter that user read
Breath, user's reading value of the information can be labeled as to 1, the user's reading value for the information that user was not read is labeled as 0.
S302, the characteristic value of the information characteristics in the Given information recommendation results is determined according to user's reading conditions
And weights corresponding with the characteristic value.
Specifically, step S302 includes:
D, extract the information characteristics of the Given information recommendation results;
E, it is that described information feature is assigned to characteristic value according to user's reading value of the Given information recommendation results;
F, initialize the weights of the described information feature in the Given information recommendation results;
G, according to the initial user reading value of Given information recommendation results described in the characteristic value and the weight computing;
H, first default value and the difference of the initial user reading value;
I, if the difference of first default value and the initial user reading value is more than predetermined threshold value, according to
Difference adjusts the weights of described information feature, and according to the weights after adjustment, builds row's model;Otherwise, according to described first
Beginning weights, build the order models.
The present embodiment uses normalizing algorithm, when the characteristic value in a sample is by calculating the user's reading value convergence obtained
In actual user's reading value, or it is substantially equal with actual user's reading value when, illustrate that the feature of the sample is related to user's
Degree is higher, then information can preferentially be pushed to user corresponding to the sample.
Wherein, the calculation formula of user's reading value is as follows:
H (x)=w1*x1+w2*x2+……+wn*xn;
Wherein, f (x) represents user's reading value, x1、x2、……xnRepresent the spy of each feature obtained from Given information
Value indicative, w1、w2……wnRepresent the weights of each feature.
For example, it is known that information is certain sports news, then when certain sports news is sent into user, user beats
News links have been opened, have illustrated that the degree of correlation of the sports news and user are higher;It is related to user's in order to analyze the sports news
Degree is, it is necessary to which it is interested to user to analyze which of sports news information characteristics.So, it is necessary to extract the physical culture first
All information characteristics in news, for example, user characteristics is man, in content characteristic, category feature is physical culture, keyword feature
For Guoan.
Wherein, characteristic value can be equal with user's reading value, for example, user clicks the sports news, then the physical culture
Characteristic value in news is entered as 1, i.e. the characteristic value of sex in user characteristics is entered as 1, the classification in content characteristic
Characteristic value is entered as 1, and the characteristic value of keyword is entered as 1;Correspondingly, should if user does not click on the sports news
Each characteristic value in sports news is entered as 0.
In addition, when calculating weights, when initializing weights first, for example, it can be set to weights are 0.5, then by above-mentioned
Formula, which calculates, obtains initial user reading value, such as is also 0.5, and actual user's reading value is 1, predetermined threshold value 0.1, then
Need to increase weights, the user's reading value for making to calculate tends to 1.
S303, according to the weights of described information feature, build the order models.
In traditional FEED recommendation services, to multiple recommendation results, it is necessary to calculate its feature in real time, then call offline
The model of training is ranked up.In the technical program, content characteristic, it can be dispensed into by dictionary routine in service, then online
Read to calculate;User characteristics, because user profile is just as every information, therefore only need to calculate once i.e.
Can;Degree of correlation feature is, it is necessary in line computation user and the cosine similarity of content;Statistical nature, parsed by real-time logs stream
Daily record on line, the information of each statistical dimension, feature corresponding to off-line calculation are then accumulated, then routine is dispensed into the form of dictionary
Online service, it is seen that the most feature calculation of the technical program is all completed in off-line state, in the time-consuming very little of line ordering, is carried
High sequence efficiency.
Embodiment three
The embodiment of the present invention provides a kind of device to information recommendation sort result.As shown in figure 4, it is the embodiment of the present invention
The device to information recommendation sort result schematic diagram.The device to information recommendation sort result of the embodiment of the present invention, bag
Include:
Described device includes:
First structure module 41, is configured to the information characteristics in Given information recommendation results and builds for being pushed away to information
Recommend the order models that result is ranked up;
First acquisition module 42, it is configured to obtain and treats that information corresponding with Given information recommendation results in sequencing information is special
Sign;
Sending module 43, it is configured to treat the described information feature in sequencing information according to, utilizes the order models
Treat that sequencing information is ranked up to described, the information recommendation result after sequence is then sent to user.
