CN107944956A - Method and apparatus for generating information - Google Patents
Method and apparatus for generating information Download PDFInfo
- Publication number
- CN107944956A CN107944956A CN201711157033.7A CN201711157033A CN107944956A CN 107944956 A CN107944956 A CN 107944956A CN 201711157033 A CN201711157033 A CN 201711157033A CN 107944956 A CN107944956 A CN 107944956A
- Authority
- CN
- China
- Prior art keywords
- item information
- value
- user
- recommended
- sampling
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
Abstract
The embodiment of the present application discloses the method and apparatus for generating information.One embodiment of this method includes:Obtain the historical record of targeted customer, and the history Item Information that definite historical record includes;The definite and matched Item Information set to be recommended of history Item Information, wherein, the correlation degree value of Item Information to be recommended between any two in Item Information set to be recommended is more than the first correlation degree threshold value;From Item Information set to be recommended, the Item Information to be recommended that the second correlation degree threshold value is more than with the correlation degree value of history Item Information is determined as recommending Item Information;Generation includes recommending the recommendation information of Item Information.This embodiment improves the specific aim of generation recommendation information.
Description
Technical field
The invention relates to field of computer technology, and in particular to Internet technical field, it is more particularly, to raw
Into the method and apparatus of information.
Background technology
Proposed algorithm is a kind of algorithm in computer major, passes through some mathematical algorithms, thus it is speculated that goes out user and may like
Thing, current proposed algorithm is widely used in internet arena.So-called proposed algorithm is exactly some rows using user
To pass through some mathematical algorithms, thus it is speculated that go out the thing that user may like.Existing proposed algorithm mainly includes:Based on content
Information recommendation algorithm, the proposed algorithm based on collaborative filtering, the proposed algorithm based on correlation rule, recommendation based on effectiveness calculate
Method, Knowledge based engineering proposed algorithm etc..The accuracy of existing various proposed algorithms is further improved, is those skilled in the art
The direction of research.
The content of the invention
The embodiment of the present application proposes the method and apparatus for generating information.
In a first aspect, the embodiment of the present application provides a kind of method for generating information, this method includes:Obtain target
The historical record of user, and the history Item Information that definite historical record includes;Determine and history Item Information is matched treats
Recommend article information aggregate, wherein, the correlation degree of Item Information to be recommended between any two in Item Information set to be recommended
Value is more than the first correlation degree threshold value;, will be big with the correlation degree value of history Item Information from Item Information set to be recommended
It is determined as recommending Item Information in the Item Information to be recommended of the second correlation degree threshold value;Generation includes recommending pushing away for Item Information
Recommend information.
In certain embodiments, correlation degree value determines as follows:Sampling Item Information set is obtained, wherein,
Sampling Item Information set includes Item Information to be recommended;For each sampling Item Information in sampling Item Information set,
Usage record value of the corresponding at least one sampling user of the sampling Item Information in preset time period is obtained, wherein, use
Record value is the numerical value that records of sampling article progress predetermined registration operation in response to sampling user for sampling Item Information characterization;
Determine to meet that the target of preset condition samples user from the corresponding at least one sampling user of the sampling Item Information;To target
The usage record value of sampling user is counted, and obtains the statistic record value of target sampling user;To obtained statistic record
Value is normalized, and obtains the preference value that target sampling user corresponds to the Item Information to be recommended;Based on obtained
Preference value and Item Information set to be recommended, obtain Item Information to be recommended in Item Information set to be recommended between any two
Correlation degree value.
In certain embodiments, preset condition includes at least one of following:Sample the fluctuation model of the usage record value of user
It is trapped among in fluctuation range threshold value, the user name for sampling user is not belonging to default user name set.
In certain embodiments, the usage record value of target sampling user is counted, obtains target sampling user's
Statistic record value, including:Sum, obtain each to usage record value of the target sampling user in each default measurement period
Statistic record value in default measurement period, wherein, the duration for presetting measurement period is less than or equal to the duration of preset time period;It is right
Each statistic record value summation, obtains the statistic record value of target sampling user.
In certain embodiments, obtained statistic record value is normalized, obtains target sampling user couple
Should in the preference value of the Item Information to be recommended, including:By the statistic record value of target sampling user and maximum usage record
The ratio of the statistic record value of value user is determined as the preference value that target sampling user corresponds to the Item Information to be recommended, its
In, maximum usage record value user is in the corresponding each target sampling user of the Item Information to be recommended, statistic record value
Maximum user.
Second aspect, the embodiment of the present application provide a kind of device for being used to generate information, which includes:First determines
Unit, is configured to obtain the historical record of targeted customer, and the history Item Information that definite historical record includes;Second is true
Order member, is configured to the definite and matched Item Information set to be recommended of history Item Information, wherein, Item Information to be recommended
The correlation degree value of Item Information to be recommended between any two in set is more than the first correlation degree threshold value;3rd determination unit,
It is configured to from Item Information set to be recommended, the second correlation degree threshold will be more than with the correlation degree value of history Item Information
The Item Information to be recommended of value is determined as recommending Item Information;Generation unit, being configured to generation includes recommending Item Information
Recommendation information.
