CN109711875A - Content recommendation method and device - Google Patents
Content recommendation method and device Download PDFInfo
- Publication number
- CN109711875A CN109711875A CN201811552763.1A CN201811552763A CN109711875A CN 109711875 A CN109711875 A CN 109711875A CN 201811552763 A CN201811552763 A CN 201811552763A CN 109711875 A CN109711875 A CN 109711875A
- Authority
- CN
- China
- Prior art keywords
- shops
- user
- grade
- wheel
- evaluation information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of content recommendation method and devices.Wherein, content recommendation method comprises determining that target user, inquires user's calling hierarchy of the target user prestored in database;It determines the object content of at least one shops to be recommended, inquires shops's grade of at least one shops prestored in database;User's calling hierarchy of target user is matched with shops's grade of at least one shops, is selected to obtain object content to be recommended from the object content of at least one shops according to matching result;Object content to be recommended is pushed to target user.Based on scheme provided by the invention, recommend suitable object content to be recommended to user according to user's calling hierarchy, user can be promoted to the interest-degree of object content to be recommended, substantially increase a possibility that user further appreciates that or buys, to further promote the marketing flow of shops, marketing flow waste ratio is reduced, push effect is improved.
Description
Technical field
The present invention relates to Internet technical fields, and in particular to a kind of content recommendation method and device.
Background technique
With the continuous development of Internet technology, various platforms come into being, for example, shopping platform, take out platform, hire a car
Platform etc..More and more businessman's selections open up shops in platform, and are accordingly promoted on platform, for example, in platform
Advertisement or commodity etc. is presented in the corresponding page, and, more and more users' selection is selected on these platforms needed for oneself
Resource, such as commodity or service.
By for advertisement is presented in the page, it is all formula of extensively casting net that traditional advertisement, which is thrown to the page, in a certain period of time
It is fixed for being thrown to the advertisement of some page or some advertisement position of some page, such as: 5 folding advertisement of KFC is owned
User, which enters some page in certain time period, can see the advertisement, however not all user is emerging to the advertisement sense
Therefore interest wastes many marketing flows.
Summary of the invention
In view of the above problems, it proposes on the present invention overcomes the above problem or at least be partially solved in order to provide one kind
State the content recommendation method and device of problem.
According to an aspect of the invention, there is provided a kind of content recommendation method, comprising:
It determines target user, inquires user's calling hierarchy of the target user prestored in database;
It determines the object content of at least one shops to be recommended, inquires the door of at least one shops prestored in database
Shop grade;
User's calling hierarchy of target user is matched with shops's grade of at least one shops, according to matching result
Selection obtains object content to be recommended from the object content of at least one shops;
Object content to be recommended is pushed to target user.
Optionally, user's calling hierarchy of target user is matched with shops's grade of at least one shops, according to
Matching result selects to obtain object content to be recommended from the object content of at least one shops: judging that target is used
Whether user's calling hierarchy at family matches with shops's grade of any shops;If so, the target for the shops that selection matches
Content is as object content to be recommended;If it is not, the object content for the shops for then selecting shops's grade to be higher than user's calling hierarchy is made
For object content to be recommended.
Optionally, before determining target user, method further include: obtain evaluation information, door is determined according to evaluation information
Shop grade and user's calling hierarchy save shops's grade and user's calling hierarchy in the database.
Optionally, shops's grade is determined according to evaluation information and user's calling hierarchy further comprises:
It determines shops's cluster to be graded, for each shops in shops's cluster to be graded, is believed according to the evaluation of the shops
Breath calculates the 1st wheel shops's grade of the shops;
It determines to Ratings User cluster, for each user in Ratings User cluster, is believed according to the evaluation of the user
Breath calculates the 1st wheel user's calling hierarchy of the user;
Using the 1st wheel shops's grade and the 1st wheel user's calling hierarchy as initial value, according to each in Ratings User cluster
User treats the evaluation information of each shops in grading shops's cluster, carries out number wheel iteration adjustment to initial value, it is final determine to
Shops's grade of each shops and user's calling hierarchy to each user in Ratings User cluster in grading shops's cluster.
Optionally, believed according to the evaluation for treating each shops in grading shops's cluster to each user in Ratings User cluster
Breath carries out number wheel iteration adjustment to initial value, it is final determine in shops's cluster to be graded shops's grade of each shops and to
User's calling hierarchy of each user further comprises in Ratings User cluster: since i=2,
S1, for each shops in shops's cluster to be graded, according to commenting for (i-1)-th wheel user's calling hierarchy and the shops
Valence information calculates i-th wheel shops's grade of the shops, and for each user in Ratings User cluster, according to (i-1)-th
The evaluation information of wheel shops's grade and the user calculate i-th wheel user's calling hierarchy of the user;
S2 judges whether i-th wheel shops's grade of each shops and (i-1)-th wheel shops's grade are identical, and each user
Whether i-th wheel user's calling hierarchy and (i-1)-th wheel user's calling hierarchy are identical;
S3, if so, i-th wheel shops's grade of each shops is ultimately determined to shops's grade of each shops, and
I-th wheel user's calling hierarchy of each user is ultimately determined to user's calling hierarchy of each user, iteration adjustment process knot
Beam;
S4 is jumped if it is not, i is then assigned a value of i+1 and is executed step S1.
Optionally, for each shops in shops's cluster to be graded, according to (i-1)-th wheel user's calling hierarchy and the shops
Evaluation information calculate the shops i-th wheel shops's grade further comprise:
Determine the assessment grade of every evaluation information of the shops;It is commented according to the assessment grade of every evaluation information and every
Valence information corresponds to (i-1)-th wheel user's calling hierarchy of user, sorts out every evaluation information according to the first classifying rules;Base
In the categorization results of each evaluation information of the shops, i-th wheel shops's grade of the shops is calculated using the first preset rules.
Optionally, the categorization results of each evaluation information based on the shops calculate the shops using the first preset rules
I-th wheel shops's grade further comprise: calculate the default class of at least one obtained after being sorted out according to the first classifying rules
The item number accounting of not middle evaluation information calculates i-th wheel shops's grade of shops according to item number accounting.
Optionally, for each user in Ratings User cluster, according to commenting for (i-1)-th wheel shops's grade and the user
I-th wheel user's calling hierarchy that valence information calculates the user further comprises:
Determine the assessment grade of every evaluation information of the user;It is commented according to the assessment grade of every evaluation information and every
Valence information corresponds to (i-1)-th wheel shops's grade of shops, sorts out every evaluation information according to the second classifying rules;Based on this
The categorization results of each evaluation information of user calculate i-th wheel user's calling hierarchy of the user using the second preset rules.
Optionally, the categorization results of each evaluation information based on the user calculate the user using the second preset rules
I-th wheel user's calling hierarchy further comprise: calculate obtained after sorting out according to the second classifying rules at least one is pre-
If the item number accounting of evaluation information in classification, i-th wheel user's calling hierarchy of user is calculated according to item number accounting.
Optionally it is determined that shops's cluster to be graded further comprises: judging whether the item number of the evaluation information of shops is greater than
Or it is equal to the first preset threshold;If so, being added the shops to shops's cluster to be graded;If it is not, then silent for shops distribution
Recognize shops's grade.
Optionally it is determined that further comprising to Ratings User cluster: judging whether the item number of the evaluation information of user is greater than
Or it is equal to the second preset threshold;If so, being added the user to Ratings User cluster;If to any in Ratings User cluster
The evaluation information of user is not belonging to the evaluation information for each shops in shops's cluster to be graded, then distributes and default for the user
User's calling hierarchy.
According to another aspect of the present invention, a kind of content recommendation device is provided, comprising:
First determining module, is adapted to determine that target user;
First enquiry module, suitable for inquiring user's calling hierarchy of the target user prestored in database;
Second determining module is adapted to determine that the object content of at least one shops to be recommended;
Second enquiry module, suitable for inquiring shops's grade of at least one shops prestored in database;
A processing module, suitable for carrying out shops's grade of user's calling hierarchy of target user and at least one shops
Match, is selected to obtain object content to be recommended from the object content of at least one shops according to matching result;
Pushing module, suitable for object content to be recommended is pushed to target user.
Optionally, processing module is further adapted for: judge target user user's calling hierarchy whether with any shops
Shops's grade matches;If so, selecting the object content of the shops to match as object content to be recommended;If it is not, then selecting
Object content of shops's grade higher than the shops of user's calling hierarchy is selected as object content to be recommended.
Optionally, device further include: third determining module is suitable for obtaining evaluation information, determines shops according to evaluation information
Grade and user's calling hierarchy;
Database is suitable for storage shops's grade and user's calling hierarchy.
