CN107632984A - A kind of cluster data table shows methods, devices and systems - Google Patents
A kind of cluster data table shows methods, devices and systems Download PDFInfo
- Publication number
- CN107632984A CN107632984A CN201610565869.XA CN201610565869A CN107632984A CN 107632984 A CN107632984 A CN 107632984A CN 201610565869 A CN201610565869 A CN 201610565869A CN 107632984 A CN107632984 A CN 107632984A
- Authority
- CN
- China
- Prior art keywords
- business object
- similarity
- information
- degree
- association
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
What the embodiment of the present application provided a kind of cluster data table shows methods, devices and systems, and methods described includes:Receive cluster data table shows request, shows cluster data table according to the request;The cluster data table includes multiple business object set, the business object set has the business object of multiple associations, and, corresponding subject information, so as to rapidly identify user's request, show the business object for meeting user's request, reduce user's search or search the time of business object, the resource cost of the system caused by searching for or searching business object is saved, improves access efficiency.
Description
Technical field
The application is related to areas of information technology, more particularly to a kind of generation method of cluster data table, a kind of cluster numbers
Show method, a kind of demonstration device of cluster data table and a kind of cluster numbers according to the generating means of table, a kind of cluster data table
Show system according to table.
Background technology
The progress of technology has promoted the development of ecommerce.Nowadays, the e-commerce website such as Taobao, day cat have been able to by
Commodity all over the world collect on the net, are chosen for consumer.But in face of the numerous commodity of category, consumer may be not
It is to be worth purchase to understand which commodity.Therefore, part e-commerce website starts actively to consumer's Recommendations, to reduce
Consumer's search, the time of the free choice of goods, show that recommended commodity are wherein to the consumer group in a manner of inventory
One of important way.Inventory is generally made up of three parts:
(1) items list:The list contains a series of similar commodity, for example, the inventory of clothes can be same style
Clothes, trousers and shoes collocation, the inventory of household can be combination of the curtain of same tone, wallpaper and carpet, etc..
(2) inventory title:The title is a short text, can be used for describing the characteristic of items list, for example, clothes
The title of inventory can be " small pure and fresh spring ", " the collocation control of pink colour system " etc..
(3) inventory describes:Inventory description can be a bit of straightaway word, for entering traveling one to inventory title
The elaboration of step, such as the inventory of entitled " holding in oneself rice bowl on hand ", its description can be that " china bowl is most healthy, no
Same size, different decorative patterns, can allow dining table to add much beauty to ", the commodity recommended with facilitating consumer to understand in inventory.
At present, the inventory of e-commerce website relies primarily on the manual operation of website operation personnel to realize
, by obtaining the consumption data of consumer, and the public sentiment statistics of external website is combined, by manual analysis, determined
The commodity to be recommended, and then by the grouping of commodities recommended in inventory, and extract the title and descriptive statement of inventory.But
It is that the above method needs to expend substantial amounts of human cost, subjectivity of the inventory formed with heavier operation personnel
Hobby, possibly can not meet the needs of most consumers and preference.
The content of the invention
In view of the above problems, it is proposed that the embodiment of the present application overcomes above mentioned problem or at least in part to provide one kind
A kind of generation method of the cluster data table to solve the above problems, a kind of generating means of cluster data table, a kind of cluster data
Table show method, a kind of demonstration device of cluster data table and a kind of cluster data table show system.
In order to solve the above problems, this application discloses a kind of system that shows of cluster data table, including:
One or more processors;
Memory;With,
One or more modules, one or more of modules are stored in the memory and are configured to by described one
Individual or multiple computing devices, wherein, one or more of modules have following function:
Receive cluster data table shows request;
Show cluster data table according to the request, the cluster data table includes multiple business object set, the industry
Business object set has the business object of multiple associations, and, corresponding subject information.
In order to solve the above problems, show method disclosed herein as well is a kind of cluster data table, it is characterised in that bag
Include:
Receive cluster data table shows request;
Show cluster data table according to the request;The cluster data table includes multiple business object set, the industry
Business object set has the business object of multiple associations, and, corresponding subject information.
Alternatively, the multiple business object set generates as follows:
Multiple business objects are obtained, the multiple business object has corresponding attribute information respectively;
According to the attribute information of the multiple business object, the degree of association between the multiple business object is determined;
According to the degree of association between the multiple business object, the multiple business object is classified, obtained multiple
Business object set.
Alternatively, title of the attribute information of the multiple business object including multiple business objects, pricing information, consumption
Person's information, brand message, category information, and/or, pictorial information;The attribute information according to the multiple business object, really
The step of determining the degree of association between the multiple business object includes:
Title similarity, price similarity, consumer's similarity, the brand between any two business object are determined respectively
Similarity, classification similarity, and/or, picture similarity;
According to the title similarity, price similarity, consumer's similarity, brand similarity, classification similarity, and/
Or, picture similarity, the degree of association between any two business object is determined respectively.
Alternatively, it is described according to the title similarity, price similarity, consumer's similarity, brand similarity, classification
Similarity, and/or, picture similarity, respectively determine any two business object between the degree of association the step of include:
To the title similarity, price similarity, consumer's similarity, brand similarity, classification similarity, and/or,
Picture Similarity-Weighted is summed, and obtains the degree of association between any two business object.
Alternatively, the degree of association according between the multiple business object, divides the multiple business object
Class, the step of obtaining multiple business object set, include:
The business object that the degree of association is more than to predetermined threshold value respectively is combined, and obtains multiple business object set.
Alternatively, the subject information includes the heading message and description information of the business object set, the theme
Information generates as follows:
Obtain the attribute information of the business object of multiple associations in the business object set;
According to the attribute information, the heading message of the business object set is determined;
According to the heading message, the description information of the business object set is determined.
Alternatively, it is described according to the attribute information, include the step of the heading message for determining the business object set:
Obtain the keyword in the attribute information of the business object of multiple associations;
The keyword is ranked up, obtains the target keyword of the first predetermined number;
Template is preset using the target keyword and first, determines the heading message of the business object set.
Alternatively, it is described according to the heading message, include the step of the description information for determining the business object set:
Obtain the comment information corresponding with the heading message;
According to the comment information, the description information of the business object set is determined.
Alternatively, described the step of obtaining the comment information corresponding with the heading message, includes:
The heading message is segmented, obtains one or more participle phrases;
The comment information to match with one or more of participle phrases is obtained respectively.
Alternatively, it is described according to the comment information, include the step of the description information for determining the business object set:
The comment information is ranked up, obtains the target comment information of the second predetermined number;
Template is preset using the target comment information and second, determines the description information of the business object set.
Alternatively, user's request information is also included in the request, it is described to show cluster data table according to the request
Step includes:
Obtain multiple target service object sets with user's request information match;
Show the multiple target service object set.
In order to solve the above problems, disclosed herein as well is a kind of generation method of cluster data table, it is characterised in that bag
Include:
Multiple business objects are obtained, the multiple business object has corresponding attribute information respectively;
According to the attribute information of the multiple business object, the degree of association between the multiple business object is determined;
According to the degree of association between the multiple business object, the multiple business object is classified, obtained multiple
Business object set, the multiple business object set have the business object of multiple associations respectively;
According to the business object of the multiple association, determine that theme corresponding to the multiple business object set is believed respectively
Breath;
According to the multiple business object set, and, corresponding subject information, generate cluster data table.
Alternatively, title of the attribute information of the multiple business object including multiple business objects, pricing information, consumption
Person's information, brand message, category information, and/or, pictorial information;The attribute information according to the multiple business object, really
The step of determining the degree of association between the multiple business object includes:
Title similarity, price similarity, consumer's similarity, the brand between any two business object are determined respectively
Similarity, classification similarity, and/or, picture similarity;
According to the title similarity, price similarity, consumer's similarity, brand similarity, classification similarity, and/
Or, picture similarity, the degree of association between any two business object is determined respectively.
Alternatively, it is described according to the title similarity, price similarity, consumer's similarity, brand similarity, classification
Similarity, and/or, picture similarity, respectively determine any two business object between the degree of association the step of include:
To the title similarity, price similarity, consumer's similarity, brand similarity, classification similarity, and/or,
Picture Similarity-Weighted is summed, and obtains the degree of association between any two business object.
Alternatively, the degree of association according between the multiple business object, divides the multiple business object
Class, the step of obtaining multiple business object set, include:
The business object that the degree of association is more than to predetermined threshold value respectively is combined, and obtains multiple business object set.
Alternatively, the business object according to the multiple association, the multiple business object set pair is determined respectively
The step of subject information answered, includes:
Obtain the attribute information of the business object of multiple associations in the business object set;
According to the attribute information, the heading message of the business object set is determined;
According to the heading message, the description information of the business object set is determined.
Alternatively, it is described according to the attribute information, include the step of the heading message for determining the business object set:
Obtain the keyword in the attribute information of the business object of multiple associations;
The keyword is ranked up, obtains the target keyword of the first predetermined number;
Template is preset using the target keyword and first, determines the heading message of the business object set.