In certain embodiments, which further includes:Acquiring unit, is configured to obtain sampling Item Information set, its
In, sampling Item Information set includes Item Information to be recommended;4th determination unit, is configured to for sampling Item Information collection
Each sampling Item Information in conjunction, obtains the corresponding at least one sampling user of the sampling Item Information in preset time period
Usage record value, wherein, usage record value be in response to sampling user for sampling Item Information characterization sampling article into
Row predetermined registration operation and the numerical value recorded;Determine to meet default bar from the corresponding at least one sampling user of the sampling Item Information
The target sampling user of part;The usage record value of target sampling user is counted, obtains the statistics note of target sampling user
Record value;Obtained statistic record value is normalized, target sampling user is obtained and corresponds to the article letter to be recommended
The preference value of breath;5th determination unit, is configured to be based on obtained preference value and Item Information set to be recommended, is treated
Recommend the correlation degree value of Item Information to be recommended between any two in article information aggregate.
In certain embodiments, preset condition includes at least one of following:Sample the fluctuation model of the usage record value of user
It is trapped among in fluctuation range threshold value, the user name for sampling user is not belonging to default user name set.
In certain embodiments, the 4th determination unit includes:First computing module, is configured to sample user to the target
Usage record value summation in each default measurement period, obtains the statistic record value in each default measurement period, wherein,
The duration of default measurement period is less than or equal to the duration of preset time period;Second computing module, is configured to each statistics note
Record value is summed, and obtains the statistic record value of target sampling user.
In certain embodiments, the 4th determination unit is further configured to:By the statistic record of target sampling user
The ratio of value and the statistic record value of maximum usage record value user is determined as target sampling user and corresponds to the article to be recommended
The preference value of information, wherein, maximum usage record value user is the corresponding each target sampling user of the Item Information to be recommended
In, the user of statistic record value maximum.
The third aspect, the embodiment of the present application provide a kind of server, which includes:One or more processors;
Storage device, for storing one or more programs;When one or more programs are executed by one or more processors so that one
A or multiple processors realize the method as described in any implementation in first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer-readable recording medium, are stored thereon with computer journey
Sequence, realizes the method as described in any implementation in first aspect when which is executed by processor.
Method and apparatus provided by the embodiments of the present application for generating information, by the history article for obtaining targeted customer
Information, determines Item Information set to be recommended, wherein, the Item Information to be recommended in Item Information set to be recommended is between any two
Correlation degree value be more than default first correlation degree threshold value, then extract correlation degree from Item Information set to be recommended
Value is finally based on more than the recommendation Item Information of the second correlation degree threshold value and recommends Item Information generation recommendation information.So as to carry
The high specific aim of generation recommendation information.
Brief description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that this application can be applied to exemplary system architecture figure therein;
Fig. 2 is the flow chart for being used to generate one embodiment of the method for information according to the application;
Fig. 3 is the schematic diagram for being used to generate an application scenarios of the method for information according to the application;
Fig. 4 is the structure diagram for being used to generate one embodiment of the device of information according to the application;
Fig. 5 is adapted for the structure diagram of the computer system of the server for realizing the embodiment of the present application.
Embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
It illustrate only easy to describe, in attached drawing and invent relevant part with related.
It should be noted that in the case where there is no conflict, the feature in embodiment and embodiment in the application can phase
Mutually combination.Describe the application in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 shows the method for being used to generate information that can apply the application or the implementation of the device for generating information
The exemplary system architecture 100 of example.
As shown in Figure 1, system architecture 100 can include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 provide communication link medium.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be interacted with using terminal equipment 101,102,103 by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications can be installed, such as web browser should on terminal device 101,102,103
With, shopping class application, searching class application, instant messaging tools, mailbox client, social platform software etc..
Terminal device 101,102,103 can have a display screen and a various electronic equipments that supported web page browses, bag
Include but be not limited to smart mobile phone, tablet computer, E-book reader, MP3 player (Moving Picture Experts
Group Audio Layer III, dynamic image expert's compression standard audio aspect 3), MP4 (Moving Picture
Experts Group Audio Layer IV, dynamic image expert's compression standard audio aspect 4) it is player, on knee portable
Computer and desktop computer etc..
Server 105 can be to provide the server of various services, for example, the historical record of user is analyzed and
The background information processing server of recommendation information is sent to the terminal device 101,102,103 of user.Background information processing service
Device can carry out the historical record of the user got analyzing etc. processing, and by handling result (such as recommendation information of generation)
Feed back to terminal device.
It should be noted that the method for being used to generate information that the embodiment of the present application is provided generally is held by server 105
OK, correspondingly, it is generally positioned at for generating the device of information in server 105.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realizing need
Will, can have any number of terminal device, network and server.
With continued reference to Fig. 2, the flow for being used to generate one embodiment of the method for information according to the application is shown
200.This is used for the method for generating information, comprises the following steps:
Step 201, the historical record of targeted customer, and the history Item Information that definite historical record includes are obtained.
In the present embodiment, electronic equipment (such as the service shown in Fig. 1 thereon is run for generating the method for information
Device) can by wired connection mode either radio connection from the terminal of targeted customer or from local or from other clothes
Business device obtains the historical record of targeted customer, and the history Item Information that definite historical record includes.Wherein, historical record is
For the information for recording some operations that user carried out and producing.Historical record can include history Item Information, can be with
Including operated with history Item Information correlation time information (such as user browse history Item Information time, purchase
Time of history Item Information etc.), for history Item Information characterization the relevant quantity information of article (such as quantity purchase)
Etc. other information.
Above-mentioned history Item Information is that the Item Information contacted was produced with targeted customer, for example, targeted customer is browsed
Item Information or the corresponding Item Information of article that obtained of targeted customer.Above-mentioned targeted customer can be it is pre-set certain
A user list or user in some user set or meet some conditions (such as browsed default article letter
Breath set in Item Information, or obtained corresponding article of default Item Information etc.) user.
Step 202, determine and the matched Item Information set to be recommended of history Item Information.