Further, the structure module 41 includes:
Second acquisition module 411, it is configured to obtain user's reading conditions in the Given information recommendation results;
First processing module 412, it is configured to be determined in the Given information recommendation results according to user's reading conditions
Information characteristics characteristic value and weights corresponding with the characteristic value;
Second structure module 413, is configured to the weights according to described information feature, builds the order models.
Further, second acquisition module 411 includes:
Judge module (not shown), it is configured to judge whether user has read the Given information recommendation results;
First assignment module (not shown), it is configured to when user has read the Given information recommendation results,
User's reading value of the Given information recommendation results is then labeled as the first default value;Or described in not read as user
When knowing information recommendation result, user's reading value of Given information recommendation results is labeled as the second default value.
Further, the first processing module 412 includes:
Extraction module (not shown), it is configured to extract the information characteristics of the Given information recommendation results;
Second assignment module (not shown), be configured to be according to user's reading value of the Given information recommendation results
Described information feature is assigned to characteristic value;
Second processing module (not shown), it is configured to initialize the described information in the Given information recommendation results
The weights of feature;
Computing module (not shown), it is configured to the Given information according to the characteristic value and the weight computing and pushes away
Recommend the initial user reading value of result;
Comparison module (not shown), it is configured to the first default value described in comparison and the initial user reading value
Difference;
Adjusting module (not shown), it is configured to the difference when first default value and the initial user reading value
When value is more than predetermined threshold value, the weights of described information feature are adjusted according to the difference, and according to the weights after adjustment, build institute
The row's of stating model;Or when the difference of first default value and the initial user reading value is not more than predetermined threshold value, root
According to the initial weight, the order models are built.
The device to information recommendation sort result of the embodiment of the present invention can realize that structure is used for information recommendation result
The order models being ranked up, it is identical with embodiment one to reduce the technique effect of feature complexity, is repeated no more with this.
Example IV
The embodiment of the present invention four provides a kind of information classification equipment, as shown in figure 5, the equipment includes:Memory 51 and place
Device 52 is managed, the internal memory of memory 51 contains the computer program that can be run on the processor 52.Processor 52 performs the computer
The information classification approach in above-described embodiment is realized during program.The quantity of memory 51 and processor 52 can be one or more
It is individual.
The equipment also includes:
Communication interface 53, for being communicated between memory 51 and processor 52 and external equipment.
Memory 51 may include high-speed RAM memory, it is also possible to also including nonvolatile memory (non-volatile
Memory), a for example, at least magnetic disk storage.
If memory 51, processor 52 and the independent realization of communication interface 53, memory 51, processor 52 and communication connect
Mouth 53 can be connected with each other by bus and complete mutual communication.The bus can be industry standard architecture
(ISA, Industry Standard Architecture) bus, external equipment interconnection (PCI, Peripheral
Component) bus or extended industry-standard architecture (EISA, Extended Industry Standard
Component) bus etc..The bus can be divided into address bus, data/address bus, controlling bus etc..For ease of representing, Fig. 5
In only represented with a thick line, it is not intended that an only bus or a type of bus.
Optionally, in specific implementation, if memory 51, processor 52 and communication interface 53 are integrated in chip piece
On, then memory 51, processor 52 and communication interface 53 can complete mutual communication by internal interface.
Embodiment five
The embodiment of the present invention provides a kind of computer-readable recording medium, and it is stored with computer program, and the program is located
Manage any described method in being realized as in the embodiment disclosed in figs. 1-3 when device performs.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment or example of the present invention.Moreover, specific features, structure, material or the feature of description
It can be combined in an appropriate manner in any one or more embodiments or example.In addition, in the case of not conflicting, this
The technical staff in field can be by the different embodiments or example described in this specification and the spy of different embodiments or example
Sign is combined and combined.
In addition, term " first ", " second " are only used for describing purpose, and it is not intended that instruction or hint relative importance
Or the implicit quantity for indicating indicated technical characteristic.Thus, " first " is defined, the feature of " second " can be expressed or hidden
Include at least one this feature containing ground.In the description of the invention, " multiple " are meant that two or more, unless otherwise
It is clearly specific to limit.
Any process or method described otherwise above description in flow chart or herein is construed as, and represents to include
Module, fragment or the portion of the code of the executable instruction of one or more the step of being used to realize specific logical function or process
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system including the system of processor or other can be held from instruction
The system of row system, device or equipment instruction fetch and execute instruction) use, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicate, propagate or pass
Defeated program is for instruction execution system, device or equipment or the dress used with reference to these instruction execution systems, device or equipment
Put.