Alternatively, it is described according to the heading message, include the step of the description information for determining the business object set:
Obtain the comment information corresponding with the heading message;
According to the comment information, the description information of the business object set is determined.
Alternatively, described the step of obtaining the comment information corresponding with the heading message, includes:
The heading message is segmented, obtains one or more participle phrases;
The comment information to match with one or more of participle phrases is obtained respectively.
Alternatively, it is described according to the comment information, include the step of the description information for determining the business object set:
The comment information is ranked up, obtains the target comment information of the second predetermined number;
Template is preset using the target comment information and second, determines the description information of the business object set.
In order to solve the above problems, disclosed herein as well is a kind of demonstration device of cluster data table, it is characterised in that bag
Include:
Receiving module, show request for receive cluster data table;
Display module, for showing cluster data table according to the request;The cluster data table includes multiple business pair
As set, the business object set has the business object of multiple associations, and, corresponding subject information.
Alternatively, the multiple business object set is by calling following module to generate:
Business object acquisition module, for obtaining multiple business objects, the multiple business object has corresponding respectively
Attribute information;
Degree of association determining module, for the attribute information according to the multiple business object, determine the multiple business pair
The degree of association as between;
Sort module, for according to the degree of association between the multiple business object, being carried out to the multiple business object
Classification, obtains multiple business object set.
Alternatively, title of the attribute information of the multiple business object including multiple business objects, pricing information, consumption
Person's information, brand message, category information, and/or, pictorial information;The degree of association determining module includes:
Similarity determination sub-module, for determining the title similarity between any two business object, price phase respectively
Like degree, consumer's similarity, brand similarity, classification similarity, and/or, picture similarity;
Degree of association determination sub-module, for according to the title similarity, price similarity, consumer's similarity, brand
Similarity, classification similarity, and/or, picture similarity, the degree of association between any two business object is determined respectively.
Alternatively, the degree of association determination sub-module includes:
Degree of association determining unit, for similar to the title similarity, price similarity, consumer's similarity, brand
Degree, classification similarity, and/or, the summation of picture Similarity-Weighted, obtain the degree of association between any two business object.
Alternatively, the sort module includes:
Submodule is combined, the business object for the degree of association to be more than to predetermined threshold value respectively is combined, and obtains multiple industry
Business object set.
Alternatively, the subject information includes the heading message and description information of the business object set, the theme
Information is by calling following module to generate:
Attribute information acquisition module, the attribute for obtaining the business object of multiple associations in the business object set are believed
Breath;
Heading message determining module, for according to the attribute information, determining the heading message of the business object set;
Description information determining module, for according to the heading message, determining the description information of the business object set.
Alternatively, the heading message determining module includes:
Keyword acquisition submodule, for the keyword in the attribute information for the business object for obtaining multiple associations;
Keyword sorting sub-module, for being ranked up to the keyword, obtain the target critical of the first predetermined number
Word;
Heading message determination sub-module, for using the target keyword and the first default template, determining the industry
The heading message of business object set.
Alternatively, the description information determining module includes:
Comment information acquisition submodule, for obtaining the comment information corresponding with the heading message;
Description information determination sub-module, for according to the comment information, determining that the description of the business object set is believed
Breath.
Alternatively, the comment information acquisition submodule includes:
Participle unit, for being segmented to the heading message, obtain one or more participle phrases;
Comment information acquiring unit, believe for obtaining the comment to match with one or more of participle phrases respectively
Breath.
Alternatively, the description information determination sub-module includes:
Comment information sequencing unit, for being ranked up to the comment information, the target for obtaining the second predetermined number is commented
By information;
Description information determining unit, for using the target comment information and the second default template, determining the business
The description information of object set.
Alternatively, user's request information is also included in the request, the display module includes:
Target service object set acquisition submodule, for obtaining multiple target services with user's request information match
Object set;
Target service object shows submodule, for showing the multiple target service object set.
In order to solve the above problems, disclosed herein as well is a kind of generating means of cluster data table, it is characterised in that bag
Include:
Acquisition module, for obtaining multiple business objects, the multiple business object has corresponding attribute information respectively;
Degree of association determining module, for the attribute information according to the multiple business object, determine the multiple business pair
The degree of association as between;
Sort module, for according to the degree of association between the multiple business object, being carried out to the multiple business object
Classification, obtains multiple business object set, and the multiple business object set has the business object of multiple associations respectively;
Subject information determining module, for the business object according to the multiple association, the multiple business is determined respectively
Subject information corresponding to object set;
Generation module, for according to the multiple business object set, and, corresponding subject information, generate cluster numbers
According to table.
Alternatively, title of the attribute information of the multiple business object including multiple business objects, pricing information, consumption
Person's information, brand message, category information, and/or, pictorial information;The degree of association determining module includes:
Similarity determination sub-module, for determining the title similarity between any two business object, price phase respectively
Like degree, consumer's similarity, brand similarity, classification similarity, and/or, picture similarity;
Degree of association determination sub-module, for according to the title similarity, price similarity, consumer's similarity, brand
Similarity, classification similarity, and/or, picture similarity, the degree of association between any two business object is determined respectively.
Alternatively, the degree of association determination sub-module includes:
Degree of association determining unit, for similar to the title similarity, price similarity, consumer's similarity, brand
Degree, classification similarity, and/or, the summation of picture Similarity-Weighted, obtain the degree of association between any two business object.
Alternatively, the sort module includes:
Submodule is combined, the business object for the degree of association to be more than to predetermined threshold value respectively is combined, and obtains multiple industry
Business object set.
Alternatively, the subject information determining module includes:
Attribute information acquisition submodule, for obtaining the attribute of the business object of multiple associations in the business object set
Information;
Heading message determination sub-module, for according to the attribute information, determining that the title of the business object set is believed
Breath;
Description information determination sub-module, for according to the heading message, determining that the description of the business object set is believed
Breath.
Alternatively, the heading message determination sub-module includes:
Keyword acquiring unit, for the keyword in the attribute information for the business object for obtaining multiple associations;
Keyword sequencing unit, for being ranked up to the keyword, obtain the target keyword of the first predetermined number;
Heading message determining unit, for using the target keyword and the first default template, determining the business
The heading message of object set.
Alternatively, the description information determination sub-module includes:
Comment information acquiring unit, for obtaining the comment information corresponding with the heading message;
Description information determining unit, for according to the comment information, determining the description information of the business object set.
Alternatively, the comment information acquiring unit includes:
Subelement is segmented, for being segmented to the heading message, obtains one or more participle phrases;
Comment information obtains subelement, believes for obtaining the comment to match with one or more of participle phrases respectively
Breath.
Alternatively, the description information determining unit includes:
Comment information sequence subelement, for being ranked up to the comment information, obtains the target of the second predetermined number
Comment information;
Description information determination subelement, for using the target comment information and the second default template, determining the industry
The description information of business object set.
Compared with background technology, the embodiment of the present application includes advantages below:
The embodiment of the present application, receive cluster data table show request after, can according to it is described request show including
The cluster data table of multiple business object set, can rapidly identify user's request, show the business pair for meeting user's request
As reducing user's search or searching the time of business object, save and be caused by searching for or searching business object
The resource cost of system, improves access efficiency.
Brief description of the drawings
Fig. 1 is a kind of step flow chart of the generation method embodiment one of cluster data table of the application;
Fig. 2 is a kind of step flow chart of the generation method embodiment two of cluster data table of the application;
Fig. 3 is a kind of theory diagram of the generation method embodiment two of cluster data table of the application;
Fig. 4 is a kind of step flow chart for showing embodiment of the method for cluster data table of the application;
Fig. 5 is a kind of exemplary plot of the cluster data table of the application;
Fig. 6 is a kind of structured flowchart of the generating means embodiment of cluster data table of the application;
Fig. 7 is a kind of structured flowchart of the demonstration device embodiment of cluster data table of the application.
Embodiment
It is below in conjunction with the accompanying drawings and specific real to enable the above-mentioned purpose of the application, feature and advantage more obvious understandable
Mode is applied to be described in further detail the application.
Reference picture 1, a kind of step flow chart of the generation method embodiment one of cluster data table of the application is shown, had
Body may include steps of:
Step 101, multiple business objects are obtained, the multiple business object has corresponding attribute information respectively;
In the embodiment of the present application, the business object can be commodity, or other kinds of object, for example, news
Information etc., the application are not construed as limiting to the type of business object.
It should be noted that for different business objects, the attribute information of its corresponding business object is also likely to be not
With.For example, when business object is commodity, the attribute information can be the titles of commodity, price, consumer, affiliated product
Board, specific classification, and/or, the information such as picture.And when business object is Domestic News, the attribute information can be then
The information such as the sources of the Domestic News, time of origin, place.Those skilled in the art can be according to the specific kind of business object
Class, correspondingly selects suitable attribute information, and the application is not especially limited to this.
In the specific implementation, the acquisition of the attribute information for different business objects, can also in different ways,
For example, for the attribute information of commodity, obtained in the commodity data that can have been stored from platforms such as e-commerce websites, and for
The attribute information of Domestic News, then it can be obtained from the information platforms such as information class website.