In the present embodiment, it can determine and go through based on the history Item Information obtained in step 201, above-mentioned electronic equipment
The matched Item Information set to be recommended of history Item Information.Wherein, Item Information to be recommended is that have to close with history Item Information
The Item Information of connection relation, also, history Item Information can be Item Information to be recommended, may not be article letter to be recommended
Breath.As an example, above-mentioned incidence relation can be presented as category associations or function association, wherein, category associations can refer to
The article that Item Information to be recommended is characterized and the article of history Item Information characterization belong to the same or similar classification, and function is closed
It is the same or similar that connection can refer to that the Item Information to be recommended article characterized and the article that history Item Information characterizes have
Function.
Above-mentioned electronic equipment can be determined according to the correlation degree value between history Item Information and other Item Information
With the matched Item Information set to be recommended of history Item Information.Above-mentioned electronic equipment can be from default Item Information set
Correlation degree value between any two is more than to the Item Information and each Item Information and history thing of the first correlation degree threshold value
Correlation degree value between product information is determined as Item Information to be recommended also greater than the Item Information of the first correlation degree threshold value.
It should be appreciated that the corresponding article of above-mentioned Item Information to be recommended can be physical item or virtual objects
(such as the data traffic of charging, various online services etc.).
Above-mentioned correlation degree value can be the numerical value for characterizing the correlation degree between two articles to be recommended.In general,
Above-mentioned correlation degree value can be the similarity value between Item Information, and similarity value (i.e. correlation degree value) is bigger, then associates
Degree is higher.What similarity can be calculated based on various algorithms, for example, similar based on cosine (Cosine-based)
Degree, the similarity based on association (Correlation-based) etc..
Above-mentioned electronic equipment can utilize various proposed algorithms, calculate the correlation degree between two Item Information to be recommended
Value, above-mentioned proposed algorithm can include but is not limited to following at least one:Content-based recommendation algorithm, collaborative filtering recommending are calculated
Method, Knowledge based engineering proposed algorithm etc..
In some optional implementations of the present embodiment, above-mentioned electronic equipment can be determined using collaborative filtering
Correlation degree value between two Item Information to be recommended.Above-mentioned correlation degree value can determine as follows:
First, above-mentioned electronic equipment can obtain sampling Item Information set.Wherein, sampling Item Information set includes treating
Recommend Item Information.Here, Item Information to be recommended can be more than or equal to by sampling the quantity of Item Information, and article to be recommended is believed
Breath is sampling Item Information in itself, namely samples Item Information set and include Item Information set to be recommended.Above-mentioned sampling article
Information can be stored in the Item Information of above-mentioned electronic equipment or the Item Information obtained from other electronic equipments.
Secondly, this can be obtained for each sampling Item Information in sampling Item Information set, above-mentioned electronic equipment
The corresponding at least one sampling user of sampling Item Information (such as browses the user of over sampling Item Information or gets sampling thing
The user of the corresponding article of product information) usage record value in preset time period (such as half a year);From the sampling Item Information
The target sampling user for meeting preset condition is determined in corresponding at least one sampling user;Use to target sampling user is remembered
Record value is counted, and obtains the statistic record value of target sampling user;Obtained statistic record value is normalized,
Obtain the preference value that target sampling user corresponds to the Item Information to be recommended.
Wherein, above-mentioned usage record value is to be carried out in response to sampling user for the sampling article of sampling Item Information characterization
Predetermined registration operation (such as buy, browse etc. operation) and the numerical value (such as expense, number of visits etc.) recorded.
Finally, based on obtained preference value and sampling Item Information set, taking in sampling Item Information set is obtained
The correlation degree value of sample Item Information between any two.
Above-mentioned electronic equipment it is inclined can to establish user according to the preference value and sampling Item Information set of each sampling user
Good matrix, is then based on user preference matrix, using collaborative filtering, obtains the sampling article in sampling Item Information set
The correlation degree value of information between any two.
It should be noted that above-mentioned obtain the method for correlation degree value based on user preference matrix using collaborative filtering
It is widely studied at present and application known technology, details are not described herein.
In some optional implementations of the present embodiment, above-mentioned preset condition can include at least one of following:Take
For the fluctuation range of the usage record value of sample user in fluctuation range threshold value, the user name for sampling user is not belonging to default user
Name set.
Exemplary, in above-mentioned electronic equipment, default fluctuation range threshold value can include upper limit threshold and lower limit threshold
Value, in above-mentioned at least one sampling user, sampling user of the usage record value in upper limit threshold with lower threshold is determined
User is sampled for target.In above-mentioned electronic equipment, the user name pair in being gathered with pre-set user name set, the user's name
The sampling user answered can be tested user or exclude sending the other users outside the user of recommendation information.Above-mentioned electronics is set
The standby corresponding sampling user of user name that can be will not belong to beyond above-mentioned user name set is determined as target sampling user.
In some optional implementations of the present embodiment, above-mentioned electronic equipment can obtain target in accordance with the following steps
Sample the statistic record value of user:Firstly, for each sampling Item Information in sampling Item Information set, above-mentioned electronics is set
It is standby to sum to usage record value of the target sampling user in each default measurement period, obtain in each default measurement period
Statistic record value.Wherein, the duration for presetting measurement period is less than or equal to the duration of preset time period.
Alternatively, for each sampling Item Information in above-mentioned sampling Item Information set, above-mentioned electronic equipment can be with
The record period of the usage record value of the corresponding target sampling user of the sampling Item Information is determined first.Then, above-mentioned electronics
Equipment can be in response to determining that above-mentioned record period is at least two, then for each in above-mentioned at least two record period
The usage record value of the corresponding target sampling user of the record period can be summed, obtained by record period, above-mentioned electronic equipment
The statistic record value of the corresponding target sampling user of the record period.