Computer-readable medium described in the embodiment of the present invention can be that computer-readable signal media or computer can
Read storage medium either the two any combination.The more specifically example of computer-readable recording medium is at least (non-poor
Property list to the greatest extent) including following:Electrical connection section (electronic installation) with one or more wiring, portable computer diskette box (magnetic
Device), random access memory (RAM), read-only storage (ROM), erasable edit read-only storage (EPROM or flash
Memory), fiber device, and portable read-only storage (CDROM).In addition, computer-readable recording medium even can be with
It is that can print the paper or other suitable media of described program thereon, because can be for example by being carried out to paper or other media
Optical scanner, then enter edlin, interpret or handled if necessary with other suitable methods described electronically to obtain
Program, it is then stored in computer storage.
In embodiments of the present invention, computer-readable signal media can be included in a base band or as a carrier wave part
The data-signal of propagation, wherein carrying computer-readable program code.The data-signal of this propagation can use a variety of
Form, including but not limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media is also
Can be any computer-readable medium beyond computer-readable recording medium, the computer-readable medium can send, pass
Broadcast and either transmit for the use of instruction execution system, input method or device or program in connection.Computer can
The program code for reading to include on medium can be transmitted with any appropriate medium, be included but is not limited to:Wirelessly, electric wire, optical cable, penetrate
Frequently (Radio Frequency, RF) etc., or above-mentioned any appropriate combination.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, software that multiple steps or method can be performed in memory and by suitable instruction execution system with storage
Or firmware is realized.If, and in another embodiment, can be with well known in the art for example, realized with hardware
Any one of row technology or their combination are realized:With the logic gates for realizing logic function to data-signal
Discrete logic, have suitable combinational logic gate circuit application specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method carries
Suddenly it is that by program the hardware of correlation can be instructed to complete, described program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing module, can also
That unit is individually physically present, can also two or more units be integrated in a module.Above-mentioned integrated mould
Block can both be realized in the form of hardware, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized in the form of software function module and as independent production marketing or in use, can also be stored in a computer
In readable storage medium storing program for executing.The storage medium can be read-only storage, disk or CD etc..
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, its various change or replacement can be readily occurred in,
These should all be included within the scope of the present invention.Therefore, protection scope of the present invention should be with the guarantor of the claim
Shield scope is defined.
Claims (10)
- A kind of 1. method to information recommendation sort result, it is characterised in that methods described includes:Information characteristics in Given information recommendation results build the order models for being ranked up to information recommendation result;Information characteristics corresponding with Given information recommendation results in sequencing information are treated in acquisition;According to the described information feature treated in sequencing information, treat that sequencing information is arranged to described using the order models Sequence, the information recommendation result after sequence is then sent to user.
- 2. according to the method for claim 1, it is characterised in that the information characteristics structure in Given information recommendation results For the order models being ranked up to information recommendation result, including:Obtain user's reading conditions in the Given information recommendation results;According to user's reading conditions determine the information characteristics in the Given information recommendation results characteristic value and with institute State weights corresponding to characteristic value;According to the weights of described information feature, the order models are built.
- 3. according to the method for claim 2, it is characterised in that the user obtained in the Given information recommendation results reads Situation, including:Judge whether user has read the Given information recommendation results;If so, user's reading value of the Given information recommendation results is then entered as the first default value;Otherwise, by known letter User's reading value of breath recommendation results is entered as the second default value.
- 4. according to the method for claim 3, it is characterised in that determine the Given information according to user's reading conditions The characteristic value of information characteristics in recommendation results and weights corresponding with the characteristic value, including:Extract the information characteristics of the Given information recommendation results;It is that described information feature is assigned to characteristic value according to user's reading value of the Given information recommendation results;Initialize the weights of the described information feature in the Given information recommendation results;According to the initial user reading value of Given information recommendation results described in the characteristic value and the weight computing;Compare the difference of first default value and the initial user reading value;If the difference of first default value and the initial user reading value is more than predetermined threshold value, adjusted according to the difference The weights of whole described information feature, and according to the weights after adjustment, build row's model;Otherwise, according to the initial weight, Build the order models.