Optionally, third determining module is further adapted for: shops's cluster to be graded is determined, in shops's cluster to be graded
Each shops, according to the evaluation information of the shops calculate the shops the 1st wheel shops's grade;
It determines to Ratings User cluster, for each user in Ratings User cluster, is believed according to the evaluation of the user
Breath calculates the 1st wheel user's calling hierarchy of the user;
Using the 1st wheel shops's grade and the 1st wheel user's calling hierarchy as initial value, according to each in Ratings User cluster
User treats the evaluation information of each shops in grading shops's cluster, carries out number wheel iteration adjustment to initial value, it is final determine to
Shops's grade of each shops and user's calling hierarchy to each user in Ratings User cluster in grading shops's cluster.
Optionally, third determining module is further adapted for being iterated adjustment according to following procedure: since i=2,
S1, for each shops in shops's cluster to be graded, according to commenting for (i-1)-th wheel user's calling hierarchy and the shops
Valence information calculates i-th wheel shops's grade of the shops, and for each user in Ratings User cluster, according to (i-1)-th
The evaluation information of wheel shops's grade and the user calculate i-th wheel user's calling hierarchy of the user;
S2 judges whether i-th wheel shops's grade of each shops and (i-1)-th wheel shops's grade are identical, and each user
Whether i-th wheel user's calling hierarchy and (i-1)-th wheel user's calling hierarchy are identical;
S3, if so, i-th wheel shops's grade of each shops is ultimately determined to shops's grade of each shops, and
I-th wheel user's calling hierarchy of each user is ultimately determined to user's calling hierarchy of each user, iteration adjustment process knot
Beam;
S4 is jumped if it is not, i is then assigned a value of i+1 and is executed S1.
Optionally, third determining module is further adapted for: determining the assessment grade of every evaluation information of the shops;According to
The assessment grade and every evaluation information of every evaluation information correspond to (i-1)-th wheel user's calling hierarchy of user, according to first point
Rule-like sorts out every evaluation information;The categorization results of each evaluation information based on the shops, it is default using first
Rule calculates i-th wheel shops's grade of the shops.
Optionally, third determining module is further adapted for: calculating sorted out according to the first classifying rules after obtain to
The item number accounting of evaluation information in few pre-set categories calculates i-th wheel shops's grade of shops according to item number accounting.
Optionally, third determining module is further adapted for: determining the assessment grade of every evaluation information of the user;According to
The assessment grade and every evaluation information of every evaluation information correspond to (i-1)-th wheel shops's grade of shops, according to the second classification gauge
Then every evaluation information is sorted out;The categorization results of each evaluation information based on the user, utilize the second preset rules
Calculate i-th wheel user's calling hierarchy of the user.
Optionally, third determining module is further adapted for: calculating sorted out according to the second classifying rules after obtain to
The item number accounting of evaluation information in few pre-set categories calculates i-th wheel user's calling hierarchy of user according to item number accounting.
Optionally, third determining module is further adapted for: judging whether the item number of the evaluation information of shops is greater than or equal to
First preset threshold;If so, being added the shops to shops's cluster to be graded;If it is not, being then distribution default shops, the shops
Grade.
Optionally, third determining module is further adapted for: judging whether the item number of the evaluation information of user is greater than or equal to
Second preset threshold;If so, being added the user to Ratings User cluster;If to any user in Ratings User cluster
Evaluation information is not belonging to the evaluation information for each shops in shops's cluster to be graded, then distributes default user for the user and want
Seek grade.
According to another aspect of the invention, provide a kind of calculating equipment, comprising: processor, memory, communication interface and
Communication bus, processor, memory and communication interface complete mutual communication by communication bus;
Memory makes processor execute above content recommended method for storing an at least executable instruction, executable instruction
Corresponding operation.
In accordance with a further aspect of the present invention, a kind of computer storage medium is provided, at least one is stored in storage medium
Executable instruction, executable instruction make processor execute such as the corresponding operation of above-mentioned content recommendation method.
The scheme provided according to the present invention determines target user, and the user for inquiring the target user prestored in database wants
Seek grade;It determines the object content of at least one shops to be recommended, inquires the door of at least one shops prestored in database
Shop grade;User's calling hierarchy of target user is matched with shops's grade of at least one shops, according to matching result
Selection obtains object content to be recommended from the object content of at least one shops;Object content to be recommended is pushed to target to use
Family.Based on scheme provided by the invention, suitable object content to be recommended, Ke Yiti are recommended to user according to user's calling hierarchy
User is risen to the interest-degree of object content to be recommended, substantially increases a possibility that user further appreciates that or buys, thus into
One step promotes the marketing flow of shops, reduces marketing flow waste ratio, improves push effect.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 shows the flow diagram of content recommendation method according to an embodiment of the invention;
Fig. 2 shows the processes of shops's grade according to an embodiment of the invention and user's calling hierarchy calculation method to show
It is intended to;
Fig. 3 shows the flow diagram that the method for i-th wheel shops's grade is calculated in the embodiment of the present invention;
Fig. 4 shows the flow diagram that the method for i-th wheel user's calling hierarchy is calculated in the embodiment of the present invention;
Fig. 5 shows the structural schematic diagram of content recommendation device according to an embodiment of the invention;
Fig. 6 shows the structural schematic diagram according to an embodiment of the invention for calculating equipment.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
Fig. 1 shows the flow diagram of content recommendation method according to an embodiment of the invention.As shown in Figure 1, should
Method the following steps are included:
Step S100 determines target user, inquires user's calling hierarchy of the target user prestored in database.
Target user be using the user applied accordingly, for example, use here can be starting application or
The application-browsing page is entered, user's calling hierarchy is division of the user to shops's service request, for example, user's calling hierarchy can
With comprising: high request, it is middle require, low requirement, it is only to illustrate here that user's calling hierarchy of different user may be not identical
It is bright, do not have any restriction effect, user's calling hierarchy that other forms divide belongs to the scope of the present invention.
Specifically, which user is real-time monitoring have using application, and the user using application is target user, is determining mesh
After marking user, database is inquired to determine user's calling hierarchy of target user.Optionally, user has been stored in advance in database
The corresponding relationship of calling hierarchy and user identifier, monitor user use in application, obtain user user identifier, according to
User identifier inquires database, the corresponding user's calling hierarchy of the user identifier is determined, so that it is determined that the user of target user wants
Seek grade.The present embodiment is not limited to inquire database according to user identifier to determine user's calling hierarchy of target user,
It is used as the information of user's unique identities, may be used to inquire database, user is stored in advance in database at this time
The corresponding relationship of calling hierarchy and other information as user's unique identities.
Step S101 determines the object content of at least one shops to be recommended, inquires at least one prestored in database
Shops's grade of a shops.
Shops's grade is to divide according to shops's service quality to shops, for example, shops's grade may include: Gao Pin
Matter, middle quality, low-quality, shops's grade of different shops may be not identical, is merely illustrative of here, does not have any limit
It is set for using, shops's grade that other forms divide belongs to the scope of the present invention.
In real life, there is a large amount of shops using as a kind of maintenance of operation platform, however, it is possible to not all door
There is commending contents demand in shop, but there is commending contents demand in part shops, and therefore, it is necessary to first determine at least one to be recommended
The object content of shops, wherein object content can be advertisement (for example, banner advertisement), commodity etc., to be recommended determining
After the object content of at least one shops, database is inquired, determines shops's grade of at least one shops.
Optionally, the corresponding relationship of shops's grade and shops's mark has been stored in advance in database, it is to be recommended determining
After the object content of at least one shops, shops's mark of at least one shops is extracted, inquiry database is identified according to shops, really
The fixed shops identifies corresponding shops's grade, so that it is determined that shops's grade of at least one shops.The present embodiment is not limited to root
The shops's grade for inquiring database to determine at least one shops is identified according to shops, it is other to be used as shops's unique identities
Information, may be used to inquire database, at this time database be stored in advance shops's grade and it is other be used as shops's unique identities
Information corresponding relationship.
Step S102 matches user's calling hierarchy of target user with shops's grade of at least one shops, root
It selects to obtain object content to be recommended from the object content of at least one shops according to matching result.
The content that some page in order to avoid all users in some period is seen is all the same, leads to certain customers
The problem of to these contents and loseing interest in, and wasting marketing flow, this step will be according to user's calling hierarchy and shops's grade
Determine object content to be recommended, it is specifically, user's calling hierarchy of target user and the shops of at least one shops etc. is grading
Row matching, obtains matching result, matching here is the comparable door of user's calling hierarchy determined whether there is with target user
Shop grade, wherein quite specifically: user's calling hierarchy is middle requirement, is with the comparable shops's grade of user's calling hierarchy
Middle quality.Then, it is selected to obtain object content to be recommended from the object content of at least one shops according to matching result.
Thus the object content to be recommended selected, it is easier to so that user is generated interest, user can be obtained and more paid close attention to,
Make the interesting understanding of user or purchase etc., to further promote the marketing flow of shops.
Object content to be recommended is pushed to target user by step S103.
After selection obtains object content to be recommended, the object content to be recommended that selection obtains can be pushed to user,
It allows users to see the object content to be recommended pushed.