As an example, being directed to same sampling article, the usage record value of some target sampling users is monthly to count and remember
Record, have plenty of what is counted and record by minute.In order to carry out preference value calculating when, so as to get preference value can reflect
The preference of article of the different user in same measurement period, above-mentioned electronic equipment, which will can be calculated needed for preference value, to be made
With the unit of record value (such as user paid in one month expense) be unified for by default measurement period (such as:Month) system
Meter.Then, above-mentioned electronic equipment remembers use of the target for monthly counting and the recording sampling user in default measurement period
Record value is counted, and obtains the first statistic record value, and the target for counting and recording by minute is sampled user in default statistics
Usage record value in cycle is counted, and obtains the second statistic record value.Unite for above-mentioned first statistic record value and second
Record value is counted, continues to execute following step.
Secondly, above-mentioned electronic equipment can sum each statistic record value, obtain target sampling user above-mentioned default
Statistic record value in period.
In some optional implementations of the present embodiment, above-mentioned electronic equipment can be in accordance with the following steps to resulting
Statistic record value be normalized:The target can be sampled the statistic record value and maximum of user by above-mentioned electronic equipment
The ratio of the statistic record value of usage record value user is determined as target sampling user and corresponds to the inclined of the Item Information to be recommended
Good value.Wherein, maximum usage record value user is in the corresponding each target sampling user of single Item Information to be recommended, unites
Count the user of record value maximum.After normalized, obtained preference value is between 0-1.
It is exemplary, it is assumed that in the corresponding each target sampling user of an Item Information to be recommended, maximum usage record
The usage record value for being worth user is 10000, and the usage record value of target sampling user is 3000, then target sampling user corresponds to
In the Item Information to be recommended preference value be 0.3
Step 203, from Item Information set to be recommended, closed being more than second with the correlation degree value of history Item Information
The Item Information to be recommended of connection degree threshold value is determined as recommending Item Information.
In the present embodiment, above-mentioned electronic equipment can preset the second correlation degree threshold value.Wherein, history Item Information with
Correlation degree threshold value between article to be recommended is more than the second correlation degree threshold value, represents history Item Information and article to be recommended
Between correlation degree it is larger, the possibility that user produces the Item Information to be recommended corresponding article interest is larger.
Exemplary, Item Information set to be recommended includes Item Information A to be recommended, Item Information B to be recommended, to be recommended
Item Information C, the history Item Information correlation degree value between Item Information A to be recommended and Item Information B to be recommended respectively
More than the second correlation degree threshold value, the correlation degree value between history Item Information and Item Information C to be recommended is less than second and closes
Connection degree threshold value, it is determined that Item Information A to be recommended and Item Information B to be recommended is recommendation Item Information.
Step 204, based on recommendation Item Information generation recommendation information.
In the present embodiment, the recommendation Item Information obtained based on step 203, above-mentioned electronic equipment can generate recommendation
Breath.Wherein, recommendation information can include recommending Item Information, can also include other with recommending other relevant letters of Item Information
Breath.For example, above-mentioned electronic equipment can will recommend Item Information and for the corresponding article word of recommendation Item Information, picture etc.
Information together adds recommendation information.
In some optional implementations of the present embodiment, above-mentioned electronic equipment can be further by the recommendation of generation
Breath is sent to terminal used in targeted customer.
With continued reference to Fig. 3, Fig. 3 is the signal for being used to generate the application scenarios of the method for information according to the present embodiment
Figure.
In the application scenarios of Fig. 3, targeted customer Zhang San had rented Cloud Server within past one month, at backend information
Reason server 301 obtains the purchaser record of Zhang San first, and Cloud Server information 303 has been extracted from the purchaser record.Its
Secondary, backend information processing server 301 determines that what is be stored therein includes the Item Information collection to be recommended of Cloud Server information 303
304 are closed, wherein, Item Information set 304 to be recommended includes Cloud Server information A, cloud storage product information B and outer net bandwidth is produced
Product information C, and the correlation degree value of the Item Information to be recommended in Item Information set 304 to be recommended between any two is more than the
One correlation degree threshold value (such as 0.3).Above-mentioned correlation degree value is to be in advance based on the purchase that multiple sampling users are directed to multiple articles
Expense is bought, and determined using collaborative filtering.Then, backend information processing server 301 contrasts Cloud Server letter
Whether the correlation degree value between breath 303 and other Item Information to be recommended is more than the second correlation degree threshold value (such as 0.5), after
Client information processing server 301 determines the correlation degree value between outer net bandwidth product information C and Cloud Server information 303
(0.7) it is more than the second correlation degree threshold value.Then, backend information processing server 301 is generated based on outer net bandwidth product information C
Recommendation information 305.Finally, backend information processing server 301 sends recommendation information 305 to terminal used in targeted customer
302, terminal 302 shows the recommendation information 305 after receiving recommendation information 305.
The method that above-described embodiment of the application provides is determined to be recommended by obtaining the history Item Information of targeted customer
Item Information set, then Item Information is recommended in extraction from Item Information set to be recommended, is finally based on recommendation Item Information
Generate recommendation information.Improve the specific aim of recommendation information.
With further reference to Fig. 4, as the realization to method shown in above-mentioned each figure, it is used to generate letter this application provides one kind
One embodiment of the device of breath, the device embodiment is corresponding with the embodiment of the method shown in Fig. 2, which can specifically answer
For in various electronic equipments.