- 5. a kind of device to information recommendation sort result, it is characterised in that described device includes:First structure module, is configured to the information characteristics in Given information recommendation results and builds for information recommendation result The order models being ranked up;First acquisition module, it is configured to obtain and treats information characteristics corresponding with Given information recommendation results in sequencing information;Sending module, it is configured to treat the described information feature in sequencing information according to, using the order models to described Treat that sequencing information is ranked up, the information recommendation result after sequence is then sent to user.
- 6. device according to claim 5, it is characterised in that the structure module includes:Second acquisition module, it is configured to obtain user's reading conditions in the Given information recommendation results;First processing module, it is configured to determine that the information in the Given information recommendation results is special according to user's reading conditions The characteristic value of sign and weights corresponding with the characteristic value;Second structure module, is configured to the weights according to described information feature, builds the order models.
- 7. device according to claim 6, it is characterised in that second acquisition module includes:Judge module, it is configured to judge whether user has read the Given information recommendation results;First assignment module, it is configured to when user has read the Given information recommendation results, then by the Given information User's reading value of recommendation results is labeled as the first default value;Or when user does not read the Given information recommendation results When, user's reading value of Given information recommendation results is labeled as the second default value.
- 8. device according to claim 6, it is characterised in that the first processing module includes:Extraction module, it is configured to extract the information characteristics of the Given information recommendation results;Second assignment module, it is that described information feature is assigned to be configured to according to user's reading value of the Given information recommendation results Characteristic value;Second processing module, it is configured to initialize the weights of the described information feature in the Given information recommendation results;Computing module, it is configured to the initial user of the Given information recommendation results according to the characteristic value and the weight computing Reading value;Comparison module, it is configured to the difference of the first default value described in comparison and the initial user reading value;Adjusting module, it is configured to when the difference of first default value and the initial user reading value is more than predetermined threshold value When, the weights of described information feature are adjusted according to the difference, and according to the weights after adjustment, build row's model;Or When the difference of first default value and the initial user reading value is not more than predetermined threshold value, according to the initial power Value, builds the order models.
- 9. a kind of server, it is characterised in that the server includes:One or more processors;Storage device, for storing one or more programs;When one or more of programs are by one or more of computing devices so that one or more of processors Realize the method as described in any in claim 1-4.
- 10. a kind of computer-readable recording medium, it is stored with computer program, it is characterised in that the program is held by processor The method as described in any in claim 1-4 is realized during row.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711288419.1A CN107885886A (en) | 2017-12-07 | 2017-12-07 | To the method, apparatus and server of information recommendation sort result |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711288419.1A CN107885886A (en) | 2017-12-07 | 2017-12-07 | To the method, apparatus and server of information recommendation sort result |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107885886A true CN107885886A (en) | 2018-04-06 |
Family
ID=61773076
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711288419.1A Pending CN107885886A (en) | 2017-12-07 | 2017-12-07 | To the method, apparatus and server of information recommendation sort result |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107885886A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108763318A (en) * | 2018-04-27 | 2018-11-06 | 达而观信息科技(上海)有限公司 | item recommendation method and device |
CN109543132A (en) * | 2018-11-22 | 2019-03-29 | 深圳墨世科技有限公司 | Content recommendation method, device, electronic equipment and storage medium |
CN109597941A (en) * | 2018-12-12 | 2019-04-09 | 拉扎斯网络科技(上海)有限公司 | Sort method and device, electronic equipment and storage medium |
CN110134348A (en) * | 2019-05-15 | 2019-08-16 | 宜春宜联科技有限公司 | Print resource matching process, apparatus and system |