In a kind of optional embodiment of the present invention, by the door of user's calling hierarchy of target user and at least one shops
Shop grade is matched, selected to obtain from the object content of at least one shops according to matching result object content to be recommended into
One step includes:
Judge whether user's calling hierarchy of target user matches with shops's grade of any shops;If so, selection
The object content of the shops to match is as object content to be recommended;If it is not, shops's grade is then selected to be higher than user's calling hierarchy
Shops object content as object content to be recommended.
After shops's grade of user's calling hierarchy and at least one shops that target user has been determined, by target user's
User's calling hierarchy is compared with shops's grade of at least one shops, with judge target user user's calling hierarchy whether
Match with shops's grade of any shops, if so, selecting the object content of the shops to match as in target to be recommended
Hold, in the optional embodiment, it is understood that there may be shops's grade phase of user's calling hierarchy of target user and multiple shops
With the case where, at this point it is possible to from the multiple shops to match randomly choose a shops object content as mesh to be recommended
Mark content;Alternatively, selecting the object content an of shops to make from the multiple shops to match according to pre-set priority
For object content to be recommended, it is not specifically limited here;If it is not, then selecting shops's grade higher than the shops of user's calling hierarchy
Object content is as object content to be recommended, for example, user's calling hierarchy is low requirement, user's calling hierarchy of target user with
Shops's grade of any shops mismatches, and shops's grade is the shops of middle requirement if it exists, then shops's grade is selected to want in
The object content of the shops asked is as object content to be recommended, if selecting door there is only the shops that shops's grade is high request
Shop grade is the object content of the shops of high request as object content to be recommended.
For example, user's calling hierarchy of target user A, target user B are middle requirement, low requirement, there are three determinations
The object content of shops to be recommended, for example, the object content of shops 1, shops 2, shops 3 respectively, and inquire and obtain shops 1, door
Shop 2, shops 3 shops's grade be respectively as follows: high-quality, middle quality, low-quality, determine that the user of target user A wants by judging
Ask grade and shops's grade of shops 2 to match, then select the object content of the shops 2 to match with user's calling hierarchy as
Object content to be recommended is pushed to target user A by object content to be recommended, thus user A it can be seen that shops 2 it is to be recommended
Content;Matched by user's calling hierarchy of the determining target user B of judgement and shops's grade of shops 3, then selection and user
The object content for the shops 3 that calling hierarchy matches is pushed to target as object content to be recommended, by object content to be recommended
User B, thus user B it can be seen that shops 3 content to be recommended.
Again for example, user's calling hierarchy of target user A is middle requirement, the target there are three shops to be recommended is determined
Content, for example, the object content of shops 1, shops 2, shops 3 respectively, and inquire and obtain shops 1, shops 2, shops of shops 3 etc.
Grade is respectively as follows: high-quality, low-quality, low-quality, user's calling hierarchy and any shops by the determining target user A of judgement
Shops's grade mismatches, then shops's grade is selected to be higher than the object content of the shops 1 of user's calling hierarchy as mesh to be recommended
Mark content, object content to be recommended is pushed to target user A, thus user A it can be seen that shops 1 content to be recommended.
Content recommendation method in the present embodiment can be applied to the recommendation of the content presented needed for the page of spreading its tail of application,
Wherein, the page of spreading its tail is the page shown before presenting using homepage face during application program launching, it can also be used to
After starting application, the specific page in application, the recommendation of the content presented needed for the page, for example, homepage face, Yi Jiqi are entered
Its details page etc..
The method provided according to that above embodiment of the present invention determines target user, inquires the target prestored in database and uses
User's calling hierarchy at family;It determines the object content of at least one shops to be recommended, inquires at least one prestored in database
Shops's grade of a shops;User's calling hierarchy of target user is matched with shops's grade of at least one shops, root
It selects to obtain object content to be recommended from the object content of at least one shops according to matching result;Object content to be recommended is pushed away
Give target user.Based on scheme provided by the invention, suitable target to be recommended is recommended to user according to user's calling hierarchy
Content can promote user to the interest-degree of object content to be recommended, and substantially increase that user further appreciates that or buy can
Energy property reduces marketing flow waste ratio, improves push effect to further promote the marketing flow of shops.
Fig. 2 shows the processes of shops's grade according to an embodiment of the invention and user's calling hierarchy calculation method to show
It is intended to.The present embodiment is shops's grade and user's calling hierarchy to be determined according to acquired evaluation information, and finally determine
Shops's grade and user's calling hierarchy can be saved in the database, in commending contents, by inquire database, determine mesh
User's calling hierarchy of user and shops's grade of at least one shops are marked, by user's calling hierarchy of target user and at least one
Shops's grade of a shops is matched, and is selected to obtain from the object content of at least one shops according to matching result to be recommended
Object content to be recommended is pushed to target user by object content.Shops's grade and user's calling hierarchy is described in detail below
Calculating process, as shown in Fig. 2, method includes the following steps:
S200 determines shops's cluster to be graded, for each shops in shops's cluster to be graded, according to commenting for the shops
Valence information calculates the 1st wheel shops's grade of the shops.
Shops's cluster to be graded is the set for participating in all shops of shops's grading, in order to promote identified shops grade
Accuracy, and guarantee the accuracy that subsequent content is recommended, it is alternatively possible to determine shops to be graded collection by the following method
Group: the item number of the evaluation information of shops is counted, judges whether the item number of the evaluation information of shops is greater than or equal to the first default threshold
Value, wherein those skilled in the art can the first preset threshold of flexible setting according to actual needs, for example, setting first is default
Threshold value is 50 or 100, is not specifically limited here;If the item number of the evaluation information of shops is greater than or equal to the first preset threshold,
Then the shops is added to shops's cluster to be graded;If the item number of the evaluation information of shops is less than the first preset threshold, for this
Shops's distribution default shops's grade.Wherein, the first preset threshold be used to measure the evaluation information of shops number, it is pre- less than first
If threshold value illustrates that the item number of the evaluation information of shops is less, shops can not accurately be determined according to the evaluation information of shops
Therefore grade can be one default shops's grade of shops's distribution, after distributing default shops's grade for shops, method terminates.
The evaluation information of shops reflects the service scenario of shops, therefore, is determining after shops's cluster of grading, for
Each shops in shops's cluster to be graded calculates the 1st wheel shops's grade of the shops according to the evaluation information of the shops, specifically
Ground can analyze the evaluation information of shops, for example, semantic analysis and/or scoring analysis etc., determine that every of shops comments
The assessment grade of valence information, wherein assessment grade include: favorable comment, in comment, difference is commented, the accounting for calculating all kinds of assessment grades is (all kinds of
The total number of item number/shops evaluation information of the evaluation information of assessment grade), according to assessment grade accounting, determine the shops
The 1st wheel shops's grade.
Assessment grade: favorable comment, in comment, difference comments corresponding accounting to be properly termed as again: shops's positive rating, shops's comment rate, door
Shop difference comments rate, wherein
The total number of favorable comment item number/shops evaluation information in shops's positive rating=shops evaluation information
The total number of item number/shops evaluation information is commented in shops's comment rate=shops evaluation information
Difference comments the total number of item number/shops evaluation information in shops's difference comments rate=shops evaluation information
Can specify that in the present embodiment as follows: when shops's positive rating>90% and shops's difference comments rate<1% when, the of shops
1 wheel shops's grade are as follows: high-quality.
When shops's positive rating<70%, alternatively, when shops's difference comments>30%, the 1st wheel shops's grade of shops are as follows: low-quality.
When other situations, the 1st wheel shops's grade of shops are as follows: middle quality.
Wherein, those skilled in the art can according to actual needs flexible setting each shops's grade classification when based on
Accounting is not specifically limited here, for example, can specify that as follows:
When shops's positive rating>85% and shops's difference comments rate<5% when, the 1st wheel shops's grade of shops are as follows: high-quality.
When shops's positive rating<65%, alternatively, when shops's difference comments>35%, the 1st wheel shops's grade of shops are as follows: low-quality.
When other situations, the 1st wheel shops's grade of shops are as follows: middle quality.
S201, determines to Ratings User cluster, for each user in Ratings User cluster, according to commenting for the user
Valence information calculates the 1st wheel user's calling hierarchy of the user.
It is the set of all users of participating user's grading to Ratings User cluster, is required to promote identified user
The accuracy of grade, and guarantee the accuracy that subsequent content is recommended, it is alternatively possible to determine use to be graded by the following method
Family cluster: it is pre- to judge whether the item number of the evaluation information of user is greater than or equal to second for the item number of the evaluation information of counting user
If threshold value;Wherein, those skilled in the art can the second preset threshold of flexible setting according to actual needs, for example, setting second
Preset threshold is 50 or 100, is not specifically limited here;If the item number of the evaluation information of user is greater than or equal to the second default threshold
Value, then the user is added to Ratings User cluster;If the item number of the evaluation information of user less than the second preset threshold, for
The user distributes default user calling hierarchy;If the evaluation information to any user in Ratings User cluster is not belonging to for be evaluated
The evaluation information of each shops in grade shops cluster, then also can not determine that user requires using the method in the present embodiment
Therefore grade can distribute default user calling hierarchy for the user.