Step 102, according to the attribute information of the multiple business object, the association between the multiple business object is determined
Degree;
In the embodiment of the present application, after the attribute information of multiple business objects is obtained, any two business can be calculated
The degree of association between object.The degree of association can be by analyzing obtain two from the attribute information of multiple different dimensions
A kind of numerical value description of correlation degree between business object, the correlation degree can embody the phase between two business objects
Like property or Matching Relation, for example, for the different types of shoes with similitude, such as leather shoes and sandals, can be have compared with
The high degree of association, and for the business object with certain Matching Relation, such as clothes and trousers, it is possible to have higher pass
Connection degree.
In the embodiment of the present application, in the title of this business object of acquisition commodity, pricing information, consumer information, product
Board information, category information, and/or, after pictorial information, the title between any two business object can be calculated respectively first
Similarity, price similarity, consumer's similarity, brand similarity, classification similarity, and/or, picture similarity, Ran Hougen
According to the title similarity, price similarity, consumer's similarity, brand similarity, classification similarity, and/or, picture is similar
Degree, determines the degree of association between any two business object.Similarity between different attribute informations can be respectively adopted
Different computational methods, it is for instance possible to use cosine law Cosine formula, or Jie Kade Jaccard similarities etc., this
Apply being not construed as limiting the calculation of specific similarity.
In the specific implementation, when the title similarity, price similarity, consumer that calculate acquisition any two business object
Similarity, brand similarity, classification similarity, and/or, can be similar to the title similarity, price after picture similarity
Degree, consumer's similarity, brand similarity, classification similarity, and/or, picture similarity is weighted summation, so as to take office
The degree of association between two business objects of anticipating.The weight of the similarity of different information dimensions can be adjusted according to being actually needed
It is whole, for example, for clothing commodity, the weight of picture similarity can be increased, and for digital class commodity, then it can increase name
Claim the weight of similarity, to enable the degree of association finally obtained preferably to embody the phase between two different business objects
Like property or collocation property.
Step 103, according to the degree of association between the multiple business object, the multiple business object is classified,
Multiple business object set are obtained, the multiple business object set has the business object of multiple associations respectively;
In the embodiment of the present application, after the degree of association between any two business object is calculated, can respectively by
The business object that the degree of association is more than predetermined threshold value is combined, so as to obtain multiple business object set.In the specific implementation, can
To classify using the method for hierarchical clustering to the multiple business object, multiple business object set are obtained.Hierarchical clustering
It is exactly by carrying out hierachical decomposition according to some way to data set, untill meeting certain condition.According to principle of classification
Difference, two methods of cohesion and division can be divided into.By taking cohesion as an example, the hierarchical clustering of cohesion is a kind of bottom-up plan
Slightly, can be first using each object as a cluster, it is increasing cluster to be then combined with these clusters, until all pairs
As all in a cluster, or some finish condition is satisfied.Hierarchical clustering is a kind of sorting algorithm being widely adopted, this Shen
Please this is repeated no more.
Step 104, according to the business object of the multiple association, determine respectively corresponding to the multiple business object set
Subject information;
In the embodiment of the present application, the subject information can include the heading message of the business object and description is believed
Breath.The heading message of the business object set can embody some common spy of whole business objects in the set
The phrase or short sentence of sign, the description information can be the text messages of the business object in set described in Unify legislation,
It can also be the text message that the heading message is further elaborated.
In a preferred embodiment of the present application, the business object according to the multiple association, institute is determined respectively
The step of stating subject information corresponding to multiple business object set can specifically include following sub-step:
Sub-step 1041, obtain the attribute information of the business object of multiple associations in the business object set;
Sub-step 1042, according to the attribute information, determine the heading message of the business object set;
Sub-step 1043, according to the heading message, determine the description information of the business object set.
In the specific implementation, the attribute information of whole business objects can be obtained, then from the attribute information first
The text message for describing the business object is extracted, for example, the title of commodity, or buyer's guide word etc., then
Keyword is extracted from the text message, by being ranked up to keyword, k keyword for sorting forward is obtained, enters
And the k keyword and default theme template can be used, determine the heading message of the business object set.Right
When keyword is ranked up, it can be carried out according to the occurrence number of keyword, or other modes, the application does not make specifically to this
Limit.
After the heading message of business object set is determined, it can be found out and the title according to the heading message
The comment information to match, is then further filtered out from the comment information found out and the heading message degree of correlation is higher comments
By information, so as to obtain the description information of the business object set.
In the specific implementation, nearly justice can be done to participle short message using semantic model by being segmented to heading message
Word extends, and does text matches to comment data, so as to recall the comment information to match with heading message.Obtaining comment letter
After breath, marking sequence can be carried out to the comment information according to certain rule, so as to using the forward comment information that sorts, make
With default text masterplate, the description information is generated.
Step 105, according to the multiple business object set, and, corresponding subject information, generate cluster data table.
In the embodiment of the present application, can be by institute after business object set and its corresponding subject information is obtained respectively
State business object set and its subject information is merged into a cluster data table, to show to user.
In the embodiment of the present application, by obtaining the attribute information of multiple business objects, so that it is determined that going out multiple business pair
The degree of association as between, and multiple business objects are classified according to the degree of association, multiple business object set are obtained, so
Extract the subject information of the business object set respectively afterwards, and then generate cluster data table, solve in prior art only
Can be by manual operation generation cluster data table the problem of, the formation efficiency of cluster data table is improved, also causes what is generated
Cluster data table is more objective, can more match the demand and preference of most of users.
Reference picture 2, a kind of step flow chart of the generation method embodiment two of cluster data table of the application is shown, had
Body may include steps of:
Step 201, multiple business objects are obtained, the multiple business object has corresponding attribute information respectively;
In the embodiment of the present application, the business object can be commodity, and the attribute information of the business object can be
The title of commodity, price, consumer, affiliated brand, specific classification, and/or, the information such as picture.
As shown in figure 3, it is a kind of theory diagram of the generation method embodiment two of cluster data table of the application.Specific
In realization, for the attribute information of commodity, obtained in the commodity data that can have been stored from platforms such as e-commerce websites.
Step 202, title similarity, price similarity, the consumer's phase between any two business object are determined respectively
Like degree, brand similarity, classification similarity, and/or, picture similarity;
In order to make it easy to understand, below by taking commodity this business objects as an example, it is specific to introduce how to determine any two commodity
Between title similarity, price similarity, consumer's similarity, brand similarity, classification similarity, and/or, picture is similar
Degree.
Title similarity can embody the similitude between the title of any two commodity, specifically, can use text
Jie Kade Jaccard similarities in excavation are calculated, its basic ideas be the identical word in trade name quantity with
Ratio between total word quantity.
For example, if title A is " it is trendy that small tomato customizes women's dress ", title B is " griggles customize women's dress Korea Spro version ", using outstanding person
During card moral Jaccard Similarity Measures, title can be segmented first, then calculate the common factor size and union size of participle,
Wherein title A and title B common factor is " customization " and " women's dress ", is calculated as 2, the union that can similarly obtain title A and title B is big
Small is 6, ratio 2/6=0.33 therebetween, as title similarity.
When setting price similarity, the quantile of same class commodity knock-down price now can be calculated first, then will
The quantile is divided into different class, so as to obtain price similarity.
Specifically, the concluded price of commodity can from small to large be sorted first, then calculates 10 quantiles to 90 points of positions
Number, is divided into 10 class, the concluded price of each commodity can fall so as to statistic in sequence by whole price domain
Into 1-10 this 10 class.If commodity A price grade is 5, and commodity B price grade is 8, then can be calculated
Price similarity between commodity A and commodity B is (8-5)/10=0.3.
Consumer's similarity can calculate by using the algorithm of collaborative filtering, and its basic ideas is by the inclined of consumer
Good and cosine law Cosine formula are calculated.For example, can first according to consumer to the browsing of commodity, collect plus purchase,
Strike a bargain etc. different behaviors to commodity to scoring, if it is 4 points to strike a bargain, it is 3 points to add purchase, collects as 2 points, browses as 1 point, can be with
Obtain consumer-commodity grade form as shown in following table one.
Table one:
Commodity A | Commodity B | |
Consumer 1 | 3 | 4 |
Consumer 2 | 2 | 1 |
Consumer 3 | 3 | 2 |
Then, calculated using cosine law Cosine formula, consumer's similarity between commodity A and commodity B is:(3*4
+ 2*1+3*2)/(SQRT (3^2+2^2+3^2) * SQRT (4^2+1^2+2^2))=0.93.
Whether brand similarity, which directly can belong to same brand by comparing two commodity, obtains.If for example, business
Product A and commodity B belong to first brand, then it is considered that the brand similarity between commodity A and commodity B is 1.
Classification similarity can use the algorithm of association analysis to be calculated, and its basic ideas is in the order of consumer
Also the probability of classification B commodity is bought while statistics purchase classification A commodity.If for example, currently there are two orders, wherein order 1
For classification A/B/C, order 2 is classification B/C/E, and order 3 is classification B/D/F, then knowable to calculating while purchase classification B commodity
Also the probability for buying classification C commodity is 2/3, i.e., order 1 with including classification B/C simultaneously in order 2.
Picture similarity can use SIFT/SURF or deep neural network algorithm that picture is transformed into vector, and then
Similarity is calculated using cosine law Cosine formula or other method, picture similarity can embody the phase between merchandise item
Like property.SIFT, i.e. Scale invariant features transform (Scale-invariant feature transform, SIFT), it is to be used to scheme
As one kind description of process field, this description has scale invariability, can detect key point in the picture.And SURF
(Speeded Up Robust Feature) then refers to the feature with robustness accelerated, and SURF technologies can apply to count
In the object identification of calculation machine vision and 3D reconstruct, SURF operators are improved by SIFT operators.Specifically, commodity figure is being obtained
After piece, the picture that can be changed commanders by the change in data is changed into the vector of similar [1,1,3,4], then using the cosine law
Cosine formula calculate the picture similarity between two commodity.
Above to how to calculate title similarity, price similarity, consumer's similarity, brand similarity, the class of commodity
Mesh similarity, and/or, picture similarity is described respectively, and those skilled in the art can also be used with above-mentioned introduction not
Same other modes carry out the calculating of similarity, and the application is not especially limited to this.
Step 203, according to the title similarity, price similarity, consumer's similarity, brand similarity, classification phase
Like degree, and/or, picture similarity, the degree of association between any two business object is determined respectively;
It is described according to the title similarity, price similarity, consumer's phase in a preferred embodiment of the present application
Like degree, brand similarity, classification similarity, and/or, picture similarity, the pass between any two business object is determined respectively
The step of connection is spent can specifically include following sub-step:
Sub-step 2031, to the title similarity, price similarity, consumer's similarity, brand similarity, classification phase
Like degree, and/or, the summation of picture Similarity-Weighted, obtain the degree of association between any two business object.
In the specific implementation, when the title similarity, price similarity, consumer that calculate acquisition any two business object
Similarity, brand similarity, classification similarity, and/or, can be similar to the title similarity, price after picture similarity
Degree, consumer's similarity, brand similarity, classification similarity, and/or, picture similarity is weighted summation, so as to take office
The degree of association between two business objects of anticipating.The weight of the similarity of different information dimensions can be adjusted according to being actually needed
It is whole, for example, for clothing commodity, the weight of picture similarity can be increased, and for digital class commodity, then it can increase name
Claim the weight of similarity, to enable the degree of association finally obtained preferably to embody the phase between two different business objects
Like property or collocation property.
Step 204, the business object that the degree of association is more than to predetermined threshold value respectively is combined, and obtains multiple business object collection
Close;
In the specific implementation, can be clustered using hierarchy clustering method based on the degree of association, so as to by the whole of acquisition
Business object is divided into different classification, and each of which classification is a business object set.
Step 205, the attribute information of the business object of multiple associations in the business object set is obtained;
Step 206, according to the attribute information, the heading message of the business object set is determined;
Generally, the heading message of the business object set can be certain that can embody whole business objects in the set
The phrase or short sentence of one common trait.In the specific implementation, the attribute information of whole business objects can be obtained, so first
The text message for describing the business object is extracted from the attribute information afterwards, for example, the title of commodity, or commodity
Word etc. is introduced, then according to the text message, determines the heading message of business object set.
It is described according to the attribute information in a preferred embodiment of the present application, determine the business object set
Heading message the step of can specifically include following sub-step:
Sub-step 2061, the keyword in the attribute information for the business object for obtaining multiple associations;
Sub-step 2062, the keyword is ranked up, obtains the target keyword of the first predetermined number;
Sub-step 2063, using the target keyword and the first default template, determine the business object set
Heading message.
In the specific implementation, can be divided first by the title of the commodity of acquisition or with the attribute informations such as word are introduced
Word, corresponding keyword is obtained, then using existing statistic algorithm, the keyword is ranked up, obtain sorting forward
K keyword, and then the k keyword and default theme template can be used, determine the mark of the business object
Inscribe information.For example, obtain predetermined number keyword after, can use template " XX XX ", or " teach you how XXX "
Deng generating the heading message of the business object., can be true according to being actually needed in the selection of the keyword of predetermined number
Fixed, the application is not especially limited to this.For example, selection two or three keywords, are then obtained using corresponding template
The heading message of business object.
The existing statistic algorithm can be TF-IDF (term frequency-inverse document
Frequency, the conventional weighting technique of information retrieval data mining) algorithm or TextRank algorithm etc., the application couple
This is not especially limited.
Step 207, according to the heading message, the description information of the business object set is determined;
It is described according to the heading message in a preferred embodiment of the present application, determine the business object set
Description information the step of can specifically include following sub-step:
Sub-step 2071, obtain the comment information corresponding with the heading message;
Sub-step 2072, according to the comment information, determine the description information of the business object set.
In the specific implementation, after the heading message of business object set is determined, can continue to search for out and the mark
The related comment information of information is inscribed, and then the description information of business object set is determined according to the comment information.
The sub-step for obtaining the comment information corresponding with the heading message may further include:
The subject information is segmented, obtains one or more participle phrases;
Obtain the comment information to match with one or more of participle phrases.
In the specific implementation, one or more participle phrases, Ran Houli can be obtained by being segmented to heading message
Near synonym extension is done to one or more of participle short messages with semantic model, and text matches are done to comment data, so as to call together
Return the comment information to match with heading message.
It is described according to the comment information, determine that the sub-step of the description information of the business object set can be further
Including:
The comment information is ranked up, obtains the target comment information of the second predetermined number;
Template is preset using the target comment information and second, determines the description information of the business object set.
In the specific implementation, after comment information is obtained, deep learning and the mode manually marked can be utilized, to comment
Information carries out marking and queuing, so as to using the comment information for the forward predetermined number that sorts, use default text masterplate, generation
The description information of the business object set.So that different business object set corresponds to different description informations.
For example, for business object set 1, its description information can be:It always can't stop and like for exquisite thing;It is right
In business object set 2, its description information can be:Sampled tea when chatting, this is how satisfied life;And for business pair
As set 3, its description information can be:The man for wearing shirt is definitely most handsome.
Step 208, according to the multiple business object set, and, corresponding heading message, description information, generation gather
Class tables of data.
In the embodiment of the present application, can be with after business object set and its heading message and description information is obtained respectively
The business object set and its heading message and description information are merged into a cluster data table.For commodity, institute
It is set and its title and the inventory of description for including different commodity to state cluster data table.
In the embodiment of the present application, inventory, Neng Gouli are generated by using based on figure cluster and information extraction algorithm
Effective commodity data and comment data are automatically obtained comprising items list, title and the inventory of description, greatly improve business
The formation efficiency of product inventory.
Reference picture 4, a kind of step flow chart for showing embodiment of the method for cluster data table of the application is shown, specifically
It may include steps of:
Step 401, receive cluster data table shows request;
Step 402, cluster data table is showed according to the request;The cluster data table includes multiple business object collection
To close, the business object set has the business object of multiple associations, and, corresponding subject information.
In the embodiment of the present application, can be according to the request generation when receiving after showing request of cluster data table
Cluster data table, so as to which the cluster data table is presented into user.
Specific manifestation form of the application to cluster data table is not construed as limiting, and the cluster data table can include multiple industry
Business object set, the business object of multiple associations can be included in the business object set, and, corresponding theme letter
Breath.As shown in figure 5, being a kind of exemplary plot of the cluster data table of the application, multiple different inventorys shown in Fig. 5 are
For different business object set, different commodity can be included in the inventory, and according to the different business
The subject information of product generation, the subject information include the title of inventory, and retouching for the different commodity
State information.
In the embodiment of the present application, the multiple business object set can generate as follows:
S11, obtains multiple business objects, and the multiple business object has corresponding attribute information respectively;
S12, according to the attribute information of the multiple business object, determine the degree of association between the multiple business object;
In the embodiment of the present application, the attribute information of the multiple business object can include the name of multiple business objects
Title, pricing information, consumer information, brand message, category information, and/or, pictorial information;It is described according to the multiple business
The attribute information of object, the step of determining the degree of association between the multiple business object, can specifically include following sub-step:
Sub-step S121, respectively determine any two business object between title similarity, price similarity, consumer
Similarity, brand similarity, classification similarity, and/or, picture similarity;
Sub-step S122, according to the title similarity, price similarity, consumer's similarity, brand similarity, classification
Similarity, and/or, picture similarity, the degree of association between any two business object is determined respectively.
Further, it is described according to the title similarity, price similarity, consumer's similarity, brand similarity, class
Mesh similarity, and/or, picture similarity, determine that the sub-step of the degree of association between any two business object can wrap respectively
Include:
To the title similarity, price similarity, consumer's similarity, brand similarity, classification similarity, and/or,
Picture Similarity-Weighted is summed, and obtains the degree of association between any two business object.
Because sub-step S121-S122 is similar with step 202-203 in embodiment two, can refer to mutually, the present embodiment
This is repeated no more.
S13, according to the degree of association between the multiple business object, the multiple business object is classified, obtained
Multiple business object set.
In the specific implementation, can use hierarchical clustering method the multiple business object is classified, obtain more
Individual business object set.
In the embodiment of the present application, the subject information can generate as follows:
S21, obtain the attribute information of the business object of multiple associations in the business object set;
S22, according to the attribute information, determine the heading message of the business object set;
Generally, the heading message of the business object set can be certain that can embody whole business objects in the set
The phrase or short sentence of one common trait.Specifically, it is described according to the attribute information, determine the business object set
The step of heading message, can include following sub-step:
Sub-step S221, the keyword in the attribute information for the business object for obtaining multiple associations;
Sub-step S222, the keyword is ranked up, obtains the target keyword of the first predetermined number;
Sub-step S223, using the target keyword and the first default template, determine the business object set
Heading message.
In the specific implementation, can be divided first by the title of the commodity of acquisition or with the attribute informations such as word are introduced
Word, corresponding keyword is obtained, then using existing statistic algorithm, the keyword is ranked up, obtain sorting forward
K keyword, and then the k keyword and default theme template can be used, determine the mark of the business object
Inscribe information.For example, obtain predetermined number keyword after, can use template " XX XX ", or " teach you how XXX "
Deng generating the heading message of the business object., can be true according to being actually needed in the selection of the keyword of predetermined number
Fixed, the application is not especially limited to this.For example, selection two or three keywords, are then obtained using corresponding template
The heading message of business object.
The existing statistic algorithm can be TF-IDF (term frequency-inverse document
Frequency, the conventional weighting technique of information retrieval data mining) algorithm or TextRank algorithm etc., the application couple
This is not especially limited.
S23, according to the heading message, determine the description information of the business object set.
Generally, the description information can be the text message of the business object in set described in Unify legislation, may be used also
To be the text message that the heading message is further elaborated.Specifically, it is described according to the heading message, determine institute
The step of stating the description information of business object set can include following sub-step:
S231, obtain the comment information corresponding with the heading message;
In the specific implementation, one or more participle phrases, Ran Houli can be obtained by being segmented to heading message
Near synonym extension is done to one or more of participle short messages with semantic model, and text matches are done to comment data, so as to call together
Return the comment information to match with heading message.
S232, according to the comment information, determine the description information of the business object set.
In the specific implementation, after comment information is obtained, deep learning and the mode manually marked can be utilized, to comment
Information carries out marking and queuing, so as to using the comment information for the forward predetermined number that sorts, use default text masterplate, generation
The description information of the business object set.So that different business object set corresponds to different description informations.
In a preferred embodiment of the present application, described the step of showing cluster data table according to the request, specifically may be used
With including following sub-step:
Sub-step 4021, obtain multiple target service object sets with user's request information match;
Sub-step 4022, show the multiple target service object set.
User's request information can also be included in the specific implementation, showing the request of cluster data table, so as to generate
After cluster data table, multiple target service object sets with user's request information match can be got, then by described in
Multiple target service object sets are presented to user.
The user's request information can be that formerly the record that browses or search for of business object is obtained according to user, example
Such as, can be the clothes that user's generation includes the commodity such as overcoat, trousers, shoes after user browses or has searched for an overcoat
The inventory of class;Certainly, user's request information can also be what is obtained according to other modes, and the application is not construed as limiting to this.
In the embodiment of the present application, receive cluster data table show request after, can according to it is described request show
Include the cluster data table of multiple business object set, can rapidly identify user's request, show the industry for meeting user's request
Business object, reduce user's search or search the time of business object, save caused by searching for or searching business object
System resource cost, improve access efficiency.
It should be noted that for embodiment of the method, in order to be briefly described, therefore it is all expressed as to a series of action group
Close, but those skilled in the art should know, the embodiment of the present application is not limited by described sequence of movement, because according to
According to the embodiment of the present application, some steps can use other orders or carry out simultaneously.Secondly, those skilled in the art also should
Know, embodiment described in this description belongs to preferred embodiment, and involved action not necessarily the application is implemented
Necessary to example.
Reference picture 6, a kind of structured flowchart of the generating means embodiment of cluster data table of the application is shown, specifically may be used
With including following module:
Acquisition module 601, for obtaining multiple business objects, there is the multiple business object corresponding attribute to believe respectively
Breath;
Degree of association determining module 602, for the attribute information according to the multiple business object, determine the multiple business
The degree of association between object;
Sort module 603, for according to the degree of association between the multiple business object, entering to the multiple business object
Row classification, obtains multiple business object set, and the multiple business object set has the business object of multiple associations respectively;
Subject information determining module 604, for the business object according to the multiple association, the multiple industry is determined respectively
Subject information corresponding to business object set;
Generation module 605, for according to the multiple business object set, and, corresponding subject information, generation cluster
Tables of data.
In the embodiment of the present application, the attribute information of the multiple business object can include the name of multiple business objects
Title, pricing information, consumer information, brand message, category information, and/or, pictorial information;The degree of association determining module 602
Following submodule can specifically be included:
Similarity determination sub-module, for determining the title similarity between any two business object, price phase respectively
Like degree, consumer's similarity, brand similarity, classification similarity, and/or, picture similarity;
Degree of association determination sub-module, for according to the title similarity, price similarity, consumer's similarity, brand
Similarity, classification similarity, and/or, picture similarity, the degree of association between any two business object is determined respectively.
In the embodiment of the present application, the degree of association determination sub-module can specifically include such as lower unit:
Degree of association determining unit, for similar to the title similarity, price similarity, consumer's similarity, brand
Degree, classification similarity, and/or, the summation of picture Similarity-Weighted, obtain the degree of association between any two business object.
In the embodiment of the present application, the sort module 603 can specifically include following submodule:
Submodule is combined, the business object for the degree of association to be more than to predetermined threshold value respectively is combined, and obtains multiple industry
Business object set.
In the embodiment of the present application, the subject information determining module 604 can specifically include following submodule:
Attribute information acquisition submodule, for obtaining the attribute of the business object of multiple associations in the business object set
Information;
Heading message determination sub-module, for according to the attribute information, determining that the title of the business object set is believed
Breath;
Description information determination sub-module, for according to the heading message, determining that the description of the business object set is believed
Breath.
In the embodiment of the present application, the heading message determination sub-module can specifically include such as lower unit:
Keyword acquiring unit, for the keyword in the attribute information for the business object for obtaining multiple associations;
Keyword sequencing unit, for being ranked up to the keyword, obtain the target keyword of the first predetermined number;
Heading message determining unit, for using the target keyword and the first default template, determining the business
The heading message of object set.
In the embodiment of the present application, the description information determination sub-module can specifically include such as lower unit:
Comment information acquiring unit, for obtaining the comment information corresponding with the heading message;
Description information determining unit, for according to the comment information, determining the description information of the business object set.
In the embodiment of the present application, the comment information acquiring unit can specifically include following subelement:
Subelement is segmented, for being segmented to the heading message, obtains one or more participle phrases;
Comment information obtains subelement, believes for obtaining the comment to match with one or more of participle phrases respectively
Breath.
In the embodiment of the present application, the description information determining unit can specifically include following subelement:
Comment information sequence subelement, for being ranked up to the comment information, obtains the target of the second predetermined number
Comment information;
Description information determination subelement, for using the target comment information and the second default template, determining the industry
The description information of business object set.
Reference picture 7, a kind of structured flowchart of the demonstration device embodiment of cluster data table of the application is shown, specifically may be used
With including following module:
Receiving module 701, show request for receive cluster data table;
Display module 702, for showing cluster data table according to the request;The cluster data table can include multiple
Business object set, the business object set have the business object of multiple associations, and, corresponding subject information.
In the embodiment of the present application, the multiple business object set can be by calling following module to generate:
Business object acquisition module 703, for obtaining multiple business objects, the multiple business object has corresponding respectively
Attribute information;
Degree of association determining module 704, for the attribute information according to the multiple business object, determine the multiple business
The degree of association between object;
Sort module 705, for according to the degree of association between the multiple business object, entering to the multiple business object
Row classification, obtains multiple business object set.
In the embodiment of the present application, the attribute information of the multiple business object can include the name of multiple business objects
Title, pricing information, consumer information, brand message, category information, and/or, pictorial information;The degree of association determining module 704
Following submodule can specifically be included:
Similarity determination sub-module, for determining the title similarity between any two business object, price phase respectively
Like degree, consumer's similarity, brand similarity, classification similarity, and/or, picture similarity;
Degree of association determination sub-module, for according to the title similarity, price similarity, consumer's similarity, brand
Similarity, classification similarity, and/or, picture similarity, the degree of association between any two business object is determined respectively.
In the embodiment of the present application, the degree of association determination sub-module can specifically include such as lower unit:
Degree of association determining unit, for similar to the title similarity, price similarity, consumer's similarity, brand
Degree, classification similarity, and/or, the summation of picture Similarity-Weighted, obtain the degree of association between any two business object.
In the embodiment of the present application, the sort module 705 can specifically include following submodule:
Submodule is combined, the business object for the degree of association to be more than to predetermined threshold value respectively is combined, and obtains multiple industry
Business object set.
In the embodiment of the present application, the subject information can include heading message and the description of the business object set
Information, the subject information can be by calling following module to generate:
Attribute information acquisition module 706, for obtaining the category of the business object of multiple associations in the business object set
Property information;
Heading message determining module 707, for according to the attribute information, determining that the title of the business object set is believed
Breath;
Description information determining module 708, for according to the heading message, determining that the description of the business object set is believed
Breath.
In the embodiment of the present application, the heading message determining module 707 can specifically include following submodule:
Keyword acquisition submodule, for the keyword in the attribute information for the business object for obtaining multiple associations;
Keyword sorting sub-module, for being ranked up to the keyword, obtain the target critical of the first predetermined number
Word;
Heading message determination sub-module, for using the target keyword and the first default template, determining the industry
The heading message of business object set.
In the embodiment of the present application, the description information determining module 708 can specifically include following submodule:
Comment information acquisition submodule, for obtaining the comment information corresponding with the heading message;
Description information determination sub-module, for according to the comment information, determining that the description of the business object set is believed
Breath.
In the embodiment of the present application, the comment information acquisition submodule can specifically include such as lower unit:
Participle unit, for being segmented to the heading message, obtain one or more participle phrases;
Comment information acquiring unit, believe for obtaining the comment to match with one or more of participle phrases respectively
Breath.
In the embodiment of the present application, the description information determination sub-module can specifically include such as lower unit:
Comment information sequencing unit, for being ranked up to the comment information, the target for obtaining the second predetermined number is commented
By information;
Description information determining unit, for using the target comment information and the second default template, determining the business
The description information of object set.
In the embodiment of the present application, user's request information can also be included in the request, the display module 702 is specific
Following submodule can be included:
Target service object set acquisition submodule, for obtaining multiple target services with user's request information match
Object set;
Target service object shows submodule, for showing the multiple target service object set.
For device embodiment, because it is substantially similar to embodiment of the method, so description is fairly simple, it is related
Part illustrates referring to the part of embodiment of the method.
The embodiment of the present application also discloses a kind of system that shows of cluster data table, and the system can include:
One or more processors;
Memory;With,
One or more modules, one or more of modules are stored in the memory and are configured to by described one
Individual or multiple computing devices, wherein, one or more of modules have following function:
One or more processors;
Memory;With,
One or more modules, one or more of modules are stored in the memory and are configured to by described one
Individual or multiple computing devices, wherein, one or more of modules have following function:
Receive cluster data table shows request;
Show cluster data table according to the request, the cluster data table includes multiple business object set, the industry
Business object set has the business object of multiple associations, and, corresponding subject information.
Each embodiment in this specification is described by the way of progressive, what each embodiment stressed be with
The difference of other embodiment, between each embodiment identical similar part mutually referring to.
It should be understood by those skilled in the art that, the embodiment of the embodiment of the present application can be provided as method, apparatus or calculate
Machine program product.Therefore, the embodiment of the present application can use complete hardware embodiment, complete software embodiment or combine software and
The form of the embodiment of hardware aspect.Moreover, the embodiment of the present application can use one or more wherein include computer can
With in the computer-usable storage medium (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code
The form of the computer program product of implementation.
In a typical configuration, the computer equipment includes one or more processors (CPU), input/output
Interface, network interface and internal memory.Internal memory may include the volatile memory in computer-readable medium, random access memory
The form such as device (RAM) and/or Nonvolatile memory, such as read-only storage (ROM) or flash memory (flash RAM).Internal memory is to calculate
The example of machine computer-readable recording medium.Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be with
Realize that information stores by any method or technique.Information can be computer-readable instruction, data structure, the module of program or
Other data.The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM
(SRAM), dynamic random access memory (DRAM), other kinds of random access memory (RAM), read-only storage
(ROM), Electrically Erasable Read Only Memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc are read-only
Memory (CD-ROM), digital versatile disc (DVD) or other optical storages, magnetic cassette tape, tape magnetic rigid disk storage or
Other magnetic storage apparatus or any other non-transmission medium, the information that can be accessed by a computing device available for storage.According to
Herein defines, and computer-readable medium does not include the computer readable media (transitory media) of non-standing, such as
The data-signal and carrier wave of modulation.
The embodiment of the present application is with reference to according to the method for the embodiment of the present application, terminal device (system) and computer program
The flow chart and/or block diagram of product describes.It should be understood that can be by computer program instructions implementation process figure and/or block diagram
In each flow and/or square frame and the flow in flow chart and/or block diagram and/or the combination of square frame.These can be provided
Computer program instructions are set to all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing terminals
Standby processor is to produce a machine so that is held by the processor of computer or other programmable data processing terminal equipments
Capable instruction is produced for realizing in one flow of flow chart or multiple flows and/or one square frame of block diagram or multiple square frames
The device for the function of specifying.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing terminal equipments
In the computer-readable memory to work in a specific way so that the instruction being stored in the computer-readable memory produces bag
The manufacture of command device is included, the command device is realized in one flow of flow chart or multiple flows and/or one side of block diagram
The function of being specified in frame or multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing terminal equipments so that
Series of operation steps is performed on computer or other programmable terminal equipments to produce computer implemented processing, so that
The instruction performed on computer or other programmable terminal equipments is provided for realizing in one flow of flow chart or multiple flows
And/or specified in one square frame of block diagram or multiple square frames function the step of.
Although having been described for the preferred embodiment of the embodiment of the present application, those skilled in the art once know base
This creative concept, then other change and modification can be made to these embodiments.So appended claims are intended to be construed to
Including preferred embodiment and fall into having altered and changing for the embodiment of the present application scope.
Finally, it is to be noted that, herein, such as first and second or the like relational terms be used merely to by
One entity or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or operation
Between any this actual relation or order be present.Moreover, term " comprising ", "comprising" or its any other variant meaning
Covering including for nonexcludability, so that process, method, article or terminal device including a series of elements are not only wrapped
Those key elements, but also the other element including being not expressly set out are included, or is also included for this process, method, article
Or the key element that terminal device is intrinsic.In the absence of more restrictions, wanted by what sentence "including a ..." limited
Element, it is not excluded that other identical element in the process including the key element, method, article or terminal device also be present.
Generation method to a kind of cluster data table provided herein, a kind of generation dress of cluster data table above
Put, show method, a kind of demonstration device of cluster data table and a kind of the showing for cluster data table of a kind of cluster data table are
System, is described in detail, and specific case used herein is set forth to the principle and embodiment of the application, the above
The explanation of embodiment is only intended to help and understands the present processes and its core concept;Meanwhile for the general skill of this area
Art personnel, according to the thought of the application, there will be changes in specific embodiments and applications, in summary, this
Description should not be construed as the limitation to the application.
Claims (30)
1. a kind of cluster data table shows system, it is characterised in that the system includes:
One or more processors;
Memory;With,
One or more modules, one or more of modules be stored in the memory and be configured to by one or
Multiple computing devices, wherein, one or more of modules have following function:
Receive cluster data table shows request;
Show cluster data table according to the request, the cluster data table includes multiple business object set, the business pair
As gathering the business object with multiple associations, and, corresponding subject information.
2. a kind of cluster data table shows method, it is characterised in that including:
Receive cluster data table shows request;
Show cluster data table according to the request;The cluster data table includes multiple business object set, the business pair
As gathering the business object with multiple associations, and, corresponding subject information.
3. according to the method for claim 2, it is characterised in that the multiple business object set is given birth to as follows
Into:
Multiple business objects are obtained, the multiple business object has corresponding attribute information respectively;
According to the attribute information of the multiple business object, the degree of association between the multiple business object is determined;
According to the degree of association between the multiple business object, the multiple business object is classified, obtains multiple business
Object set.
4. according to the method for claim 3, it is characterised in that the attribute information of the multiple business object includes multiple industry
Title, pricing information, consumer information, brand message, the category information of business object, and/or, pictorial information;It is described according to institute
The step of stating the attribute information of multiple business objects, determining the degree of association between the multiple business object includes:
Determine that title similarity, price similarity, consumer's similarity, brand between any two business object are similar respectively
Degree, classification similarity, and/or, picture similarity;
According to the title similarity, price similarity, consumer's similarity, brand similarity, classification similarity, and/or, figure
Piece similarity, the degree of association between any two business object is determined respectively.
5. according to the method for claim 4, it is characterised in that it is described according to the title similarity, price similarity, disappear
The person's of expense similarity, brand similarity, classification similarity, and/or, picture similarity, determine respectively any two business object it
Between the degree of association the step of include:
To the title similarity, price similarity, consumer's similarity, brand similarity, classification similarity, and/or, picture
Similarity-Weighted is summed, and obtains the degree of association between any two business object.
6. according to any described methods of claim 3-5, it is characterised in that described according between the multiple business object
The step of degree of association, classifying to the multiple business object, obtaining multiple business object set includes:
The business object that the degree of association is more than to predetermined threshold value respectively is combined, and obtains multiple business object set.
7. according to the method for claim 2, it is characterised in that the subject information includes the mark of the business object set
Topic information and description information, the subject information generate as follows:
Obtain the attribute information of the business object of multiple associations in the business object set;
According to the attribute information, the heading message of the business object set is determined;
According to the heading message, the description information of the business object set is determined.
8. according to the method for claim 7, it is characterised in that it is described according to the attribute information, determine the business pair
As set heading message the step of include:
Obtain the keyword in the attribute information of the business object of multiple associations;
The keyword is ranked up, obtains the target keyword of the first predetermined number;
Template is preset using the target keyword and first, determines the heading message of the business object set.
9. according to the method for claim 7, it is characterised in that it is described according to the heading message, determine the business pair
As set description information the step of include:
Obtain the comment information corresponding with the heading message;
According to the comment information, the description information of the business object set is determined.
10. according to the method for claim 9, it is characterised in that described to obtain the comment corresponding with the heading message
The step of information, includes:
The heading message is segmented, obtains one or more participle phrases;
The comment information to match with one or more of participle phrases is obtained respectively.
11. according to the method for claim 9, it is characterised in that it is described according to the comment information, determine the business pair
As set description information the step of include:
The comment information is ranked up, obtains the target comment information of the second predetermined number;
Template is preset using the target comment information and second, determines the description information of the business object set.
12. according to the method for claim 2, it is characterised in that also include user's request information in the request, it is described according to
The step of showing cluster data table according to the request includes:
Obtain multiple target service object sets with user's request information match;
Show the multiple target service object set.
A kind of 13. generation method of cluster data table, it is characterised in that including:
Multiple business objects are obtained, the multiple business object has corresponding attribute information respectively;
According to the attribute information of the multiple business object, the degree of association between the multiple business object is determined;
According to the degree of association between the multiple business object, the multiple business object is classified, obtains multiple business
Object set, the multiple business object set have the business object of multiple associations respectively;
According to the business object of the multiple association, subject information corresponding to the multiple business object set is determined respectively;
According to the multiple business object set, and, corresponding subject information, generate cluster data table.
14. according to the method for claim 13, it is characterised in that the attribute information of the multiple business object includes multiple
Title, pricing information, consumer information, brand message, the category information of business object, and/or, pictorial information;The basis
The attribute information of the multiple business object, the step of determining the degree of association between the multiple business object, include:
Determine that title similarity, price similarity, consumer's similarity, brand between any two business object are similar respectively
Degree, classification similarity, and/or, picture similarity;
According to the title similarity, price similarity, consumer's similarity, brand similarity, classification similarity, and/or, figure
Piece similarity, the degree of association between any two business object is determined respectively.
15. according to the method for claim 14, it is characterised in that it is described according to the title similarity, price similarity,
Consumer's similarity, brand similarity, classification similarity, and/or, picture similarity, any two business object is determined respectively
Between the degree of association the step of include:
To the title similarity, price similarity, consumer's similarity, brand similarity, classification similarity, and/or, picture
Similarity-Weighted is summed, and obtains the degree of association between any two business object.
16. according to any described methods of claim 13-15, it is characterised in that it is described according to the multiple business object it
Between the degree of association, the step of classifying to the multiple business object, obtaining multiple business object set includes:
The business object that the degree of association is more than to predetermined threshold value respectively is combined, and obtains multiple business object set.
17. according to the method for claim 16, it is characterised in that the business object according to the multiple association, point
The step of not determining subject information corresponding to the multiple business object set includes:
Obtain the attribute information of the business object of multiple associations in the business object set;
According to the attribute information, the heading message of the business object set is determined;
According to the heading message, the description information of the business object set is determined.
18. according to the method for claim 17, it is characterised in that it is described according to the attribute information, determine the business
The step of heading message of object set, includes:
Obtain the keyword in the attribute information of the business object of multiple associations;
The keyword is ranked up, obtains the target keyword of the first predetermined number;
Template is preset using the target keyword and first, determines the heading message of the business object set.
19. according to the method for claim 17, it is characterised in that it is described according to the heading message, determine the business
The step of description information of object set, includes:
Obtain the comment information corresponding with the heading message;
According to the comment information, the description information of the business object set is determined.
20. according to the method for claim 19, it is characterised in that described to obtain the comment corresponding with the heading message
The step of information, includes:
The heading message is segmented, obtains one or more participle phrases;
The comment information to match with one or more of participle phrases is obtained respectively.
21. according to the method for claim 19, it is characterised in that it is described according to the comment information, determine the business
The step of description information of object set, includes:
The comment information is ranked up, obtains the target comment information of the second predetermined number;
Template is preset using the target comment information and second, determines the description information of the business object set.
A kind of 22. demonstration device of cluster data table, it is characterised in that including:
Receiving module, show request for receive cluster data table;
Display module, for showing cluster data table according to the request;The cluster data table includes multiple business object collection
To close, the business object set has the business object of multiple associations, and, corresponding subject information.
23. device according to claim 22, it is characterised in that the multiple business object set is by calling following mould
Block generates:
Business object acquisition module, for obtaining multiple business objects, the multiple business object has corresponding attribute respectively
Information;
Degree of association determining module, for the attribute information according to the multiple business object, determine the multiple business object it
Between the degree of association;
Sort module, for according to the degree of association between the multiple business object, classifying to the multiple business object,
Obtain multiple business object set.
24. device according to claim 23, it is characterised in that the attribute information of the multiple business object includes multiple
Title, pricing information, consumer information, brand message, the category information of business object, and/or, pictorial information;The association
Degree determining module includes:
Similarity determination sub-module, for determine respectively the title similarity between any two business object, price similarity,
Consumer's similarity, brand similarity, classification similarity, and/or, picture similarity;
Degree of association determination sub-module, for similar according to the title similarity, price similarity, consumer's similarity, brand
Degree, classification similarity, and/or, picture similarity, the degree of association between any two business object is determined respectively.
25. the device according to claim 23 or 24, it is characterised in that the sort module includes:
Submodule is combined, the business object for the degree of association to be more than to predetermined threshold value respectively is combined, and obtains multiple business pair
As set.
26. device according to claim 22, it is characterised in that the subject information includes the business object set
Heading message and description information, the subject information is by calling following module to generate:
Attribute information acquisition module, for obtaining the attribute information of the business object of multiple associations in the business object set;
Heading message determining module, for according to the attribute information, determining the heading message of the business object set;
Description information determining module, for according to the heading message, determining the description information of the business object set.
27. device according to claim 22, it is characterised in that also include user's request information in the request, it is described
Display module includes:
Target service object set acquisition submodule, for obtaining multiple target service objects with user's request information match
Set;
Target service object shows submodule, for showing the multiple target service object set.
A kind of 28. generating means of cluster data table, it is characterised in that including:
Acquisition module, for obtaining multiple business objects, the multiple business object has corresponding attribute information respectively;
Degree of association determining module, for the attribute information according to the multiple business object, determine the multiple business object it
Between the degree of association;
Sort module, for according to the degree of association between the multiple business object, classifying to the multiple business object,
Multiple business object set are obtained, the multiple business object set has the business object of multiple associations respectively;
Subject information determining module, for the business object according to the multiple association, the multiple business object is determined respectively
Subject information corresponding to set;
Generation module, for according to the multiple business object set, and, corresponding subject information, generate cluster data table.
29. device according to claim 28, it is characterised in that the attribute information of the multiple business object includes multiple
Title, pricing information, consumer information, brand message, the category information of business object, and/or, pictorial information;The association
Degree determining module includes:
Similarity determination sub-module, for determine respectively the title similarity between any two business object, price similarity,
Consumer's similarity, brand similarity, classification similarity, and/or, picture similarity;
Degree of association determination sub-module, for similar according to the title similarity, price similarity, consumer's similarity, brand
Degree, classification similarity, and/or, picture similarity, the degree of association between any two business object is determined respectively.
30. the device according to claim 28 or 29, it is characterised in that the subject information determining module includes:
Attribute information acquisition submodule, the attribute for obtaining the business object of multiple associations in the business object set are believed
Breath;
Heading message determination sub-module, for according to the attribute information, determining the heading message of the business object set;
Description information determination sub-module, for according to the heading message, determining the description information of the business object set.
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610565869.XA CN107632984A (en) | 2016-07-18 | 2016-07-18 | A kind of cluster data table shows methods, devices and systems |
TW106118713A TW201816684A (en) | 2016-07-18 | 2017-06-06 | Method, device and system for presenting clustering data table |
PCT/CN2017/092444 WO2018014759A1 (en) | 2016-07-18 | 2017-07-11 | Method, device and system for presenting clustering data table |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610565869.XA CN107632984A (en) | 2016-07-18 | 2016-07-18 | A kind of cluster data table shows methods, devices and systems |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107632984A true CN107632984A (en) | 2018-01-26 |
Family
ID=60991905
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610565869.XA Pending CN107632984A (en) | 2016-07-18 | 2016-07-18 | A kind of cluster data table shows methods, devices and systems |
Country Status (3)
Country | Link |
---|---|
CN (1) | CN107632984A (en) |
TW (1) | TW201816684A (en) |
WO (1) | WO2018014759A1 (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108647981A (en) * | 2018-05-17 | 2018-10-12 | 阿里巴巴集团控股有限公司 | A kind of target object incidence relation determines method and apparatus |
CN109800215A (en) * | 2018-12-26 | 2019-05-24 | 北京明略软件系统有限公司 | Method, apparatus, computer storage medium and the terminal of a kind of pair of mark processing |
CN110232138A (en) * | 2019-05-20 | 2019-09-13 | 中国银行股份有限公司 | A kind of business bootstrap technique, device and storage medium |
CN111291059A (en) * | 2020-05-12 | 2020-06-16 | 北京东方通科技股份有限公司 | Data processing method based on memory data grid |
CN111522606A (en) * | 2020-04-26 | 2020-08-11 | 广东优特云科技有限公司 | Data processing method, device, equipment and storage medium |
CN113256420A (en) * | 2021-05-27 | 2021-08-13 | 中国航空结算有限责任公司 | Enterprise user identification method, device, equipment and medium in transaction |
CN113807630A (en) * | 2020-12-23 | 2021-12-17 | 京东科技控股股份有限公司 | Method, device, equipment and storage medium for acquiring requirements of robot service platform |
CN117933206A (en) * | 2024-03-14 | 2024-04-26 | 武汉数澜科技有限公司 | Service data processing method, device, equipment, storage medium and program product |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108921918B (en) * | 2018-07-24 | 2023-05-30 | Oppo广东移动通信有限公司 | Video creation method and related device |
CN110852094B (en) * | 2018-08-01 | 2023-11-03 | 北京京东尚科信息技术有限公司 | Method, apparatus and computer readable storage medium for searching target |
CN110929002B (en) * | 2018-09-03 | 2022-10-11 | 优视科技(中国)有限公司 | Similar article duplicate removal method, device, terminal and computer readable storage medium |
CN109558593A (en) * | 2018-11-30 | 2019-04-02 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling text |
CN111291019B (en) * | 2018-12-07 | 2023-09-29 | 中国移动通信集团陕西有限公司 | Similarity discrimination method and device for data model |
CN111782916B (en) * | 2020-08-20 | 2024-03-22 | 支付宝(杭州)信息技术有限公司 | Method and device for generating business information report |
CN112527965A (en) * | 2020-12-18 | 2021-03-19 | 国家电网有限公司客户服务中心 | Automatic question answering implementation method and device based on combination of professional library and chatting library |
CN113722370A (en) * | 2021-08-30 | 2021-11-30 | 康键信息技术(深圳)有限公司 | Data management method, device, equipment and medium based on index analysis |
CN114219589B (en) * | 2022-02-21 | 2023-02-10 | 浙江口碑网络技术有限公司 | Virtual entity object generation and page display method and device and electronic equipment |
CN115019078B (en) * | 2022-08-09 | 2023-01-24 | 阿里巴巴(中国)有限公司 | Vehicle image processing method, computing device and storage medium |
CN116090789B (en) * | 2023-03-03 | 2023-08-29 | 麦高(广东)数字科技有限公司 | Lean manufacturing production management system and method based on data analysis |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102375823A (en) * | 2010-08-13 | 2012-03-14 | 腾讯科技(深圳)有限公司 | Searching result gathering display method and system |
CN103246685A (en) * | 2012-02-14 | 2013-08-14 | 株式会社理光 | Method and equipment for normalizing attributes of object instance into features |
CN103365902A (en) * | 2012-03-31 | 2013-10-23 | 北大方正集团有限公司 | Method and device for evaluating Internet News |
CN103678335A (en) * | 2012-09-05 | 2014-03-26 | 阿里巴巴集团控股有限公司 | Method and device for identifying commodity with labels and method for commodity navigation |
CN103902674A (en) * | 2014-03-19 | 2014-07-02 | 百度在线网络技术(北京)有限公司 | Method and device for collecting evaluation data of specific subject |
-
2016
- 2016-07-18 CN CN201610565869.XA patent/CN107632984A/en active Pending
-
2017
- 2017-06-06 TW TW106118713A patent/TW201816684A/en unknown
- 2017-07-11 WO PCT/CN2017/092444 patent/WO2018014759A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102375823A (en) * | 2010-08-13 | 2012-03-14 | 腾讯科技(深圳)有限公司 | Searching result gathering display method and system |
CN103246685A (en) * | 2012-02-14 | 2013-08-14 | 株式会社理光 | Method and equipment for normalizing attributes of object instance into features |
CN103365902A (en) * | 2012-03-31 | 2013-10-23 | 北大方正集团有限公司 | Method and device for evaluating Internet News |
CN103678335A (en) * | 2012-09-05 | 2014-03-26 | 阿里巴巴集团控股有限公司 | Method and device for identifying commodity with labels and method for commodity navigation |
CN103902674A (en) * | 2014-03-19 | 2014-07-02 | 百度在线网络技术(北京)有限公司 | Method and device for collecting evaluation data of specific subject |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108647981A (en) * | 2018-05-17 | 2018-10-12 | 阿里巴巴集团控股有限公司 | A kind of target object incidence relation determines method and apparatus |
CN109800215A (en) * | 2018-12-26 | 2019-05-24 | 北京明略软件系统有限公司 | Method, apparatus, computer storage medium and the terminal of a kind of pair of mark processing |
CN109800215B (en) * | 2018-12-26 | 2020-11-24 | 北京明略软件系统有限公司 | Bidding processing method and device, computer storage medium and terminal |
CN110232138A (en) * | 2019-05-20 | 2019-09-13 | 中国银行股份有限公司 | A kind of business bootstrap technique, device and storage medium |
CN111522606A (en) * | 2020-04-26 | 2020-08-11 | 广东优特云科技有限公司 | Data processing method, device, equipment and storage medium |
CN111522606B (en) * | 2020-04-26 | 2023-08-04 | 广东优特云科技有限公司 | Data processing method, device, equipment and storage medium |
CN111291059A (en) * | 2020-05-12 | 2020-06-16 | 北京东方通科技股份有限公司 | Data processing method based on memory data grid |
CN113807630A (en) * | 2020-12-23 | 2021-12-17 | 京东科技控股股份有限公司 | Method, device, equipment and storage medium for acquiring requirements of robot service platform |
CN113807630B (en) * | 2020-12-23 | 2024-03-05 | 京东科技控股股份有限公司 | Method, device, equipment and storage medium for acquiring requirements of robot service platform |
CN113256420A (en) * | 2021-05-27 | 2021-08-13 | 中国航空结算有限责任公司 | Enterprise user identification method, device, equipment and medium in transaction |
CN113256420B (en) * | 2021-05-27 | 2024-03-01 | 中国航空结算有限责任公司 | Enterprise user identification method, device, equipment and medium in transaction |
CN117933206A (en) * | 2024-03-14 | 2024-04-26 | 武汉数澜科技有限公司 | Service data processing method, device, equipment, storage medium and program product |
Also Published As
Publication number | Publication date |
---|---|
WO2018014759A1 (en) | 2018-01-25 |
TW201816684A (en) | 2018-05-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107632984A (en) | A kind of cluster data table shows methods, devices and systems | |
CN109359244B (en) | Personalized information recommendation method and device | |
CN108121737B (en) | Method, device and system for generating business object attribute identifier | |
CN107424043B (en) | Product recommendation method and device and electronic equipment | |
CN107748754B (en) | Knowledge graph perfecting method and device | |
TWI631474B (en) | Method and device for product identification label and method for product navigation | |
Deldjoo et al. | A review of modern fashion recommender systems | |
CN102609523B (en) | The collaborative filtering recommending method classified based on taxonomy of goods and user | |
CN103970850B (en) | Site information recommends method and system | |
CN107833082B (en) | Commodity picture recommendation method and device | |
CN109492180A (en) | Resource recommendation method, device, computer equipment and computer readable storage medium | |
US20230214895A1 (en) | Methods and systems for product discovery in user generated content | |
CN111523010A (en) | Recommendation method and device, terminal equipment and computer storage medium | |
CN109816482B (en) | Knowledge graph construction method, device and equipment of e-commerce platform and storage medium | |
CN102609422A (en) | Class misplacing identification method and device | |
US20200226168A1 (en) | Methods and systems for optimizing display of user content | |
CN110503459A (en) | User credit degree appraisal procedure, device and storage medium based on big data | |
CN110909536A (en) | System and method for automatically generating articles for a product | |
CA3166094A1 (en) | Commodity short title generation method and apparatus | |
Kiran et al. | User specific product recommendation and rating system by performing sentiment analysis on product reviews | |
Fry et al. | Can we group similar amazon reviews: a case study with different clustering algorithms | |
Liu et al. | A clothing recommendation dataset for online shopping | |
CN104881447A (en) | Searching method and device | |
CN113222687A (en) | Deep learning-based recommendation method and device | |
US11410418B2 (en) | Methods and systems for tagged image generation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180126 |
|
RJ01 | Rejection of invention patent application after publication |