CN111159341A (en) * | 2019-12-25 | 2020-05-15 | 中国建设银行股份有限公司 | Information recommendation method and device based on user investment and financing preference |
CN111368190A (en) * | 2020-02-28 | 2020-07-03 | 北京百度网讯科技有限公司 | Information recommendation method and device |
CN112231593A (en) * | 2020-12-15 | 2021-01-15 | 上海朝阳永续信息技术股份有限公司 | Financial information intelligent recommendation system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103778260A (en) * | 2014-03-03 | 2014-05-07 | 哈尔滨工业大学 | Individualized microblog information recommending system and method |
CN103942279A (en) * | 2014-04-01 | 2014-07-23 | 百度(中国)有限公司 | Method and device for showing search result |
CN104036038A (en) * | 2014-06-30 | 2014-09-10 | 北京奇虎科技有限公司 | News recommendation method and system |
-
2017
- 2017-12-07 CN CN201711288419.1A patent/CN107885886A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103778260A (en) * | 2014-03-03 | 2014-05-07 | 哈尔滨工业大学 | Individualized microblog information recommending system and method |
CN103942279A (en) * | 2014-04-01 | 2014-07-23 | 百度(中国)有限公司 | Method and device for showing search result |
CN104036038A (en) * | 2014-06-30 | 2014-09-10 | 北京奇虎科技有限公司 | News recommendation method and system |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108763318A (en) * | 2018-04-27 | 2018-11-06 | 达而观信息科技(上海)有限公司 | item recommendation method and device |
CN108763318B (en) * | 2018-04-27 | 2022-04-19 | 达而观信息科技(上海)有限公司 | Item recommendation method and device |
CN109543132A (en) * | 2018-11-22 | 2019-03-29 | 深圳墨世科技有限公司 | Content recommendation method, device, electronic equipment and storage medium |
CN109597941A (en) * | 2018-12-12 | 2019-04-09 | 拉扎斯网络科技(上海)有限公司 | Sort method and device, electronic equipment and storage medium |
CN109597941B (en) * | 2018-12-12 | 2021-04-27 | 拉扎斯网络科技(上海)有限公司 | Sorting method and device, electronic equipment and storage medium |
CN110134348A (en) * | 2019-05-15 | 2019-08-16 | 宜春宜联科技有限公司 | Print resource matching process, apparatus and system |
CN111159341A (en) * | 2019-12-25 | 2020-05-15 | 中国建设银行股份有限公司 | Information recommendation method and device based on user investment and financing preference |
CN111159341B (en) * | 2019-12-25 | 2023-04-14 | 中国建设银行股份有限公司 | Information recommendation method and device based on user investment and financial management preference |
CN111368190A (en) * | 2020-02-28 | 2020-07-03 | 北京百度网讯科技有限公司 | Information recommendation method and device |
CN111368190B (en) * | 2020-02-28 | 2023-08-15 | 北京百度网讯科技有限公司 | Information recommendation method and device |
CN112231593A (en) * | 2020-12-15 | 2021-01-15 | 上海朝阳永续信息技术股份有限公司 | Financial information intelligent recommendation system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107885886A (en) | To the method, apparatus and server of information recommendation sort result | |
US20230237328A1 (en) | Information processing method and terminal, and computer storage medium | |
CN103914550B (en) | Show the method and apparatus of content recommendation | |
CN108182279A (en) | Object classification method, device and computer equipment based on text feature | |
CN108427708B (en) | Data processing method, data processing apparatus, storage medium, and electronic apparatus | |
CN112395489B (en) | Recommendation method, recommendation device, recommendation equipment and computer storage medium | |
US20140074831A1 (en) | Determination of category information using multiple stages | |
US9875294B2 (en) | Method and apparatus for classifying object based on social networking service, and storage medium | |
CN107256267A (en) | Querying method and device | |
CN107133221A (en) | Signal auditing method, device, computer-readable medium and electronic equipment | |
CN104866969A (en) | Personal credit data processing method and device | |
CN113254804B (en) | Social relationship recommendation method and system based on user attributes and behavior characteristics | |
CN110428277B (en) | Touch method of recommended product, storage medium and program product | |
CN106339507A (en) | Method and device for pushing streaming media message | |
CN109582788A (en) | Comment spam training, recognition methods, device, equipment and readable storage medium storing program for executing | |
CN107918778A (en) | A kind of information matching method and relevant apparatus | |
CN107977678A (en) | Method and apparatus for output information | |
CN109961311A (en) | Lead referral method, apparatus calculates equipment and storage medium | |
CN110825974B (en) | Recommendation system content ordering method and device | |
CN111104590A (en) | Information recommendation method, device, medium and electronic equipment | |
CN116137004B (en) | Attribution method, attribution system and attribution computer for advertisement putting effect | |
CN107562881A (en) | Interference method, medium, system and the computing device of commending system | |
CN107463853A (en) | The method and system of audient's label analysis | |
CN107729708A (en) | A kind of traffic policy recommends method and device | |
CN112256844A (en) | Text classification method and 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180406 |
|
RJ01 | Rejection of invention patent application after publication |