The evaluation information of user reflects user to the service request situation of shops, therefore, is determining to Ratings User
After cluster, for each user in Ratings User cluster, used according to the 1st wheel that the evaluation information of the user calculates the user
Family calling hierarchy can specifically analyze the evaluation information of user, for example, semantic analysis and/or scoring analysis etc.,
Determine the assessment grade of every evaluation information of user, wherein assessment grade include: favorable comment, in comment, difference is commented, calculate and all kinds of comment
The accounting (total number of item number/user evaluation information of the evaluation information of all kinds of assessment grades) of valence rank, according to evaluation grade
Other accounting determines the 1st wheel user's calling hierarchy of the user.
Assessment grade: favorable comment, in comment, difference comments corresponding accounting to be properly termed as again: user's positive rating, user's comment rate, use
Family difference comments rate, wherein
The total number of favorable comment item number/user evaluation information in user's positive rating=user evaluation information
The total number of item number/user evaluation information is commented in user's comment rate=user evaluation information
Difference comments the total number of item number/user evaluation information in user's difference comments rate=user evaluation information
It can specify that in the present embodiment as follows:
When user's positive rating>90% and user's difference comments rate<1% when, the 1st wheel user's calling hierarchy of user are as follows: low requirement.
When user's positive rating<70%, alternatively, user's difference comments rate>30% when, the 1st wheel user's calling hierarchy of user are as follows: high
It is required that.
When other situations, the 1st wheel user's calling hierarchy of user are as follows: middle requirement.
Wherein, those skilled in the art can divide Shi Suoyi by each user's calling hierarchy of flexible setting according to actual needs
According to accounting, be not specifically limited here, for example, can specify that as follows:
When user's positive rating>85% and user's difference comments rate<5% when, the 1st wheel user's calling hierarchy of user are as follows: low requirement.
When user's positive rating<65%, alternatively, user's difference comments rate>35% when, the 1st wheel user's calling hierarchy of user are as follows: high
It is required that.
When other situations, the 1st wheel user's calling hierarchy of user are as follows: middle requirement.
After the 1st wheel shops's grade and the 1st wheel user's calling hierarchy has been determined, the 1st wheel shops's grade and the 1st wheel are used
Family calling hierarchy treats each shops in grading shops's cluster as initial value, according to each user in Ratings User cluster
Evaluation information carries out number wheel iteration adjustment, the final shops's grade for determining each shops in shops's cluster to be graded to initial value
And user's calling hierarchy to each user in Ratings User cluster.
Specifically, it can be determined using the method in following steps S202- step S205 each in shops's cluster to be graded
Shops's grade of shops and user's calling hierarchy to each user in Ratings User cluster:
Since i=2,
S202, for each shops in shops's cluster to be graded, according to (i-1)-th wheel user's calling hierarchy and the shops
Evaluation information calculates i-th wheel shops's grade of the shops, and for each user in Ratings User cluster, according to i-th-
The evaluation information of 1 wheel shops's grade and the user calculate i-th wheel user's calling hierarchy of the user.
1st wheel shops's grade of each shops according to determined by the evaluation information of shops can reflect to a certain extent
The service scenario of shops, but the 1st wheel shops's grade can not may accurately reflect shops's quality, in order to more accurately
Determine shops's grade, the present embodiment combines the evaluation information of (i-1)-th wheel user's calling hierarchy and the shops to calculate the i-th of the shops
Take turns shops's grade, wherein user's calling hierarchy reflects the different requirements that user services shops, and the evaluation information of shops is anti-
The service scenario of Ying Liao shops, therefore, i-th wheel shops's grade being calculated based on (i-1)-th wheel user's calling hierarchy more can visitor
See the service scenario of ground reflection shops.
The 1st wheel user's calling hierarchy of each user according to determined by the evaluation information of user can be anti-to a certain extent
User is mirrored to shops's service request, but the 1st wheel user's calling hierarchy can not may accurately reflect user to the clothes of shops
Business requires, in order to more accurately determine that user's calling hierarchy, the present embodiment combine (i-1)-th wheel shops's grade and the user
Evaluation information calculate the user i-th wheel user's calling hierarchy, wherein shops's grade reflects shops's service scenario, and uses
The evaluation information at family reflects user to the service request of shops, therefore, i-th obtained based on (i-1)-th wheel shops's rating calculation
Wheel user's calling hierarchy more can objectively reflect user to the service request of shops.
Fig. 3 shows the flow diagram that the method for i-th wheel shops's grade is calculated in the embodiment of the present invention, it may be assumed that step
The refinement flow diagram of Part Methods in S202, as shown in figure 3, method includes the following steps:
Step S300 determines the assessment grade of every evaluation information of the shops.
Specifically, the evaluation information of shops can be analyzed, for example, semantic analysis and/or scoring analysis etc., determine
The assessment grade of every evaluation information of shops, wherein assessment grade include: favorable comment, in comment, difference is commented.For example, evaluation information packet
Contain: it is good, very good, very etc. words when, it is believed that the assessment grade of evaluation information is favorable comment;Evaluation information includes: generally, also
When can wait words, it is believed that the assessment grade of evaluation information be in comment;Evaluation information includes: it is bad, too the words such as poor when,
It is considered that the assessment grade of evaluation information is commented for difference;For another example the corresponding scoring of evaluation information is 5 stars, it is believed that evaluation letter
The assessment grade of breath is favorable comment;The corresponding scoring of evaluation information is 3 stars or 4 stars, it is believed that during the assessment grade of evaluation information is
It comments;The corresponding scoring of evaluation information is 1 star or 2 stars, it is believed that the assessment grade of evaluation information is commented for difference, is only to illustrate here
It is bright, do not have any restriction effect.
Step S301 is used according to the (i-1)-th wheel that the assessment grade of every evaluation information and every evaluation information correspond to user
Family calling hierarchy sorts out every evaluation information according to the first classifying rules.
First classifying rules specifically defines how to be sorted out according to evaluation information of user's calling hierarchy to shops, under
The rule definition of the first classifying rules is simply enumerated in face:
The favorable comment of high request user is 1 class evaluation information;It is commented in high request user, is 2 class evaluation informations;High request
The difference of user is commented, and is 3 class evaluation informations.
The middle favorable comment for requiring user is 2 class evaluation informations;It is middle to require to comment in user, it is 3 class evaluation informations;Middle requirement
The difference of user is commented, and is 4 class evaluation informations.
The low favorable comment for requiring user is 3 class evaluation informations;It is low to require to comment in user, it is 4 class evaluation informations;Low requirement
The difference of user is commented, and is 5 class evaluation informations.
After the assessment grade (for example, favorable comment, in comment or difference is commented) that every evaluation information has been determined, believed according to every evaluation
The assessment grade of breath and every evaluation information correspond to (i-1)-th wheel user's calling hierarchy of user, will be every according to above-mentioned classifying rules
Evaluation information is sorted out, for example, the assessment grade of a certain evaluation information is favorable comment when calculating the 2nd wheel shops's grade,
The 1st wheel shops's grade of the corresponding user of this article of evaluation information is middle requirement, according to above-mentioned this of classifying rules evaluation information pair
The classification answered is 2 classes, is merely illustrative of here, does not have any restriction effect.
Step S302, the categorization results of each evaluation information based on the shops calculate the door using the first preset rules
I-th wheel shops's grade in shop.
First preset rules concrete regulation each shops's grade corresponding condition is evaluating every according to step S301
After information is sorted out, the categorization results of this evaluation information are obtained, the categorization results of each evaluation information based on the shops,
Specifically it can use following methods calculate shops the using i-th wheel shops's grade that the first preset rules calculate the shops
I takes turns shops's grade: calculating evaluation information at least one pre-set categories obtained after being sorted out according to the first classifying rules
Item number accounting calculates i-th wheel shops's grade of shops according to item number accounting.
It can specify that in the present embodiment as follows:
When item number accounting>90% of 1,2 class evaluation informations, when and the item number accounting of 4,5 class evaluation informations<1%, shops etc.
Grade is high-quality;
When 1,2 class evaluation informations item number accounting<70% or 4,5 class evaluation informations item number accounting>30% when, door
Shop grade is low-quality;
When other situations, shops's grade is middle quality.
Certainly, those skilled in the art can the corresponding numerical value of flexible setting according to actual needs, for example, it is also possible to provide
It is as follows:
When item number accounting>85% of 1,2 class evaluation informations, when and the item number accounting of 4,5 class evaluation informations<5%, shops etc.
Grade is high-quality;
When 1,2 class evaluation informations item number accounting<65% or 4,5 class evaluation informations item number accounting>35% when, door
Shop grade is low-quality;
When other situations, shops's grade is middle quality.