As shown in figure 4, the device 400 for being used to generate information of the present embodiment includes:First determination unit 401, configuration are used
In the historical record for obtaining targeted customer, and the history Item Information that definite historical record includes;Second determination unit 402,
The definite and matched Item Information set to be recommended of history Item Information is configured to, wherein, in Item Information set to be recommended
Item Information to be recommended correlation degree value between any two be more than the first correlation degree threshold value;3rd determination unit 403, configuration
For from Item Information set to be recommended, the second correlation degree threshold value will to be more than with the correlation degree value of history Item Information
Item Information to be recommended is determined as recommending Item Information;Generation unit 404, being configured to generation includes recommending pushing away for Item Information
Recommend information.
In the present embodiment, above-mentioned first determination unit 401 can from the terminal of targeted customer either from it is local or from
Other servers obtain the historical record of targeted customer, and the history Item Information that definite historical record includes.Wherein, history
Record is the information for recording some operations that user carried out and producing.Historical record can include history Item Information,
Can also include for history Item Information operate relevant temporal information (such as user browse history Item Information when
Between, time of purchasing history Item Information etc.), (such as purchase for the relevant quantity information of article of history Item Information characterization
Buy quantity) etc. other information.Above-mentioned history Item Information is that the Item Information contacted was produced with targeted customer.Above-mentioned target is used
Family can be some pre-set user list or some user set in user or meet some condition (examples
Item Information in such as browsed default Item Information set, or obtained corresponding article of default Item Information etc.)
User.
In the present embodiment, above-mentioned second determination unit 402 can determine and the matched thing to be recommended of history Item Information
Product information aggregate.Wherein, Item Information to be recommended is the Item Information for having incidence relation with history Item Information, also, is gone through
History Item Information can be in itself Item Information to be recommended, may not be Item Information to be recommended.Above-mentioned second determination unit
402 can determine to match with history Item Information according to the correlation degree value between history Item Information and other Item Information
Item Information set to be recommended.The association journey of Item Information to be recommended between any two in above-mentioned Item Information set to be recommended
Angle value should be more than the first correlation degree threshold value, and each associate journey between Item Information to be recommended and history Item Information
Angle value should also be as being more than the first correlation degree threshold value.
Above-mentioned correlation degree value can be the numerical value for characterizing the correlation degree between two articles to be recommended.In general,
Above-mentioned correlation degree value can be the similarity value between Item Information, and similarity value (i.e. correlation degree value) is bigger, then associates
Degree is higher.What similarity can be calculated based on various algorithms, for example, similar based on cosine (Cosine-based)
Degree, the similarity based on association (Correlation-based) etc..
In some optional implementations of the present embodiment, the above-mentioned device 400 for being used to generate information can also include
Acquiring unit (not shown), is configured to obtain sampling Item Information set, wherein, sampling Item Information set includes treating
Recommend Item Information;4th determination unit (not shown), is configured to for each taking in sampling Item Information set
Sample Item Information, obtains usage record of the corresponding at least one sampling user of the sampling Item Information in preset time period
Value, wherein, usage record value is to carry out predetermined registration operation for the sampling article of sampling Item Information characterization in response to sampling user
And the numerical value recorded;Determine to meet that the target of preset condition takes from the corresponding at least one sampling user of the sampling Item Information
Sample user;The usage record value of target sampling user is counted, obtains the statistic record value of target sampling user;To gained
To statistic record value be normalized, obtain target sampling user correspond to the Item Information to be recommended preference value;
5th determination unit (not shown), is configured to be based on obtained preference value and Item Information set to be recommended, obtains
The correlation degree value of Item Information to be recommended between any two in Item Information set to be recommended.
In some optional implementations of the present embodiment, above-mentioned preset condition can include at least one of following:Take
For the fluctuation range of the usage record value of sample user in fluctuation range threshold value, the user name for sampling user is not belonging to default user
Name set.
In some optional implementations of the present embodiment, above-mentioned 4th determination unit can obtain in accordance with the following steps
Target samples the statistic record value of user:Firstly, for each sampling Item Information in sampling Item Information set, above-mentioned electricity
Sub- equipment sums usage record value of the target sampling user in each default measurement period, obtains each default statistics week
Statistic record value in phase.Wherein, the duration for presetting measurement period is less than or equal to the duration of preset time period.Secondly, above-mentioned electricity
Sub- equipment can sum each statistic record value, obtain statistic record of the target sampling user in above-mentioned preset time period
Value.
In some optional implementations of the present embodiment, which can be sampled user by above-mentioned 4th determination unit
Statistic record value and the statistic record value of maximum usage record value user ratio be determined as that target sampling user corresponds to should
The preference value of Item Information to be recommended.Wherein, maximum usage record value user is that single Item Information to be recommended is corresponding each
In target sampling user, statistic record value maximum user.After normalized, obtained preference value be located at 0-1 it
Between.
In the present embodiment, above-mentioned 3rd determination unit 403 can preset the second correlation degree threshold value.Wherein, history thing
Correlation degree threshold value between product information and article to be recommended is more than the second correlation degree threshold value, represents history Item Information and treats
Recommend the correlation degree between article larger, user the corresponding article of the Item Information to be recommended is produced the possibility of interest compared with
Greatly.
In the present embodiment, above-mentioned generation unit 404 can be based on the recommendation article letter that the 3rd determination unit 403 obtains
Breath, further generates recommendation information.Wherein, recommendation information can include recommending Item Information, can also include other and recommendation
The relevant other information of Item Information.For example, above-mentioned electronic equipment can will recommend Item Information and for recommendation Item Information
The information such as corresponding article word, picture together add recommendation information.
In some optional implementations of the present embodiment, the above-mentioned device 400 for being used to generate information can also include
Transmitting element (not shown), is configured to the recommendation information of generation being sent to terminal used in targeted customer.
The history article that the device that above-described embodiment of the application provides obtains targeted customer by the first determination unit is believed
Breath, the second determination unit determine Item Information set to be recommended, and then the 3rd determination unit is from Item Information set to be recommended
Item Information is recommended in extraction, ultimately produces unit and is based on recommending Item Information generation recommendation information.Improve generation recommendation information
Specific aim.
Below with reference to Fig. 5, it illustrates suitable for for realizing the computer system 500 of the server of the embodiment of the present application
Structure diagram.Server shown in Fig. 5 is only an example, should not be to the function and use scope band of the embodiment of the present application
Carry out any restrictions.
As shown in figure 5, computer system 500 includes central processing unit (CPU) 501, it can be read-only according to being stored in
Program in memory (ROM) 502 or be loaded into program in random access storage device (RAM) 503 from storage part 508 and
Perform various appropriate actions and processing.In RAM 503, also it is stored with system 500 and operates required various programs and data.
CPU 501, ROM 502 and RAM 503 are connected with each other by bus 504.Input/output (I/O) interface 505 is also connected to always
Line 504.
I/O interfaces 505 are connected to lower component:Importation 506 including keyboard, mouse etc.;Penetrated including such as cathode
The output par, c 507 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.;Storage part 508 including hard disk etc.;
And the communications portion 509 of the network interface card including LAN card, modem etc..Communications portion 509 via such as because
The network of spy's net performs communication process.Driver 510 is also according to needing to be connected to I/O interfaces 505.Detachable media 511, such as
Disk, CD, magneto-optic disk, semiconductor memory etc., are installed on driver 510, in order to read from it as needed
Computer program be mounted into as needed storage part 508.
Especially, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product, it includes being carried on computer-readable medium
On computer program, the computer program include be used for execution flow chart shown in method program code.In such reality
Apply in example, which can be downloaded and installed by communications portion 509 from network, and/or from detachable media
511 are mounted.When the computer program is performed by central processing unit (CPU) 501, perform what is limited in the present processes
Above-mentioned function.It should be noted that the computer-readable medium of the application can be computer-readable signal media or calculating
Machine readable storage medium storing program for executing either the two any combination.Computer-readable recording medium for example can be --- but it is unlimited
In system, device or the device of --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or it is any more than combination.Calculate
The more specifically example of machine readable storage medium storing program for executing can include but is not limited to:It is electrical connection with one or more conducting wires, portable
Formula computer disk, hard disk, random access storage device (RAM), read-only storage (ROM), erasable programmable read only memory
(EPROM or flash memory), optical fiber, portable compact disc read-only storage (CD-ROM), light storage device, magnetic memory device or
The above-mentioned any appropriate combination of person.In this application, computer-readable recording medium can be any includes or storage program
Tangible medium, the program can be commanded execution system, device either device use or it is in connection.And in this Shen
Please in, computer-readable signal media can include in a base band or as carrier wave a part propagation data-signal, its
In carry computer-readable program code.The data-signal of this propagation can take various forms, and include but not limited to
Electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable
Any computer-readable medium beyond storage medium, the computer-readable medium can send, propagate or transmit for by
Instruction execution system, device either device use or program in connection.The journey included on computer-readable medium
Sequence code can be transmitted with any appropriate medium, be included but not limited to:Wirelessly, electric wire, optical cable, RF etc., or it is above-mentioned
Any appropriate combination.
Flow chart and block diagram in attached drawing, it is illustrated that according to the system of the various embodiments of the application, method and computer journey
Architectural framework in the cards, function and the operation of sequence product.At this point, each square frame in flow chart or block diagram can generation
The part of one module of table, program segment or code, the part of the module, program segment or code include one or more use
In the executable instruction of logic function as defined in realization.It should also be noted that marked at some as in the realization replaced in square frame
The function of note can also be with different from the order marked in attached drawing generation.For example, two square frames succeedingly represented are actually
It can perform substantially in parallel, they can also be performed in the opposite order sometimes, this is depending on involved function.Also to note
Meaning, the combination of each square frame and block diagram in block diagram and/or flow chart and/or the square frame in flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit can also be set within a processor, for example, can be described as:A kind of processor, bag
Include the first determination unit, the second determination unit, the 3rd determination unit and generation unit.Wherein, the title of these units is at certain
In the case of do not form restriction to the unit in itself, for example, the first determination unit is also described as " obtaining targeted customer
Historical record, and the history Item Information that includes of definite historical record ".
As on the other hand, present invention also provides a kind of computer-readable medium, which can be
Included in server described in above-described embodiment;Can also be individualism, and without be incorporated the server in.It is above-mentioned
Computer-readable medium carries one or more program, when said one or multiple programs are performed by the server,
So that the server:Obtain the historical record of targeted customer, and the history Item Information that definite historical record includes;Determine with
The matched Item Information set to be recommended of history Item Information, wherein, the article to be recommended letter in Item Information set to be recommended
The correlation degree value of breath between any two is more than the first correlation degree threshold value;, will be with history thing from Item Information set to be recommended
The Item Information to be recommended that the correlation degree value of product information is more than the second correlation degree threshold value is determined as recommending Item Information;Generation
Recommendation information including recommending Item Information.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to the technology that the particular combination of above-mentioned technical characteristic forms
Scheme, while should also cover in the case where not departing from foregoing invention design, carried out by above-mentioned technical characteristic or its equivalent feature
The other technical solutions for being combined and being formed.Such as features described above has similar work(with (but not limited to) disclosed herein
The technical solution that the technical characteristic of energy is replaced mutually and formed.
Claims (12)
1. a kind of method for generating information, including:
The historical record of targeted customer is obtained, and determines the history Item Information that the historical record includes;
The definite and matched Item Information set to be recommended of the history Item Information, wherein, the Item Information collection to be recommended
The correlation degree value of Item Information to be recommended between any two in conjunction is more than the first correlation degree threshold value;
From the Item Information set to be recommended, journey will be associated more than second with the correlation degree value of the history Item Information
The Item Information to be recommended of degree threshold value is determined as recommending Item Information;
Generation includes the recommendation information of the recommendation Item Information.
2. according to the method described in claim 1, wherein, correlation degree value determines as follows:
Sampling Item Information set is obtained, wherein, the sampling Item Information set includes Item Information to be recommended;
For each sampling Item Information in the sampling Item Information set, it is corresponding at least to obtain the sampling Item Information
Usage record value of one sampling user in preset time period, wherein, usage record value is to be directed to take in response to sampling user
The numerical value that the sampling article of sample Item Information characterization carries out predetermined registration operation and records;From the sampling Item Information corresponding at least one
The target sampling user for meeting preset condition is determined in a sampling user;Unite to the usage record value of target sampling user
Meter, obtains the statistic record value of target sampling user;Obtained statistic record value is normalized, target is obtained and takes
Sample user corresponds to the preference value of the Item Information to be recommended;
Based on obtained preference value and the Item Information set to be recommended, obtain in the Item Information set to be recommended
The correlation degree value of Item Information to be recommended between any two.
3. according to the method described in claim 2, wherein, the preset condition includes at least one of following:Sampling user's makes
With the fluctuation range of record value in fluctuation range threshold value, the user name for sampling user is not belonging to default user name set.
4. according to the method described in claim 2, wherein, the usage record value to target sampling user counts, and obtains
To the statistic record value of target sampling user, including:
Sum to usage record value of the target sampling user in each default measurement period, obtain each default measurement period
Interior statistic record value, wherein, the duration for presetting measurement period is less than or equal to the duration of the preset time period;
Sum to each statistic record value, obtain the statistic record value of target sampling user.
5. according to the method described in one of claim 2-4, wherein, it is described that place is normalized to obtained statistic record value
Reason, obtains the preference value that target sampling user corresponds to the Item Information to be recommended, including:
The statistic record value of target sampling user and the ratio of the statistic record value of maximum usage record value user are determined as
Target sampling user corresponds to the preference value of the Item Information to be recommended, wherein, maximum usage record value user is that this is to be recommended
In the corresponding each target sampling user of Item Information, statistic record value maximum user.
6. a kind of device for being used to generate information, including:
First determination unit, is configured to obtain the historical record of targeted customer, and determines going through of including of the historical record
History Item Information;
Second determination unit, is configured to the definite and matched Item Information set to be recommended of the history Item Information, wherein,
The correlation degree value of Item Information to be recommended between any two in the Item Information set to be recommended is more than the first correlation degree
Threshold value;
3rd determination unit, is configured to from the Item Information set to be recommended, by the pass with the history Item Information
The Item Information to be recommended that connection degree value is more than the second correlation degree threshold value is determined as recommending Item Information;
Generation unit, being configured to generation includes the recommendation information of the recommendation Item Information.
7. device according to claim 6, wherein, described device further includes:
Acquiring unit, is configured to obtain sampling Item Information set, wherein, the sampling Item Information set includes to be recommended
Item Information;
4th determination unit, is configured to for each sampling Item Information in the sampling Item Information set, obtaining should
Usage record value of the corresponding at least one sampling user of Item Information in preset time period is sampled, wherein, usage record value
For the numerical value recorded in response to sampling user for the sampling article progress predetermined registration operation of sampling Item Information characterization;Taken from this
The target sampling user for meeting preset condition is determined in the corresponding at least one sampling user of sample Item Information;Target is sampled and is used
The usage record value at family is counted, and obtains the statistic record value of target sampling user;Obtained statistic record value is carried out
Normalized, obtains the preference value that target sampling user corresponds to the Item Information to be recommended;
5th determination unit, is configured to be based on obtained preference value and the Item Information set to be recommended, obtains described
The correlation degree value of Item Information to be recommended between any two in Item Information set to be recommended.
8. device according to claim 7, wherein, the preset condition includes at least one of following:Sampling user's makes
With the fluctuation range of record value in fluctuation range threshold value, the user name for sampling user is not belonging to default user name set.
9. device according to claim 7, wherein, the 4th determination unit includes:
First computing module, is configured to seek usage record value of the target sampling user in each default measurement period
With, the statistic record value in each default measurement period is obtained, wherein, the duration for presetting measurement period is less than or equal to described preset
The duration of period;
Second computing module, is configured to sum to each statistic record value, obtains the statistic record value of target sampling user.
10. according to the device described in one of claim 7-9, wherein, the 4th determination unit is further configured to:
The statistic record value of target sampling user and the ratio of the statistic record value of maximum usage record value user are determined as
Target sampling user corresponds to the preference value of the Item Information to be recommended, wherein, maximum usage record value user is that this is to be recommended
In the corresponding each target sampling user of Item Information, statistic record value maximum user.
11. a kind of server, including:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processors are real
The now method as described in any in claim 1-5.
12. a kind of computer-readable recording medium, is stored thereon with computer program, wherein, when which is executed by processor
Realize the method as described in any in claim 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711157033.7A CN107944956A (en) | 2017-11-20 | 2017-11-20 | Method and apparatus for generating information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711157033.7A CN107944956A (en) | 2017-11-20 | 2017-11-20 | Method and apparatus for generating information |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107944956A true CN107944956A (en) | 2018-04-20 |
Family
ID=61930233
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711157033.7A Pending CN107944956A (en) | 2017-11-20 | 2017-11-20 | Method and apparatus for generating information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107944956A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109767288A (en) * | 2018-12-15 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Product information synchronous method, device, computer equipment and storage medium |
CN110473043A (en) * | 2018-05-11 | 2019-11-19 | 北京京东尚科信息技术有限公司 | A kind of item recommendation method and device based on user behavior |
CN111177543A (en) * | 2019-12-23 | 2020-05-19 | 杭州火小二科技有限公司 | Object recommendation method and device, storage medium and electronic device |
CN111723293A (en) * | 2020-06-24 | 2020-09-29 | 上海风秩科技有限公司 | Article content recommendation method and device, electronic equipment and storage medium |
CN111861293A (en) * | 2019-04-26 | 2020-10-30 | 北京京东振世信息技术有限公司 | Method and apparatus for transmitting information |
CN112288540A (en) * | 2020-11-02 | 2021-01-29 | 北京每日优鲜电子商务有限公司 | Item customization information pushing method and device, electronic equipment and readable medium |
CN112632384A (en) * | 2020-12-25 | 2021-04-09 | 北京百度网讯科技有限公司 | Data processing method and device for application program, electronic equipment and medium |
CN112819555A (en) * | 2019-11-15 | 2021-05-18 | 北京沃东天骏信息技术有限公司 | Article recommendation method and device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103942712A (en) * | 2014-05-09 | 2014-07-23 | 北京联时空网络通信设备有限公司 | Product similarity based e-commerce recommendation system and method thereof |
US20140372338A1 (en) * | 2013-06-18 | 2014-12-18 | Capital One Financial Corporation | Systems and methods for recommending merchants to a consumer |
CN105469263A (en) * | 2014-09-24 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and device |
-
2017
- 2017-11-20 CN CN201711157033.7A patent/CN107944956A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140372338A1 (en) * | 2013-06-18 | 2014-12-18 | Capital One Financial Corporation | Systems and methods for recommending merchants to a consumer |
CN103942712A (en) * | 2014-05-09 | 2014-07-23 | 北京联时空网络通信设备有限公司 | Product similarity based e-commerce recommendation system and method thereof |
CN105469263A (en) * | 2014-09-24 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and device |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110473043A (en) * | 2018-05-11 | 2019-11-19 | 北京京东尚科信息技术有限公司 | A kind of item recommendation method and device based on user behavior |
CN109767288A (en) * | 2018-12-15 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Product information synchronous method, device, computer equipment and storage medium |
CN111861293A (en) * | 2019-04-26 | 2020-10-30 | 北京京东振世信息技术有限公司 | Method and apparatus for transmitting information |
CN112819555A (en) * | 2019-11-15 | 2021-05-18 | 北京沃东天骏信息技术有限公司 | Article recommendation method and device |
CN111177543A (en) * | 2019-12-23 | 2020-05-19 | 杭州火小二科技有限公司 | Object recommendation method and device, storage medium and electronic device |
CN111723293A (en) * | 2020-06-24 | 2020-09-29 | 上海风秩科技有限公司 | Article content recommendation method and device, electronic equipment and storage medium |
CN111723293B (en) * | 2020-06-24 | 2023-08-25 | 上海风秩科技有限公司 | Article content recommendation method and device, electronic equipment and storage medium |
CN112288540A (en) * | 2020-11-02 | 2021-01-29 | 北京每日优鲜电子商务有限公司 | Item customization information pushing method and device, electronic equipment and readable medium |
CN112632384A (en) * | 2020-12-25 | 2021-04-09 | 北京百度网讯科技有限公司 | Data processing method and device for application program, electronic equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107944956A (en) | Method and apparatus for generating information | |
CN107464169B (en) | Information output method and device | |
CN107172151A (en) | Method and apparatus for pushed information | |
CN108664513B (en) | Method, device and equipment for pushing keywords | |
CN109145280A (en) | The method and apparatus of information push | |
CN106845999A (en) | Risk subscribers recognition methods, device and server | |
CN107944481A (en) | Method and apparatus for generating information | |
CN108335177A (en) | Shopping recommendation method, user terminal, server-side, equipment and storage medium | |
CN108805594A (en) | Information-pushing method and device | |
CN107295095A (en) | The method and apparatus for pushing and showing advertisement | |
CN108632311A (en) | Information-pushing method and device | |
CN107609890A (en) | A kind of method and apparatus of order tracking | |
CN110020162B (en) | User identification method and device | |
CN107911449A (en) | Method and apparatus for pushed information | |
CN109976997A (en) | Test method and device | |
CN110298716A (en) | Information-pushing method and device | |
CN107426328A (en) | Information-pushing method and device | |
CN108491267A (en) | Method and apparatus for generating information | |
CN108810047A (en) | For determining that information pushes the method, apparatus and server of accuracy rate | |
CN108595448A (en) | Information-pushing method and device | |
CN108243219A (en) | The method and apparatus of information push | |
CN109727047A (en) | A kind of method and apparatus, data recommendation method and the device of determining data correlation degree | |
CN107169077A (en) | Method and apparatus for pushed information | |
CN107977678A (en) | Method and apparatus for output information | |
CN107451785A (en) | Method and apparatus for output information |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180420 |