Fig. 4 shows the flow diagram that the method for i-th wheel user's calling hierarchy is calculated in the embodiment of the present invention, it may be assumed that step
The refinement flow diagram of Part Methods in rapid S202, as shown in figure 4, method includes the following steps:
Step S400 determines the assessment grade of every evaluation information of the user.
Specifically, the evaluation information of user can be analyzed, for example, semantic analysis and/or scoring analysis etc., determine
The assessment grade of every evaluation information of user, wherein assessment grade include: favorable comment, in comment, difference is commented.For example, evaluation information packet
Contain: it is good, very good, very etc. words when, it is believed that the assessment grade of evaluation information is favorable comment;Evaluation information includes: generally, also
When can wait words, it is believed that the assessment grade of evaluation information be in comment;Evaluation information includes: it is bad, too the words such as poor when,
It is considered that the assessment grade of evaluation information is commented for difference;For another example the corresponding scoring of evaluation information is 5 stars, it is believed that evaluation letter
The assessment grade of breath is favorable comment;The corresponding scoring of evaluation information is 3 stars or 4 stars, it is believed that during the assessment grade of evaluation information is
It comments;The corresponding scoring of evaluation information is 1 star or 2 stars, it is believed that the assessment grade of evaluation information is commented for difference, is only to illustrate here
It is bright, do not have any restriction effect.
Step S401 corresponds to the (i-1)-th wheel door of shops according to the assessment grade of every evaluation information and every evaluation information
Shop grade sorts out every evaluation information according to the second classifying rules.
Second classifying rules specifically defines how to be sorted out according to evaluation information of shops's grade to user, below letter
The single-row rule definition for lifting the second classifying rules:
The difference of high-quality shops is commented, and is 1 class evaluation information;It is commented in high-quality shops, is 2 class evaluation informations;High-quality
The favorable comment of shops is 3 class evaluation informations.
The difference of middle quality shops is commented, and is 2 class evaluation informations;It is commented in middle quality shops, is 3 class evaluation informations;Middle quality
The favorable comment of shops, 4 class evaluation informations.
The difference of low-quality shops is commented, and is 3 class evaluation informations;It is commented in low-quality shops, is 4 class evaluation informations;It is low-quality
The favorable comment of shops is 5 class evaluation informations.
After the assessment grade (for example, favorable comment, in comment or difference is commented) that every evaluation information has been determined, believed according to every evaluation
The assessment grade of breath and every evaluation information correspond to (i-1)-th wheel shops's grade of shops, comment every according to above-mentioned classifying rules
Valence information is sorted out, for example, the assessment grade of a certain evaluation information is favorable comment when calculating the 2nd wheel user's calling hierarchy,
1st wheel shops's grade of the corresponding shops of this article of evaluation information is middle quality, according to above-mentioned this of classifying rules evaluation information pair
The classification answered is 4 classes, is merely illustrative of here, does not have any restriction effect.
Step S402, the categorization results of each evaluation information based on the user calculate the use using the second preset rules
I-th wheel user's calling hierarchy at family.
Second preset rules concrete regulation each user's calling hierarchy corresponding condition, according to step S401 by every
After evaluation information is sorted out, the categorization results of this evaluation information are obtained, the classification of each evaluation information based on the user
As a result, specifically can use following methods meter using i-th wheel user's calling hierarchy that the second preset rules calculate the user
It calculates i-th wheel user's calling hierarchy of shops: calculating the default class of at least one obtained after sorting out according to the second classifying rules
The item number accounting of not middle evaluation information calculates i-th wheel user's calling hierarchy of user according to item number accounting.
It can specify that in the present embodiment as follows:
When item number accounting>90% of 4,5 class evaluation informations, when and the item number accounting of 1,2 class evaluation informations<1%, Yong Huyao
Seeking grade is low requirement;
When item number accounting<70% of 4,5 class evaluation informations, alternatively, the item number accounting of 1,2 class evaluation informations>30% when, use
Family calling hierarchy is high request;
When other situations, user's calling hierarchy is middle requirement.
Certainly, those skilled in the art can the corresponding numerical value of flexible setting according to actual needs, for example, it is also possible to provide
It is as follows:
When item number accounting>85% of 4,5 class evaluation informations, when and the item number accounting of 1,2 class evaluation informations<5%, Yong Huyao
Seeking grade is low requirement;
When item number accounting<65% of 4,5 class evaluation informations, alternatively, the item number accounting of 1,2 class evaluation informations>35% when, use
Family calling hierarchy is high request;
When other situations, user's calling hierarchy is middle requirement.
S203 judges whether i-th wheel shops's grade of each shops and (i-1)-th wheel shops's grade are identical, and each user
I-th wheel user's calling hierarchy with (i-1)-th take turns user's calling hierarchy it is whether identical;If so, thening follow the steps S204;If it is not, then
Execute step S205.
In order to determine whether to terminate iteration adjustment process, in i-th wheel shops's grade and each that each shops is calculated
After i-th wheel user's calling hierarchy of user, need to judge the i-th wheel shops's grade and (i-1)-th wheel shops's grade of each shops
It is whether identical, and whether i-th wheel user's calling hierarchy of each user and (i-1)-th wheel user's calling hierarchy are identical, are judging
Each shops i-th wheel shops's grade with (i-1)-th wheel shops's grade it is identical, and each user i-th wheel user's calling hierarchy and
In the identical situation of (i-1)-th wheel user's calling hierarchy, show that shops's level constant of each shops is constant, the user of each user
Calling hierarchy is also invariable, can terminate iteration adjustment process;In the i-th wheel shops's grade and i-th-for judging a certain shops
1 wheel shops's grade is identical or i-th wheel user's calling hierarchy of a certain user with (i-1)-th to take turns user's calling hierarchy not identical
In the case where, need to continue iteration adjustment process.
I-th wheel shops's grade of each shops is ultimately determined to shops's grade of each shops by S204, and will be each
I-th wheel user's calling hierarchy of user is ultimately determined to user's calling hierarchy of each user, and iteration adjustment process terminates.
It is identical as (i-1)-th wheel shops's grade in the i-th wheel shops's grade for judging each shops, and the i-th of each user
It takes turns in user's calling hierarchy situation identical with (i-1)-th wheel user's calling hierarchy, shows shops's level constant of each shops not
Become, user's calling hierarchy of each user is also invariable, at this point it is possible to which i-th wheel shops's grade by each shops is finally true
It is set to shops's grade of each shops, and i-th wheel user's calling hierarchy of each user is ultimately determined to each user's
User's calling hierarchy, and terminate iteration adjustment process.
I is assigned a value of i+1 by S205, is jumped and is executed step S202.
Take turns that shops's grade is identical or a certain user with (i-1)-th in the i-th wheel shops's grade for judging a certain shops
Under i-th wheel user's calling hierarchy and the (i-1)-th wheel different situation of user's calling hierarchy, i is assigned a value of i+1, jumps and executes step
Rapid S202.
In a kind of optional embodiment of the present invention, in order to economize on resources, shops's grade and user's calling hierarchy meter are avoided
Evaluation time is too long, can control iteration adjustment and executes wheel number, when i is greater than third predetermined threshold value, terminates iteration adjustment process, will
I-th wheel shops's grade of each shops is ultimately determined to shops's grade of each shops, and takes turns user for the i-th of each user
Calling hierarchy is ultimately determined to user's calling hierarchy of each user.
Step S206 saves shops's grade and user's calling hierarchy in the database.
Shops's grade of each shops and to be evaluated is finally being determined in shops's cluster to be graded according to above method step
In grade user's cluster after user's calling hierarchy of each user, shops's grade and user's calling hierarchy are saved in the database.
For example, shops can be identified with shops's grade associated storage, and by user identifier and user's calling hierarchy associated storage.It protects
Shops's grade in the database and user's calling hierarchy are deposited, can be used in commending contents.
Illustrate the detailed process for calculating shops's grade and user's calling hierarchy below with reference to specific example:
Assuming that there are 5, respectively S1~S5 in shops to be graded, there are 5 to Ratings User, respectively C1~C5, evaluation information
It is as shown in table 1:
Table 1:
C1 | C2 | C3 | C4 | C5 | |
S1 | 10, in 15, poor 5=30 | 20, middle 5=25 | Good 10=10 | Middle 20=20 | Good 15=15 |
S2 | 20, in 5, poor 5=30 | 15, poor 5=20 | 5, poor 5=10 | 5, poor 5=10 | 15, middle 5=20 |
S3 | 10, middle 5=15 | Good 15=15 | Good 40=40 | Good 10=10 | Good 20=20 |
S4 | 5, in 5, poor 10=20 | Good 20=20 | 10, poor 20=30 | 10, poor 5=15 | Good 15=15 |
S5 | Good 5=5 | In 10, poor 10=20 | Middle 10=10 | In 10, poor 5=15 | Good 30=30 |
For shops S1~S5, the 1st wheel shops's grade of each shops is determined respectively, specific as follows:
S1: shops's positive rating=(10+20+10+15)/100=55%, shops's difference comments rate=5/100=5% (low-quality)
S2: shops's positive rating=(20+15+5+5+15)/90=66%, shops's difference comments rate=(5+5+5+5)/90=22%
(low-quality)
S3: shops's positive rating=(10+15+40+10+20)/100=95%, shops's difference comments rate=0% (high-quality)
S4: shops's positive rating=(5+20+10+10+15)/100=60%, shops's difference comments rate=(10+20+5)/100=
35% (low-quality)
S5: shops's positive rating=(5+30)/80=43%, shops's difference comments rate=(10+5)/80=18% (low-quality)
For user C1~C5, the 1st wheel user's calling hierarchy of each user is determined respectively, specific as follows:
C1: user's positive rating=(10+20+10+5+5)/100=50%, user's difference comments rate=(5+5+10)/100=
20% (high request)
C2: user's positive rating=(20+15+15+20)/100=70%, user's difference comments rate=(5+10)/100=15%
(middle requirement)
C3: user's positive rating=(10+5+40+10)/100=65%, user's difference comments rate=(5+20)/100=25% are (high
It is required that)
C4: user's positive rating=(5+10+10)/70=35%, user's difference comments rate=(5+5+5)/70=21% (want by height
It asks)
C5: user's positive rating=(15+15+20+15+30)/100=95%, user's difference comments rate=0% (low requirement)
According to user's calling hierarchy of corresponding 1st wheel of the assessment grade of every evaluation information and every evaluation information, press
According to the first classifying rules, determine that the categorization results of every evaluation information are as shown in table 2:
Table 2:
C1 (height) | C2 (in) | C3 (height) | C4 (height) | C5 (low) | |
S1 is low | 1 class, 10,2 class, 15,3 class 5=30 | 2 class, 20,3 class 5=25 | 1 class 10=10 | 2 class 20=20 | 3 class 15=15 |
S2 is low | 1 class, 20,2 class, 5,3 class 5=30 | 2 class, 15,4 class 5=20 | 1 class, 5,3 class 5=10 | 1 class, 5,3 class 5=10 | 3 class, 15,4 class 5=20 |
S3 high | 1 class, 10,2 class 5=15 | 2 class 15=15 | 1 class 40=40 | 1 class 10=10 | 3 class 20=20 |
S4 is low | 1 class, 5,2 class, 5,3 class 10=20 | 2 class 20=20 | 1 class, 10,3 class 20=30 | 1 class, 10,3 class 5=15 | 3 class 15=15 |
S5 is low | 1 class 5=5 | 3 class, 10,4 class 10=20 | 2 class 10=10 | 2 class, 10,3 class 5=15 | 3 class 30=30 |
The 2nd wheel shops's grade is calculated according to above-mentioned categorization results, specific as follows:
Item number accounting=(25+20+10+20)/100=75% of S1:1,2 class evaluation informations, the item of 4,5 class evaluation informations
Number accounting=0% (middle quality shops)
Item number accounting=(25+15+5+5)/90=55% of S2:1,2 class evaluation informations, the item number of 4,5 class evaluation informations
Accounting=(5+5)/90=11% (low-quality shops)
Item number accounting=(15+15+40+10)/100=80% of S3:1,2 class evaluation informations, the item of 4,5 class evaluation informations
Number accounting=0% (middle quality shops)
Item number accounting=(10+20+10+10)/100=50% of S4:1,2 class evaluation informations, the item of 4,5 class evaluation informations
Number accounting=0% (low-quality shops)
Item number accounting=(5+10+10)/80=31% of S5:1,2 class evaluation informations, the item number of 4,5 class evaluation informations account for
Than=10/80=12.5% (low-quality shops)
The 1st wheel shops's grade that shops is corresponded to according to the assessment grade of every evaluation information and every evaluation information, according to
Second classifying rules determines that the categorization results of every evaluation information are as shown in table 3:
Table 3:
C1 (height) | C2 (in) | C3 (height) | C4 (height) | C5 (low) | |
S1 is low | 5 class, 10,4 class, 15,3 class 5=30 | 5 class, 20,4 class 5=25 | 5 class 10=10 | 4 class 20=20 | 5 class 15=15 |
S2 is low | 5 class, 20,4 class, 5,3 class 5=30 | 5 class, 15,3 class 5=20 | 5 class, 5,3 class 5=10 | 5 class, 5,3 class 5=10 | 5 class, 15,4 class 5=20 |
S3 high | 3 class, 10,2 class 5=15 | 3 class 15=15 | 3 class 40=40 | 3 class 10=10 | 3 class 20=20 |
S4 is low | 5 class, 5,4 class, 5,3 class 10=20 | 5 class 20=20 | 5 class, 10,3 class 20=30 | 5 class, 10,3 class 5=15 | 5 class 15=15 |
S5 is low | 5 class 5=5 | 4 class, 10,3 class 10=20 | 4 class 10=10 | 4 class, 10,3 class 5=15 | 5 class 30=30 |
The 2nd wheel user's calling hierarchy is calculated according to above-mentioned categorization results, specific as follows:
Item number accounting=(25+25+10+5)/100=65% of C1:4,5 class evaluation informations, the item of 1,2 class evaluation informations
Number accounting=5/100=5% (high request)
Item number accounting=(25+15+20+10)/100=70% of C2:4,5 class evaluation informations, the item of 1,2 class evaluation informations
Number accounting=0% (middle requirement)
Item number accounting=(10+5+10+10)/100=35% of C3:4,5 class evaluation informations, the item of 1,2 class evaluation informations
Number accounting=0% (high request)
Item number accounting=(20+5+10+10)/70=64% of C4:4,5 class evaluation informations, the item number of 1,2 class evaluation informations
Accounting=0% (high request)
Item number accounting=(15+20+15+30)/100=80% of C5:4,5 class evaluation informations, the item of 1,2 class evaluation informations
Number accounting=0% (middle requirement)
By comparing discovery, the 2nd wheel shops's grade of shops S1, S3 are different from the 1st wheel shops's grade, and the 2nd of user C5 the
It is different from the 1st wheel user's calling hierarchy to take turns user's calling hierarchy, then needs to carry out the 3rd wheel shops's rating calculation and the 3rd wheel user
Calling hierarchy calculates, after number takes turns iteration adjustment, the final shops's grade for determining each shops in shops's cluster to be graded with
And user's calling hierarchy to each user in Ratings User cluster, shops's grade and user's calling hierarchy are stored in database
In, to be used in commending contents.
The method provided according to that above embodiment of the present invention is mutually restricted more by shops's grade and user's calling hierarchy
Shops's grade of each shops and to each user in Ratings User cluster in shops's cluster to be graded determined by secondary adjustment
User's calling hierarchy it is more accurate, can objectively and accurately reflect the requirement of user and the service scenario of shops, thus root
When carrying out commending contents according to identified shops's grade and user's calling hierarchy, the object content to be recommended recommended, it is easier to
So that user is generated interest, user can be obtained and more paid close attention to, makes the interesting understanding of user or purchase etc., to further be promoted
The marketing flow of shops.
Fig. 5 shows the structural schematic diagram of content recommendation device according to an embodiment of the invention.As shown in figure 5, should
Device includes: the first determining module 500, the first enquiry module 510, the second determining module 520, the second enquiry module 530, processing
Module 540, pushing module 550.
First determining module 500, is adapted to determine that target user.
First enquiry module 510, suitable for inquiring user's calling hierarchy of the target user prestored in database.
Second determining module 520, is adapted to determine that the object content of at least one shops to be recommended.
Second enquiry module 530, suitable for inquiring shops's grade of at least one shops prestored in database.
Processing module 540, suitable for carrying out shops's grade of user's calling hierarchy of target user and at least one shops
Matching, selects to obtain object content to be recommended from the object content of at least one shops according to matching result.
Pushing module 550, suitable for object content to be recommended is pushed to target user.
Optionally, processing module 540 is further adapted for: judge target user user's calling hierarchy whether with any shops
Shops's grade match;If so, selecting the object content of the shops to match as object content to be recommended;If it is not, then
Shops's grade is selected to be higher than the object content of the shops of user's calling hierarchy as object content to be recommended.
Optionally, device further include: third determining module 560 is suitable for obtaining evaluation information, determines door according to evaluation information
Shop grade and user's calling hierarchy;
Database 570 is suitable for storage shops's grade and user's calling hierarchy.
Optionally, third determining module 560 is further adapted for: being determined shops's cluster to be graded, is collected for shops to be graded
Each shops in group calculates the 1st wheel shops's grade of the shops according to the evaluation information of the shops;
It determines to Ratings User cluster, for each user in Ratings User cluster, is believed according to the evaluation of the user
Breath calculates the 1st wheel user's calling hierarchy of the user;
Using the 1st wheel shops's grade and the 1st wheel user's calling hierarchy as initial value, according to each in Ratings User cluster
User treats the evaluation information of each shops in grading shops's cluster, carries out number wheel iteration adjustment to initial value, it is final determine to
Shops's grade of each shops and user's calling hierarchy to each user in Ratings User cluster in grading shops's cluster.
Optionally, third determining module 560 is further adapted for being iterated adjustment according to following procedure: since i=2,
S1, for each shops in shops's cluster to be graded, according to commenting for (i-1)-th wheel user's calling hierarchy and the shops
Valence information calculates i-th wheel shops's grade of the shops, and for each user in Ratings User cluster, according to (i-1)-th
The evaluation information of wheel shops's grade and the user calculate i-th wheel user's calling hierarchy of the user;
S2 judges whether i-th wheel shops's grade of each shops and (i-1)-th wheel shops's grade are identical, and each user
Whether i-th wheel user's calling hierarchy and (i-1)-th wheel user's calling hierarchy are identical;
S3, if so, i-th wheel shops's grade of each shops is ultimately determined to shops's grade of each shops, and
I-th wheel user's calling hierarchy of each user is ultimately determined to user's calling hierarchy of each user, iteration adjustment process knot
Beam;
S4 is jumped if it is not, i is then assigned a value of i+1 and is executed S1.
Optionally, third determining module 560 is further adapted for: determining the assessment grade of every evaluation information of the shops;
(i-1)-th wheel user's calling hierarchy that user is corresponded to according to the assessment grade of every evaluation information and every evaluation information, according to the
One classifying rules sorts out every evaluation information;The categorization results of each evaluation information based on the shops, utilize first
Preset rules calculate i-th wheel shops's grade of the shops.
Optionally, third determining module 560 is further adapted for: what calculating obtained after being sorted out according to the first classifying rules
The item number accounting of evaluation information at least one pre-set categories calculates i-th wheel shops's grade of shops according to item number accounting.
Optionally, third determining module 560 is further adapted for: determining the assessment grade of every evaluation information of the user;
(i-1)-th wheel shops's grade that shops is corresponded to according to the assessment grade of every evaluation information and every evaluation information, according to second point
Rule-like sorts out every evaluation information;The categorization results of each evaluation information based on the user, it is default using second
Rule calculates i-th wheel user's calling hierarchy of the user.
Optionally, third determining module 560 is further adapted for: what calculating obtained after being sorted out according to the second classifying rules
The item number accounting of evaluation information at least one pre-set categories calculates i-th wheel user's calling hierarchy of user according to item number accounting.
Optionally, third determining module 560 is further adapted for: judging whether the item number of the evaluation information of shops is greater than or waits
In the first preset threshold;If so, being added the shops to shops's cluster to be graded;If it is not, being then shops distribution default door
Shop grade.
Optionally, third determining module 560 is further adapted for: judging whether the item number of the evaluation information of user is greater than or waits
In the second preset threshold;If so, being added the user to Ratings User cluster;If to any user in Ratings User cluster
Evaluation information be not belonging to the evaluation information for each shops in shops's cluster to be graded, then be that the user distributes default user
Calling hierarchy.
The device provided according to that above embodiment of the present invention determines target user, inquires the target prestored in database and uses
User's calling hierarchy at family;It determines the object content of at least one shops to be recommended, inquires at least one prestored in database
Shops's grade of a shops;User's calling hierarchy of target user is matched with shops's grade of at least one shops, root
It selects to obtain object content to be recommended from the object content of at least one shops according to matching result;Object content to be recommended is pushed away
Give target user.Based on scheme provided by the invention, suitable target to be recommended is recommended to user according to user's calling hierarchy
Content can promote user to the interest-degree of object content to be recommended, and substantially increase that user further appreciates that or buy can
Energy property reduces marketing flow waste ratio, improves push effect to further promote the marketing flow of shops.
The embodiment of the present application also provides a kind of nonvolatile computer storage media, the computer storage medium storage
There is an at least executable instruction, which can be performed the method in above-mentioned any means embodiment.
Fig. 6 shows the structural schematic diagram according to an embodiment of the invention for calculating equipment, the specific embodiment of the invention
The specific implementation for calculating equipment is not limited.
As shown in fig. 6, the calculating equipment may include: processor (processor) 602, communication interface
(Communications Interface) 604, memory (memory) 606 and communication bus 608.
Wherein:
Processor 602, communication interface 604 and memory 606 complete mutual communication by communication bus 608.
Communication interface 604, for being communicated with the network element of other equipment such as client or other servers etc..
Processor 602 can specifically execute the correlation step in above method embodiment for executing program 610.
Specifically, program 610 may include program code, which includes computer operation instruction.
Processor 602 may be central processor CPU or specific integrated circuit ASIC (Application
Specific Integrated Circuit), or be arranged to implement the integrated electricity of one or more of the embodiment of the present invention
Road.The one or more processors that equipment includes are calculated, can be same type of processor, such as one or more CPU;It can also
To be different types of processor, such as one or more CPU and one or more ASIC.
Memory 606, for storing program 610.Memory 606 may include high speed RAM memory, it is also possible to further include
Nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.
Program 610 specifically can be used for so that processor 602 executes the method in above-mentioned any means embodiment.Program
The specific implementation of each step may refer to corresponding description in corresponding steps and unit in above-described embodiment in 610, herein not
It repeats.It is apparent to those skilled in the art that for convenience and simplicity of description, the equipment and mould of foregoing description
The specific work process of block can refer to corresponding processes in the foregoing method embodiment description, and details are not described herein.
Algorithm and display are not inherently related to any particular computer, virtual system, or other device provided herein.
Various general-purpose systems can also be used together with teachings based herein.As described above, it constructs required by this kind of system
Structure be obvious.In addition, the present invention is also not directed to any particular programming language.It should be understood that can use various
Programming language realizes summary of the invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of the various inventive aspects,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. required to protect
Shield the present invention claims features more more than feature expressly recited in each claim.More precisely, as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim itself
All as a separate embodiment of the present invention.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
Meaning one of can in any combination mode come using.
Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors
Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice
Microprocessor or digital signal processor (DSP) come realize some in content recommendation apparatus according to an embodiment of the present invention or
The some or all functions of person's whole component.The present invention is also implemented as one for executing method as described herein
Point or whole device or device programs (for example, computer program and computer program product).Such this hair of realization
Bright program can store on a computer-readable medium, or may be in the form of one or more signals.It is such
Signal can be downloaded from an internet website to obtain, and is perhaps provided on the carrier signal or is provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be through the same hardware branch
To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame
Claim.
Claims (10)
1. a kind of content recommendation method, comprising:
It determines target user, inquires user's calling hierarchy of the target user prestored in database;
It determines the object content of at least one shops to be recommended, inquires the door of at least one shops prestored in database
Shop grade;
User's calling hierarchy of the target user is matched with shops's grade of at least one shops, according to matching
As a result selection obtains object content to be recommended from the object content of at least one shops;
The object content to be recommended is pushed to the target user.
2. according to the method described in claim 1, wherein, user's calling hierarchy by the target user and it is described at least
Shops's grade of one shops is matched, and selects to obtain from the object content of at least one shops according to matching result
Object content to be recommended further comprises:
Judge whether user's calling hierarchy of the target user matches with shops's grade of any shops;
If so, selecting the object content of the shops to match as object content to be recommended;
If it is not, then selecting shops's grade higher than the object content of the shops of user's calling hierarchy as object content to be recommended.
3. method according to claim 1 or 2, wherein before determining target user, the method also includes:
Evaluation information is obtained, shops's grade and user's calling hierarchy are determined according to evaluation information, shops's grade and user are required
Grade saves in the database.
4. described to determine shops's grade and user's calling hierarchy according to evaluation information according to the method described in claim 3, wherein
Further comprise:
Shops's cluster to be graded is determined, for each shops in shops's cluster to be graded, according to the evaluation information meter of the shops
Calculate the 1st wheel shops's grade of the shops;
It determines to Ratings User cluster, for each user in Ratings User cluster, according to the evaluation information meter of the user
Calculate the 1st wheel user's calling hierarchy of the user;
Using the 1st wheel shops's grade and the 1st wheel user's calling hierarchy as initial value, according to described in Ratings User cluster
Each user treats the evaluation information of each shops in grading shops's cluster, carries out number wheel iteration adjustment to initial value, final true
Shops's grade of each shops and user's requirement to each user in Ratings User cluster etc. in fixed shops's cluster to be graded
Grade.
5. according to the method described in claim 4, wherein, it is described according to each user in Ratings User cluster to be evaluated
The evaluation information of each shops in grade shops cluster carries out number wheel iteration adjustment to initial value, final to determine shops's collection to be graded
Shops's grade of each shops and user's calling hierarchy to each user in Ratings User cluster further comprise in group: from
I=2 starts,
S1 believes for each shops in shops's cluster to be graded according to the evaluation of (i-1)-th wheel user's calling hierarchy and the shops
Breath calculates i-th wheel shops's grade of the shops, and for each user in Ratings User cluster, takes turns door according to (i-1)-th
The evaluation information of shop grade and the user calculate i-th wheel user's calling hierarchy of the user;
S2 judges whether i-th wheel shops's grade of each shops and (i-1)-th wheel shops's grade are identical, and the i-th wheel of each user
Whether user's calling hierarchy and (i-1)-th wheel user's calling hierarchy are identical;
S3, if so, i-th wheel shops's grade of each shops to be ultimately determined to shops's grade of each shops, and will be each
I-th wheel user's calling hierarchy of a user is ultimately determined to user's calling hierarchy of each user, and iteration adjustment process terminates;
S4 is jumped if it is not, i is then assigned a value of i+1 and is executed step S1.
6. according to the method described in claim 5, wherein, each shops in shops's cluster to be graded, according to the
I-th wheel shops's grade that i-1 wheel user's calling hierarchy and the evaluation information of the shops calculate the shops further comprises:
Determine the assessment grade of every evaluation information of the shops;
(i-1)-th wheel user's calling hierarchy that user is corresponded to according to the assessment grade of every evaluation information and every evaluation information, is pressed
Every evaluation information is sorted out according to the first classifying rules;
The categorization results of each evaluation information based on the shops calculate the i-th wheel shops of the shops using the first preset rules
Grade.
7. according to the method described in claim 6, wherein, the categorization results of each evaluation information based on the shops are sharp
Further comprise with i-th wheel shops's grade that the first preset rules calculate the shops:
The item number accounting of evaluation information at least one pre-set categories obtained after being sorted out according to the first classifying rules is calculated,
I-th wheel shops's grade of shops is calculated according to the item number accounting.
8. a kind of content recommendation device, comprising:
First determining module, is adapted to determine that target user;
First enquiry module, suitable for inquiring user's calling hierarchy of the target user prestored in database;
Second determining module is adapted to determine that the object content of at least one shops to be recommended;
Second enquiry module, suitable for inquire database in prestore described at least one shops shops's grade;
Processing module, suitable for carrying out shops's grade of user's calling hierarchy of the target user and at least one shops
Matching, selects to obtain object content to be recommended from the object content of at least one shops according to matching result;
Pushing module, suitable for the object content to be recommended is pushed to the target user.
9. a kind of calculating equipment, comprising: processor, memory, communication interface and communication bus, the processor, the storage
Device and the communication interface complete mutual communication by the communication bus;
The memory executes the processor as right is wanted for storing an at least executable instruction, the executable instruction
Ask the corresponding operation of content recommendation method described in any one of 1-7.
10. a kind of computer storage medium, an at least executable instruction, the executable instruction are stored in the storage medium
Processor is set to execute such as the corresponding operation of content recommendation method of any of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811552763.1A CN109711875B (en) | 2018-12-19 | 2018-12-19 | Content recommendation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811552763.1A CN109711875B (en) | 2018-12-19 | 2018-12-19 | Content recommendation method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109711875A true CN109711875A (en) | 2019-05-03 |
CN109711875B CN109711875B (en) | 2021-04-20 |
Family
ID=66256709
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811552763.1A Active CN109711875B (en) | 2018-12-19 | 2018-12-19 | Content recommendation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109711875B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110297987A (en) * | 2019-07-02 | 2019-10-01 | 武汉斗鱼网络科技有限公司 | A kind of model recommended method, device, equipment and storage medium |
CN111695084A (en) * | 2020-04-26 | 2020-09-22 | 北京奇艺世纪科技有限公司 | Model generation method, credit score generation method, device, equipment and storage medium |
CN112508649A (en) * | 2020-12-11 | 2021-03-16 | 北京首汽智行科技有限公司 | Recommendation method for vehicle rental commercial tenants |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130046689A1 (en) * | 2011-08-16 | 2013-02-21 | Bank Of America Corporation | System and Method for Facilitating Transactions |
CN103927324A (en) * | 2014-03-13 | 2014-07-16 | 中国联合网络通信集团有限公司 | Method and device for information pushing |
CN104463617A (en) * | 2014-10-30 | 2015-03-25 | 中英融贯资讯(武汉)有限公司 | Method and system for intelligently matching commercial tenant range |
CN105718535A (en) * | 2016-01-15 | 2016-06-29 | 深圳大学 | Online scoring method and system |
CN106408377A (en) * | 2016-08-31 | 2017-02-15 | 广东华邦云计算股份有限公司 | Shopping recommended method and system |
CN106991584A (en) * | 2017-04-10 | 2017-07-28 | 山东科技大学 | A kind of electronic commerce credits computational methods based on scoring person's impression |
CN108280729A (en) * | 2017-01-06 | 2018-07-13 | 中兴通讯股份有限公司 | A kind of food preparation method and device |
CN108415992A (en) * | 2018-02-12 | 2018-08-17 | 百度在线网络技术(北京)有限公司 | Resource recommendation method, device and computer equipment |
-
2018
- 2018-12-19 CN CN201811552763.1A patent/CN109711875B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130046689A1 (en) * | 2011-08-16 | 2013-02-21 | Bank Of America Corporation | System and Method for Facilitating Transactions |
CN103927324A (en) * | 2014-03-13 | 2014-07-16 | 中国联合网络通信集团有限公司 | Method and device for information pushing |
CN104463617A (en) * | 2014-10-30 | 2015-03-25 | 中英融贯资讯(武汉)有限公司 | Method and system for intelligently matching commercial tenant range |
CN105718535A (en) * | 2016-01-15 | 2016-06-29 | 深圳大学 | Online scoring method and system |
CN106408377A (en) * | 2016-08-31 | 2017-02-15 | 广东华邦云计算股份有限公司 | Shopping recommended method and system |
CN108280729A (en) * | 2017-01-06 | 2018-07-13 | 中兴通讯股份有限公司 | A kind of food preparation method and device |
CN106991584A (en) * | 2017-04-10 | 2017-07-28 | 山东科技大学 | A kind of electronic commerce credits computational methods based on scoring person's impression |
CN108415992A (en) * | 2018-02-12 | 2018-08-17 | 百度在线网络技术(北京)有限公司 | Resource recommendation method, device and computer equipment |
Non-Patent Citations (1)
Title |
---|
卢建昌 等: "《电力企业管理》", 31 August 2007, 中国电力出版社 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110297987A (en) * | 2019-07-02 | 2019-10-01 | 武汉斗鱼网络科技有限公司 | A kind of model recommended method, device, equipment and storage medium |
CN111695084A (en) * | 2020-04-26 | 2020-09-22 | 北京奇艺世纪科技有限公司 | Model generation method, credit score generation method, device, equipment and storage medium |
CN112508649A (en) * | 2020-12-11 | 2021-03-16 | 北京首汽智行科技有限公司 | Recommendation method for vehicle rental commercial tenants |
CN112508649B (en) * | 2020-12-11 | 2024-03-15 | 北京首汽智行科技有限公司 | Recommendation method for vehicle leasing merchant |
Also Published As
Publication number | Publication date |
---|---|
CN109711875B (en) | 2021-04-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20180341898A1 (en) | Demand forecast | |
CN104933591B (en) | A kind of method and device that advertisement dispensing is realized based on real time data | |
CN109711875A (en) | Content recommendation method and device | |
CN103578010A (en) | Method and device generating flow quality comparison parameters and advertisement billing method | |
CN109255007A (en) | Geographical space basic data sharing method and device based on block chain | |
CN107679103B (en) | Attribute analysis method and system for entity | |
CN109272360B (en) | Intelligent advertisement recommendation method, system and device | |
CN108765094A (en) | Insurance data processing method, device, computer equipment and storage medium | |
CN107067282B (en) | Consumer product rebate sale marketing management system and use method thereof | |
US8010399B1 (en) | Methods, systems, and articles of manufacture for analyzing initiatives for a business network | |
CN109615410B (en) | Data processing method and device, computer equipment and computer readable storage medium | |
CN111242318A (en) | Business model training method and device based on heterogeneous feature library | |
CN107633257A (en) | Data Quality Assessment Methodology and device, computer-readable recording medium, terminal | |
CN117172633B (en) | Manufacturing service subgraph simulation method and system for industrial Internet platform | |
CN110264364B (en) | Recommendation method for investor | |
CN108446923B (en) | Task pricing method based on self-service labor crowdsourcing platform | |
CN108460630B (en) | Method and device for carrying out classification analysis based on user data | |
CN116151460A (en) | Optimization method and device for intelligent vehicle product, server and storage medium | |
CN104462412A (en) | Keyword detection method and device for release of internet keywords | |
CN109325795A (en) | The application method of store discount coupon and the application system of store discount coupon | |
CN104486313A (en) | Method and device for detecting delivery of network multimedia file | |
CN114723373A (en) | Distribution scheduling management method, device, equipment and storage medium for health care products | |
CN113902470A (en) | Advertisement experiment platform and method and electronic equipment | |
TW201516925A (en) | Assembly and charge system of processing composite discount and the method thereof | |
Bjelica et al. | Enhancing IT project management maturity assessment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |