WO2018014759A1

WO2018014759A1 - Method, device and system for presenting clustering data table

Info

Publication number: WO2018014759A1
Application number: PCT/CN2017/092444
Authority: WO
Inventors: 叶舟; 王瑜; 张亚楠; 苏飞; 杨洋; 杜楠楠; 毛庆凯
Original assignee: 阿里巴巴集团控股有限公司; 叶舟; 王瑜; 张亚楠; 苏飞; 杨洋; 杜楠楠; 毛庆凯
Priority date: 2016-07-18
Filing date: 2017-07-11
Publication date: 2018-01-25
Also published as: TW201816684A; CN107632984A

Abstract

A method, device and system for presenting a clustering data table. The method comprises: receiving a presentation request for a clustering data table (401); and presenting the clustering data table according to the presentation request, the clustering data table comprising multiple service object sets, the service object sets having multiple associated service objects and corresponding topic information (402). The method enables user needs to be identified rapidly, and can present service objects satisfying the user needs, thus reducing the time for a user to search for or query a service object, reducing the waste of system resources caused by searching for or querying a service object, and increasing the accessing efficiency.

Description

Method, device and system for displaying cluster data table

Technical field

The present invention relates to the field of information technology, and in particular, to a method for generating a cluster data table, a device for generating a cluster data table, a method for displaying a cluster data table, and a display device for a cluster data table. A presentation system for clustering data tables.

Background technique

Advances in technology have driven the development of e-commerce. Today, e-commerce websites such as Taobao and Tmall have been able to bring products from all over the world online for consumers to purchase. However, in the face of a wide range of goods, consumers may not know which products are worth buying. Therefore, some e-commerce websites have begun to actively recommend products to consumers to reduce the time for consumers to search and purchase goods. It is one of the important ways to display the recommended products to the consumer groups in the form of product lists. The list of goods usually consists of three parts:

(1) Product list: This list contains a series of similar products. For example, the list of clothing can be the same style of clothes, pants and shoes. The list of household items can be a combination of the same color curtains, wallpaper and carpet. and many more.

(2) List title: The title is a short text that can be used to describe the characteristics of the product list. For example, the title of the clothing list can be “small fresh spring”, “pink matching control” and so on.

(3) List description: The list description can be a short paragraph of easy-to-understand text for further elaboration of the title of the list, such as a list of goods titled “The rice bowl in your hand”, the description can be “porcelain” The healthiest bowls, different sizes and different patterns can add a lot to the table, so that consumers can understand the products recommended in the list.

At present, the merchandise list of the e-commerce website is mainly realized by relying on the manual operation of the website operator, and by obtaining the consumption data of the consumer and combining the public opinion statistics of the external website, the product to be recommended is determined through manual analysis. The recommended items are then combined into a list, and the title and description of the list are refined. However, the above method requires a lot of labor costs, and the list of goods formed also has subjective preferences of heavy operators, and may Unable to meet the needs and preferences of most consumers.

Summary of the invention

In view of the above problems, embodiments of the present application are provided to provide a method for generating a cluster data table, a cluster data table generating device, and a clustering data, which overcome the above problems or at least partially solve the above problems. A presentation method of a table, a presentation device of a cluster data table, and a presentation system of a cluster data table.

In order to solve the above problem, the present application discloses a display system of a cluster data table, including:

One or more processors;

Memory; and,

One or more modules, the one or more modules being stored in the memory and configured to be executed by the one or more processors, wherein the one or more modules have the following functions:

Receiving a presentation request of the cluster data table;

A cluster data table is presented according to the request, the cluster data table includes a plurality of business object sets, the business object set having a plurality of associated business objects, and corresponding topic information.

In order to solve the above problem, the present application also discloses a method for displaying a cluster data table, which is characterized in that it comprises:

Receiving a presentation request of the cluster data table;

And presenting a cluster data table according to the request; the cluster data table includes a plurality of business object sets, the business object set having a plurality of associated business objects, and corresponding topic information.

Optionally, the multiple business object sets are generated by the following steps:

Obtaining a plurality of business objects, wherein the plurality of business objects respectively have corresponding attribute information;

Determining, according to attribute information of the plurality of business objects, a degree of association between the plurality of business objects;

And classifying the plurality of business objects according to the degree of association between the plurality of business objects to obtain a plurality of business object sets.

Optionally, the attribute information of the plurality of business objects includes a name, price information, consumer information, brand information, category information, and/or picture information of the plurality of business objects; The attribute information of the object, the determining the degree of association between the plurality of business objects includes:

Determining name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity between any two business objects;

The degree of association between any two business objects is determined according to the name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity.

Optionally, the determining the association between any two business objects according to the name similarity, the price similarity, the consumer similarity, the brand similarity, the category similarity, and/or the picture similarity respectively The steps of degree include:

The name similarity, the price similarity, the consumer similarity, the brand similarity, the category similarity, and/or the picture similarity are weighted and summed to obtain the degree of association between any two business objects.

Optionally, the step of classifying the multiple service objects according to the degree of association between the multiple service objects, and obtaining the multiple service object sets includes:

The business objects whose association degree is greater than the preset threshold are respectively combined to obtain a plurality of business object sets.

Optionally, the topic information includes title information and description information of the service object set, and the topic information is generated by the following steps:

Obtaining attribute information of multiple associated business objects in the business object set;

Determining, according to the attribute information, title information of the business object set;

Determining the description information of the business object set according to the title information.

Optionally, the step of determining, according to the attribute information, the header information of the service object set includes:

Obtaining keywords in attribute information of multiple associated business objects;

Sorting the keywords to obtain a first preset number of target keywords;

Using the target keyword and the first preset template, determining header information of the business object set.

Optionally, the step of determining the description information of the service object set according to the header information includes:

Obtaining comment information corresponding to the title information;

Determining the description information of the business object set according to the comment information.

Optionally, the step of acquiring the comment information corresponding to the title information includes:

Segmenting the title information to obtain one or more participle phrases;

The review information that matches the one or more participle phrases is separately obtained.

Optionally, the determining, according to the comment information, the description information of the service object set includes:

Sorting the comment information to obtain a second preset number of target comment information;

Determining the description information of the business object set by using the target comment information and the second preset template.

Optionally, the request further includes user requirement information, and the step of displaying the cluster data table according to the request includes:

Obtaining a plurality of target business object sets that match user demand information;

Presenting the plurality of target business object sets.

In order to solve the above problem, the present application also discloses a method for generating a clustering data table, which is characterized in that it comprises:

And categorizing the plurality of business objects according to the degree of association between the plurality of business objects, to obtain a plurality of business object sets, wherein the plurality of business object sets respectively have a plurality of associated business objects;

Determining, according to the plurality of associated business objects, the plurality of service object sets respectively Subject information

Generating a cluster data table according to the plurality of business object sets and corresponding topic information.

Optionally, the step of determining the topic information corresponding to the multiple service object sets according to the multiple associated service objects includes:

Sorting the keywords to obtain a first preset number of target keywords;

Obtaining comment information corresponding to the title information;

Segmenting the title information to obtain one or more participle phrases;

In order to solve the above problem, the present application further discloses a display device for cluster data table, which is characterized in that it comprises:

a receiving module, configured to receive a presentation request of the cluster data table;

a presentation module, configured to present a cluster data table according to the request; the cluster data table includes a plurality of business object sets, the business object set having a plurality of associated business objects, and corresponding topic information.

Optionally, the plurality of business object sets are generated by calling the following modules:

a business object obtaining module, configured to acquire a plurality of business objects, where the plurality of business objects respectively have corresponding attribute information;

An association determining module, configured to determine, according to attribute information of the multiple business objects, an association degree between the multiple service objects;

And a classification module, configured to classify the plurality of business objects according to the degree of association between the plurality of business objects, to obtain a plurality of business object sets.

Optionally, the attribute information of the multiple service objects includes a name, a price information, a consumer information, a brand information, a category information, and/or a picture information of the plurality of service objects. The association degree determining module includes:

The similarity determination submodule is configured to respectively determine name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity between any two business objects;

The association determination submodule is configured to respectively determine between any two business objects according to the name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity The degree of relevance.

Optionally, the association determination submodule includes:

The association degree determining unit is configured to weight the sum of the name similarity, the price similarity, the consumer similarity, the brand similarity, the category similarity, and/or the picture similarity to obtain any two business objects. The degree of association between them.

Optionally, the classification module includes:

The combination sub-module is configured to combine the business objects whose degree of association is greater than the preset threshold to obtain a plurality of business object sets.

Optionally, the topic information includes title information and description information of the set of business objects, and the topic information is generated by calling the following module:

An attribute information obtaining module, configured to acquire attribute information of multiple associated business objects in the business object set;

a header information determining module, configured to determine, according to the attribute information, header information of the service object set;

And a description information determining module, configured to determine, according to the title information, description information of the service object set.

Optionally, the title information determining module includes:

Keyword acquisition sub-module for obtaining key information in attribute information of multiple associated business objects word;

a keyword sorting sub-module, configured to sort the keywords to obtain a first preset number of target keywords;

And a header information determining submodule, configured to determine, by using the target keyword and the first preset template, header information of the service object set.

Optionally, the description information determining module includes:

a comment information obtaining submodule, configured to obtain comment information corresponding to the title information;

And a description information determining submodule, configured to determine, according to the comment information, description information of the business object set.

Optionally, the comment information obtaining submodule includes:

a word segmentation unit, configured to perform segmentation on the title information to obtain one or more word segmentation phrases;

a comment information obtaining unit, configured to respectively obtain the comment information that matches the one or more participle phrases.

Optionally, the description information determining submodule includes:

a comment information sorting unit, configured to sort the comment information to obtain a second preset number of target comment information;

The description information determining unit is configured to determine description information of the business object set by using the target comment information and the second preset template.

Optionally, the request further includes user requirement information, where the presentation module includes:

a target business object set obtaining submodule, configured to acquire a plurality of target business object sets that match user demand information;

The target business object presentation submodule is configured to display the plurality of target business object sets.

In order to solve the above problem, the present application further discloses a device for generating a cluster data table, which includes:

An obtaining module, configured to acquire a plurality of business objects, where the plurality of business objects respectively have corresponding attribute information;

An association determining module, configured to determine the multiple according to attribute information of the multiple service objects The degree of association between business objects;

a classification module, configured to classify the plurality of business objects according to the degree of association between the plurality of business objects, to obtain a plurality of business object sets, wherein the plurality of business object sets respectively have multiple associated business objects ;

a topic information determining module, configured to respectively determine topic information corresponding to the plurality of service object sets according to the plurality of associated business objects;

And a generating module, configured to generate a cluster data table according to the plurality of business object sets and the corresponding topic information.

Optionally, the association determination submodule includes:

Optionally, the classification module includes:

Optionally, the topic information determining module includes:

An attribute information obtaining submodule, configured to acquire attribute information of multiple associated business objects in the business object set;

a header information determining submodule, configured to determine the set of business objects according to the attribute information Title information;

And a description information determining submodule, configured to determine, according to the header information, description information of the service object set.

Optionally, the header information determining submodule includes:

a keyword obtaining unit, configured to acquire keywords in attribute information of a plurality of associated business objects;

a keyword sorting unit, configured to sort the keywords to obtain a first preset number of target keywords;

The title information determining unit is configured to determine the title information of the business object set by using the target keyword and the first preset template.

Optionally, the description information determining submodule includes:

a comment information obtaining unit, configured to obtain comment information corresponding to the title information;

The description information determining unit is configured to determine description information of the business object set according to the comment information.

Optionally, the comment information acquiring unit includes:

a word segmentation unit for segmenting the title information to obtain one or more word segmentation phrases;

The comment information acquisition subunit is configured to respectively obtain the comment information that matches the one or more participle phrases.

Optionally, the description information determining unit includes:

a comment information sorting subunit, configured to sort the comment information to obtain a second preset number of target comment information;

a description information determining subunit, configured to determine description information of the business object set by using the target comment information and the second preset template.

Compared with the background art, the embodiments of the present application include the following advantages:

After receiving the presentation request of the cluster data table, the embodiment of the present application may display a cluster data table including a plurality of service object sets according to the request, and can quickly identify the user demand, and exhibit The business object that satisfies the user's needs reduces the time for the user to search or find the business object, saves the resource consumption of the system caused by searching or searching for the business object, and improves the access efficiency.

DRAWINGS

1 is a flow chart showing the steps of Embodiment 1 of a method for generating a cluster data table according to the present application;

2 is a flow chart showing the steps of Embodiment 2 of a method for generating a cluster data table according to the present application;

3 is a schematic block diagram of Embodiment 2 of a method for generating a cluster data table according to the present application;

4 is a flow chart showing the steps of an embodiment of a method for displaying a cluster data table according to the present application;

5 is a diagram showing an example of a cluster data table of the present application;

6 is a structural block diagram of an embodiment of a device for generating a cluster data table according to the present application;

7 is a structural block diagram of an embodiment of a presentation device of a cluster data table of the present application.

detailed description

The above described objects, features and advantages of the present application will become more apparent and understood.

Referring to FIG. 1 , a flow chart of a first embodiment of a method for generating a cluster data table according to the present application is shown, which may specifically include the following steps:

Step 101: Acquire a plurality of service objects, where the plurality of service objects respectively have corresponding attribute information;

In the embodiment of the present application, the business object may be a commodity, or other types of objects, for example, news information, etc., and the type of the business object is not limited in the present application.

It should be noted that the attribute information of the corresponding business object may be different for different business objects. For example, when the business object is a commodity, the attribute information may be a name, a price, a consumer, a brand, a specific category, and/or a picture of the item. When the business object is news information, the attribute information may be information such as the source, time, location, and the like of the news information. A person skilled in the art can select appropriate attribute information according to the specific type of the business object, which is not specifically limited in this application.

In a specific implementation, the acquisition of attribute information of different business objects may also be adopted. Different ways, for example, the attribute information of the product can be obtained from the product data stored on the platform such as the e-commerce website, and the attribute information of the news information can be obtained from the information platform such as the information website.

Step 102: Determine, according to attribute information of the multiple service objects, a degree of association between the multiple service objects.

In the embodiment of the present application, after obtaining attribute information of multiple business objects, the degree of association between any two business objects may be calculated. The degree of association may be a numerical description of a degree of association between two business objects obtained by analyzing from attribute information of a plurality of different dimensions, the degree of association may reflect similarity between two business objects or Collocations, for example, for different types of shoes with similarities, such as leather shoes and sandals, can have a higher degree of relevance, but for business objects with certain collocations, such as clothes and pants, can also have higher The degree of relevance.

In the embodiment of the present application, after obtaining the name, price information, consumer information, brand information, category information, and/or picture information of the business object of the commodity, the two business objects may be separately calculated first. Name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity, then based on the name similarity, price similarity, consumer similarity, brand Similarity, category similarity, and/or picture similarity determine the degree of association between any two business objects. The similarity between the different attribute information may be respectively calculated by using different calculation methods. For example, the cosine theorem Cosine formula, or the Jaccard Jaccard similarity may be used, and the specific similarity calculation method is not limited in this application.

In a specific implementation, when calculating the name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity of any two business objects, the name may be Similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity are weighted and summed to obtain the degree of association between any two business objects. The weights of the similarities of different information dimensions can be adjusted according to actual needs. For example, for clothing goods, the weight of picture similarity can be increased, and for digital goods, the weight of name similarity can be increased, so that the final obtained Relevance can be better Reflects the similarity or collocation between two different business objects.

Step 103: Classify the multiple service objects according to the degree of association between the multiple service objects, to obtain multiple service object sets, where the multiple service object sets respectively have multiple associated service objects;

In the embodiment of the present application, after the degree of association between any two service objects is calculated, the service objects whose association degree is greater than the preset threshold may be respectively combined to obtain a plurality of service object sets. In a specific implementation, the multiple business objects may be classified by using a hierarchical clustering method to obtain a plurality of business object sets. Hierarchical clustering is the hierarchical decomposition of a data set according to a certain method until a certain condition is met. According to the classification principle, it can be divided into two methods: condensation and splitting. Taking cohesion as an example, condensed hierarchical clustering is a bottom-up strategy. You can first treat each object as a cluster, then merge the clusters into larger and larger clusters until all objects are in one cluster. Medium, or a certain termination condition is met. Hierarchical clustering is a widely used classification algorithm, which is not described in this application.

Step 104: Determine, according to the multiple associated service objects, topic information corresponding to the plurality of service object sets respectively;

In the embodiment of the present application, the topic information may include title information and description information of the business object. The title information of the set of business objects may be a phrase or a phrase that can reflect a common feature of all the business objects in the set, and the description information may be text information used to uniformly describe the business objects in the set, and It may be text information that further elaborates on the title information.

In a preferred embodiment of the present application, the step of determining the topic information corresponding to the plurality of service object sets according to the multiple associated service objects may specifically include the following sub-steps:

Sub-step 1041, acquiring attribute information of multiple associated business objects in the business object set;

Sub-step 1042, determining, according to the attribute information, header information of the service object set;

Sub-step 1043, determining, according to the header information, description information of the service object set.

In a specific implementation, attribute information of all business objects may be obtained first, and then from the The attribute information extracts text information for describing the business object, for example, the name of the product, or the product introduction text, and the like, and then extracts keywords from the text information, and sorts the keywords to obtain a ranking. The first k keywords, and then the k keywords and the preset theme template may be used to determine the title information of the business object set. When the keyword is sorted, it may be performed according to the number of occurrences of the keyword, or other methods, which is not specifically limited in this application.

After determining the title information of the business object set, the review information matching the title may be found according to the title information, and then the comment information with higher relevance to the title information is further filtered out from the searched search information. , thereby obtaining description information of the set of business objects.

In the specific implementation, the segmentation information can be segmented, the semantic model is used to expand the synonym of the segmentation message, and the comment data is matched by the text, thereby recalling the comment information matching the title information. After obtaining the comment information, the comment information may be scored according to a certain rule, so that the top-ranked comment information is used, and the description information is generated by using a preset text template.

Step 105: Generate a cluster data table according to the plurality of business object sets and corresponding topic information.

In the embodiment of the present application, after obtaining the business object set and the corresponding topic information respectively, the business object set and the topic information thereof may be merged into one cluster data table to be presented to the user.

In the embodiment of the present application, the attribute information of the plurality of business objects is obtained, thereby determining the degree of association between the plurality of business objects, and classifying the plurality of business objects according to the degree of association to obtain the plurality of business object sets. Then, the topic information of the business object set is extracted separately, and then the cluster data table is generated, which solves the problem that the cluster data table can only be generated by manual operation in the prior art, and the generation efficiency of the cluster data table is improved. It also makes the generated cluster data table more objective and more suitable for the needs and preferences of most users.

Referring to FIG. 2, the steps of the second embodiment of the method for generating a cluster data table of the present application are shown. The flow chart may specifically include the following steps:

Step 201: Acquire a plurality of service objects, where the plurality of service objects respectively have corresponding attribute information;

In the embodiment of the present application, the business object may be a commodity, and the attribute information of the business object may be a name, a price, a consumer, a brand, a specific category, and/or a picture of the product.

FIG. 3 is a schematic block diagram of Embodiment 2 of a method for generating a cluster data table according to the present application. In a specific implementation, the attribute information of the commodity may be obtained from the commodity data stored on the platform such as an e-commerce website.

Step 202: Determine name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity between any two business objects, respectively;

For the sake of understanding, the business object of the commodity is taken as an example to describe how to determine the name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or between any two commodities. , picture similarity.

The name similarity can reflect the similarity between the names of any two commodities. Specifically, the Jaccard Jaccard similarity in text mining can be used for calculation. The basic idea is the number of identical words in the product name and the total words. The ratio between the numbers.

For example, if the title A is “small tomato custom women's new style” and the title B is “small apple custom women's Korean version”, when using the Jaccard Jaccard similarity calculation, the title can be first divided, and then the intersection size and union of the word segmentation can be calculated. Size, where the intersection of title A and title B is "customized" and "women's", counted as 2, the same can be obtained that the union size of title A and title B is 6, the ratio between the two is 2/6=0.33 Is the name similarity.

When determining the price similarity, the quantile of the transaction price of the commodity under the same category can be calculated first, and then the quantile is divided into different grades, thereby obtaining the price similarity.

Specifically, the transaction price of the commodity can be first sorted from small to large, and then the 10-digit to 90-digit number can be calculated, so that the entire price domain can be divided into 10 grades according to the order statistics, and the transaction price of each commodity will be Fall to the 10 grades of 1-10. If the price grade of commodity A is 5 and the price grade of commodity B is 8, then the price between commodity A and commodity B can be calculated. The lattice similarity is (8-5)/10=0.3.

Consumer similarity can be calculated by an algorithm that uses collaborative filtering. The basic idea is to calculate it by the consumer's preference and the cosine theorem Cosine formula. For example, the product pair may be first scored according to different behaviors such as browsing, collecting, purchasing, and closing of the product by the consumer. If the transaction is 4 points, the purchase is 3 points, the collection is 2 points, and the browsing is 1 point. A consumer-commodity score sheet as shown in Table 1 below was obtained.

Table I:

	商品ACommodity A	商品BCommodity B
消费者1Consumer 1	33	44
消费者2Consumer 2	22	11
消费者3Consumer 3	33	22

Then, using the cosine theorem Cosine formula, the consumer 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.

Brand similarity can be obtained directly by comparing whether two commodities belong to the same brand. For example, if both the product A and the product B belong to the A brand, the brand similarity between the product A and the product B can be considered to be 1.

The category similarity can be calculated by the algorithm of association analysis. The basic idea is to calculate the probability of purchasing the category A commodity and the category B commodity while purchasing the category A commodity in the consumer's order. For example, if there are currently two orders, where order 1 is category A/B/C, order 2 is category B/C/E, and order 3 is category B/D/F, then the calculation knows the purchase category B. The probability of purchasing a category C product at the same time is 2/3, that is, both the order 1 and the order 2 contain the category B/C.

Image similarity can be converted into a vector by SIFT/SURF or deep neural network algorithm, and then the cosine theorem Cosine formula or other methods can be used to calculate the similarity. The similarity of the image can reflect the similarity between the product styles. SIFT, the Scale-invariant feature transform (SIFT), is a description used in the field of image processing. This description has scale invariance and can detect key points in the image. SURF (Speeded Up Robust Feature,) refers to the robust feature of acceleration, SURF technology The technique can be applied to object recognition and 3D reconstruction of computer vision, and the SURF operator is improved by the SIFT operator. Specifically, after obtaining the product picture, the picture can be transformed into a vector like [1, 1, 3, 4] by transformation on the data, and then the cosine theorem Cosine formula is used to calculate the picture similarity between the two products.

The above describes how to calculate the product similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity, respectively, and those skilled in the art can also adopt the above introduction. The calculation of the similarity is performed in different manners, which is not specifically limited in this application.

Step 203: Determine, according to the name similarity, the price similarity, the consumer similarity, the brand similarity, the category similarity, and/or the picture similarity, the degree of association between any two business objects, respectively;

In a preferred embodiment of the present application, the determining the arbitrary two according to the name similarity, the price similarity, the consumer similarity, the brand similarity, the category similarity, and/or the picture similarity respectively The step of the degree of association between the business objects may specifically include the following sub-steps:

Sub-step 2031, weighting the name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity to obtain an association between any two business objects. degree.

In a specific implementation, when calculating the name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity of any two business objects, the name may be Similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity are weighted and summed to obtain the degree of association between any two business objects. The weights of the similarities of different information dimensions can be adjusted according to actual needs. For example, for clothing goods, the weight of picture similarity can be increased, and for digital goods, the weight of name similarity can be increased, so that the final obtained The degree of relevance better reflects the similarity or collocation between two different business objects.

Step 204: Combine the business objects whose degree of association is greater than the preset threshold to obtain a plurality of service object sets.

In a specific implementation, the hierarchical clustering method can be used to perform clustering based on the degree of association, thereby All acquired business objects are divided into different categories, each of which is a collection of business objects.

Step 205: Acquire attribute information of multiple associated business objects in the business object set.

Step 206: Determine, according to the attribute information, header information of the service object set.

Generally, the title information of the business object set may be a phrase or a short sentence that can reflect a common feature of all business objects in the set. In a specific implementation, the attribute information of all the business objects may be obtained first, and then the text information used to describe the business object, for example, the name of the product, or the introduction text of the product, etc., may be extracted from the attribute information, and then The text information is used to determine the title information of the business object set.

In a preferred embodiment of the present application, the step of determining the title information of the service object set according to the attribute information may specifically include the following sub-steps:

Sub-step 2061, acquiring keywords in attribute information of multiple associated business objects;

Sub-step 2062, sorting the keywords to obtain a first preset number of target keywords;

Sub-step 2063, determining the title information of the business object set by using the target keyword and the first preset template.

In a specific implementation, the name of the obtained commodity or the attribute information such as the introduction text may be first segmented, the corresponding keyword is obtained, and then the existing statistical algorithm is used to sort the keywords to obtain the top ranking. k keywords, and then the k keywords and the preset theme template may be used to determine the title information of the business object. For example, after obtaining a preset number of keywords, the title information of the business object may be generated using the template "XX of XX" or "Teach you how to XXX" or the like. The selection of a predetermined number of keywords may be determined according to actual needs, which is not specifically limited in this application. For example, select two or three keywords and then use the corresponding template to get the title information of the business object.

The existing statistical algorithm may be a TF-IDF (term frequency-inverse document frequency) algorithm, or a TextRank algorithm, which is not specifically limited in this application.

Step 207: Determine, according to the header information, description information of the service object set.

In a preferred embodiment of the present application, the step of determining the description information of the service object set according to the header information may specifically include the following sub-steps:

Sub-step 2071, obtaining review information corresponding to the title information;

Sub-step 2072, determining, according to the comment information, description information of the business object set.

In a specific implementation, after the header information of the service object set is determined, the comment information related to the title information may be further searched, and the description information of the service object set is determined according to the comment information.

The sub-step of obtaining the comment information corresponding to the title information may further include:

Segmenting the subject information to obtain one or more participle phrases;

Obtaining review information that matches the one or more participle phrases.

In a specific implementation, one or more word segmentation phrases may be obtained by segmenting the title information, and then the semantic model is used to expand the synonyms of the one or more word segmentation messages, and text matching is performed on the comment data, thereby recalling the title The information that matches the information.

The sub-step of determining the description information of the service object set according to the comment information may further include:

In the specific implementation, after obtaining the comment information, the review information may be ranked by using deep learning and manual labeling, so that the preset number of comment information is sorted by using the preset text template, and the preset text template is generated. Descriptive information about the set of business objects. Different sets of business objects are made to correspond to different description information.

For example, for the business object set 1, the description information may be: for the delicate things, it is always unstoppable; for the business object set 2, the description information may be: teasing while chatting, which is a pleasant life; For the business object collection 3, the description information can be: the man wearing the shirt is absolutely the most handsome.

Step 208: Generate a cluster data table according to the plurality of service object sets and corresponding header information and description information.

In the embodiment of the present application, after obtaining the business object set and its title information and description information respectively, the business object set and its title information and description information may be combined into one cluster data table. For a commodity, the cluster data table is a list of commodities including a collection of different commodities and their titles and descriptions.

In the embodiment of the present application, by generating a product list by using the graph clustering and the information extraction algorithm, the list of the product list, the title, and the description can be automatically obtained by effectively using the product data and the comment data, thereby greatly improving the generation of the product list. effectiveness.

Referring to FIG. 4, a flow chart of steps of an embodiment of a method for displaying a cluster data table of the present application is shown, which may specifically include the following steps:

Step 401: Receive a presentation request of a cluster data table.

Step 402: Present a cluster data table according to the request; the cluster data table includes a plurality of business object sets, the business object set has a plurality of associated business objects, and corresponding topic information.

In the embodiment of the present application, after receiving the presentation request of the cluster data table, the cluster data table may be generated according to the request, so that the cluster data table is presented to the user.

The present application does not limit the specific representation of the cluster data table. The cluster data table may include multiple business object sets, and the business object set may include multiple associated business objects, and corresponding topic information. . As shown in FIG. 5, which is an exemplary diagram of the cluster data table of the present application, a plurality of different product lists shown in FIG. 5 are different sets of business objects, and the product list may include different The item, and subject information generated according to the different item, the subject information includes a title of the item list, and description information for the different item.

In this embodiment of the present application, the multiple service object sets may be generated by the following steps:

S11. Acquire multiple service objects, where the multiple service objects respectively have corresponding attribute information.

S12. Determine, according to attribute information of the multiple service objects, an association degree between the multiple service objects.

In the embodiment of the present application, the attribute information of the plurality of business objects may include a name, price information, consumer information, brand information, category information, and/or picture information of the plurality of business objects; The step of determining the degree of association between the plurality of service objects may include the following sub-steps:

Sub-step S121, respectively determining name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity between any two business objects;

Sub-step S122, determining the degree of association between any two business objects according to the name similarity, the price similarity, the consumer similarity, the brand similarity, the category similarity, and/or the picture similarity.

Further, the determining the degree of association between any two business objects according to the name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity The substeps can include:

Since the sub-steps S121-S122 are similar to the steps 202-203 in the second embodiment, they can be referred to each other, and the details are not described in this embodiment.

S13. Classify the plurality of service objects according to the degree of association between the plurality of service objects, to obtain a plurality of service object sets.

In a specific implementation, the multiple business objects may be classified by using a hierarchical clustering method to obtain a plurality of business object sets.

In the embodiment of the present application, the topic information may be generated by the following steps:

S21. Acquire attribute information of multiple associated business objects in the business object set.

S22. Determine, according to the attribute information, header information of the service object set.

Generally, the title information of the business object set may be a phrase or a short sentence that can reflect a common feature of all business objects in the set. Specifically, the step of determining the title information of the service object set according to the attribute information may include the following sub-steps:

Sub-step S221, acquiring keywords in the attribute information of the plurality of associated business objects;

Sub-step S222, sorting the keywords to obtain a first preset number of target keywords;

Sub-step S223, determining the title information of the business object set by using the target keyword and the first preset template.

S23. Determine, according to the header information, description information of the service object set.

Generally, the description information may be text information used to uniformly describe a business object in the set, and may also be text information that further elaborates the title information. Specifically, the step of determining the description information of the service object set according to the header information may include the following sub-steps:

S231. Acquire, the comment information corresponding to the title information.

S232. Determine, according to the comment information, description information of the service object set.

In the specific implementation, after obtaining the comment information, the review information may be ranked by using deep learning and manual labeling, so that the preset number of comment information is sorted by using the preset text template, and the preset text template is generated. Descriptive information about the set of business objects. Make different The set of business objects corresponds to different descriptive information.

In a preferred embodiment of the present application, the step of presenting the cluster data table according to the request may specifically include the following sub-steps:

Sub-step 4021: acquiring a plurality of target service object sets that match user requirement information;

Sub-step 4022, presenting the plurality of target business object sets.

In a specific implementation, the request for presenting the cluster data table may further include user requirement information, so after generating the cluster data table, a plurality of target business object sets matching the user requirement information may be acquired, and then the A plurality of target business object collections are presented to the user.

The user requirement information may be obtained according to a user's previous browsing or search record of the business object. For example, when the user browses or searches for a jacket, the user may generate clothing including a jacket, pants, shoes, and the like. The product list information; of course, the user demand information may also be obtained according to other methods, which is not limited in this application.

In the embodiment of the present application, after receiving the presentation request of the cluster data table, the cluster data table including the plurality of service object sets may be presented according to the request, which can quickly identify the user requirements and display the service that meets the user requirements. The object reduces the time for the user to search or find the business object, saves the resource consumption of the system caused by searching or searching for the business object, and improves the access efficiency.

It should be noted that, for the method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should understand that the embodiments of the present application are not limited by the described action sequence, because In accordance with embodiments of the present application, certain steps may be performed in other sequences or concurrently. In the following, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required in the embodiments of the present application.

Referring to FIG. 6, a structural block diagram of an embodiment of a device for generating a clustering data table of the present application is shown, which may specifically include the following modules:

The obtaining module 601 is configured to acquire a plurality of service objects, where the plurality of service objects respectively have corresponding attribute information;

The association degree determining module 602 is configured to determine, according to the attribute information of the multiple service objects, the degree of association between the multiple service objects;

The categorization module 603 is configured to classify the plurality of service objects according to the degree of association between the plurality of service objects, to obtain a plurality of service object sets, where the plurality of service object sets respectively have multiple associated services Object

The topic information determining module 604 is configured to separately determine topic information corresponding to the plurality of service object sets according to the plurality of associated service objects;

The generating module 605 is configured to generate a cluster data table according to the plurality of business object sets and the corresponding topic information.

In the embodiment of the present application, the attribute information of the plurality of business objects may include a name, price information, consumer information, brand information, category information, and/or picture information of the plurality of business objects; The determining module 602 may specifically include the following submodules:

In the embodiment of the present application, the association determining sub-module may specifically include the following units:

In the embodiment of the present application, the classification module 603 may specifically include the following sub-modules:

In the embodiment of the present application, the topic information determining module 604 may specifically include the following submodules:

An attribute information obtaining submodule, configured to acquire multiple associated service pairs in the business object set Attribute information of the image;

a header information determining submodule, configured to determine, according to the attribute information, header information of the service object set;

In the embodiment of the present application, the header information determining submodule may specifically include the following units:

In the embodiment of the present application, the description information determining submodule may specifically include the following units:

In the embodiment of the present application, the comment information acquiring unit may specifically include the following subunits:

In the embodiment of the present application, the description information determining unit may specifically include the following subunits:

Referring to FIG. 7, a structural block of an embodiment of a display device of a cluster data table of the present application is shown. The figure may specifically include the following modules:

The receiving module 701 is configured to receive a presentation request of the cluster data table.

The presentation module 702 is configured to present a cluster data table according to the request; the cluster data table may include a plurality of business object sets, the business object set having a plurality of associated business objects, and corresponding topic information.

In this embodiment of the present application, the multiple service object sets may be generated by calling the following modules:

The business object obtaining module 703 is configured to acquire a plurality of business objects, where the plurality of business objects respectively have corresponding attribute information;

The association degree determining module 704 is configured to determine, according to attribute information of the multiple service objects, an association degree between the multiple service objects;

The classification module 705 is configured to classify the plurality of business objects according to the degree of association between the plurality of business objects, to obtain a plurality of business object sets.

In the embodiment of the present application, the attribute information of the plurality of business objects may include a name, price information, consumer information, brand information, category information, and/or picture information of the plurality of business objects; The determining module 704 may specifically include the following submodules:

In the embodiment of the present application, the classification module 705 may specifically include the following sub-modules:

a combination sub-module for respectively combining business objects whose association degree is greater than a preset threshold To multiple business object collections.

In this embodiment, the topic information may include title information and description information of the service object set, and the topic information may be generated by calling the following module:

The attribute information obtaining module 706 is configured to acquire attribute information of multiple associated business objects in the business object set;

a header information determining module 707, configured to determine, according to the attribute information, header information of the service object set;

The description information determining module 708 is configured to determine description information of the business object set according to the title information.

In the embodiment of the present application, the title information determining module 707 may specifically include the following sub-modules:

a keyword acquisition sub-module, configured to acquire keywords in attribute information of multiple associated business objects;

In the embodiment of the present application, the description information determining module 708 may specifically include the following sub-modules:

In the embodiment of the present application, the comment information obtaining submodule may specifically include the following units:

In the embodiment of the present application, the description information determining submodule may specifically include the following yuan:

In the embodiment of the present application, the request may further include user requirement information, and the presentation module 702 may specifically include the following sub-modules:

For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

The embodiment of the present application further discloses a presentation system of a cluster data table, and the system may include:

One or more processors;

Memory; and,

One or more processors;

Memory; and,

Receiving a presentation request of the cluster data table;

Presenting a cluster data table according to the request, the cluster data table including a plurality of business object sets The business object set has a plurality of associated business objects, and corresponding topic information.

The various embodiments in the present specification are described in a progressive manner, and each embodiment focuses on differences from other embodiments, and the same similar parts between the various embodiments can be referred to each other.

Those skilled in the art will appreciate that embodiments of the embodiments of the present application can be provided as a method, apparatus, or computer program product. Therefore, the embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Moreover, embodiments of the present application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

In a typical configuration, the computer device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory. The memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory. Memory is an example of a computer readable medium. Computer readable media includes both permanent and non-persistent, removable and non-removable media. Information storage can be implemented by any method or technology. The information can be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include non-persistent computer readable media, such as modulated data signals and carrier waves.

Embodiments of the present application are described with reference to flowcharts and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the present application. It should be understood that the computer program instructions A combination of the processes and/or blocks in the flowcharts and/or block diagrams, and the flowcharts and/or blocks in the flowcharts and/or block diagrams. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing terminal device to produce a machine such that instructions are executed by a processor of a computer or other programmable data processing terminal device Means are provided for implementing the functions specified in one or more of the flow or in one or more blocks of the flow chart.

The computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device. The instruction device implements the functions specified in one or more blocks of the flowchart or in a flow or block of the flowchart.

These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device such that a series of operational steps are performed on the computer or other programmable terminal device to produce computer-implemented processing, such that the computer or other programmable terminal device The instructions executed above provide steps for implementing the functions specified in one or more blocks of the flowchart or in a block or blocks of the flowchart.

While a preferred embodiment of the embodiments of the present application has been described, those skilled in the art can make further changes and modifications to the embodiments once they are aware of the basic inventive concept. Therefore, the appended claims are intended to be interpreted as including all the modifications and the modifications

Finally, it should also be noted that in this context, relational terms such as first and second are used merely to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply these entities. There is any such actual relationship or order between operations. Furthermore, the terms "comprises" or "comprising" or "comprising" or any other variations are intended to encompass a non-exclusive inclusion, such that a process, method, article, or terminal device that includes a plurality of elements includes not only those elements but also Other elements that are included, or include elements inherent to such a process, method, article, or terminal device. An element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that comprises the element, without further limitation.

The method for generating a cluster data table provided by the present application, a device for generating a cluster data table, a method for displaying a cluster data table, a display device for cluster data table, and a clustering The presentation system of the data table is described in detail. The principles and implementation manners of the present application are described in the specific examples. The description of the above embodiments is only used to help understand the method of the present application and its core ideas; For those of ordinary skill in the art, the details of the present invention and the scope of the application are subject to change without departing from the scope of the present application.

Claims

A presentation system for clustering data tables, characterized in that the system comprises:

One or more processors;

Memory; and,

One or more modules, the one or more modules being stored in the memory and configured to be executed by the one or more processors, wherein the one or more modules have the following functions:

Receiving a presentation request of the cluster data table;

A cluster data table is presented according to the request, the cluster data table includes a plurality of business object sets, the business object set having a plurality of associated business objects, and corresponding topic information.
A method for presenting a cluster data table, comprising:

Receiving a presentation request of the cluster data table;

And presenting a cluster data table according to the request; the cluster data table includes a plurality of business object sets, the business object set having a plurality of associated business objects, and corresponding topic information.
The method according to claim 2, wherein the plurality of business object sets are generated by the following steps:

Obtaining a plurality of business objects, wherein the plurality of business objects respectively have corresponding attribute information;

Determining, according to attribute information of the plurality of business objects, a degree of association between the plurality of business objects;

And classifying the plurality of business objects according to the degree of association between the plurality of business objects to obtain a plurality of business object sets.
The method according to claim 3, wherein the attribute information of the plurality of business objects includes a name, price information, consumer information, brand information, category information, and/or picture information of the plurality of business objects. The step of determining the degree of association between the plurality of service objects according to the attribute information of the multiple service objects includes:

Determining name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity between any two business objects;

The degree of association between any two business objects is determined according to the name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity.
The method according to claim 4, wherein said determining is based on said name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity, respectively The steps of the degree of association between any two business objects include:

The name similarity, the price similarity, the consumer similarity, the brand similarity, the category similarity, and/or the picture similarity are weighted and summed to obtain the degree of association between any two business objects.
The method according to any one of claims 3-5, wherein the step of classifying the plurality of business objects according to the degree of association between the plurality of business objects to obtain a plurality of business object sets include:

The business objects whose association degree is greater than the preset threshold are respectively combined to obtain a plurality of business object sets.
The method according to claim 2, wherein the topic information comprises title information and description information of the set of business objects, and the topic information is generated by the following steps:

Obtaining attribute information of multiple associated business objects in the business object set;

Determining, according to the attribute information, title information of the business object set;

Determining the description information of the business object set according to the title information.
The method according to claim 7, wherein the determining the header information of the set of business objects according to the attribute information comprises:

Obtaining keywords in attribute information of multiple associated business objects;

Sorting the keywords to obtain a first preset number of target keywords;

Using the target keyword and the first preset template, determining header information of the business object set.
The method according to claim 7, wherein the determining the description information of the business object set according to the title information comprises:

Obtaining comment information corresponding to the title information;

Determining the description information of the business object set according to the comment information.
The method according to claim 9, wherein the step of acquiring the comment information corresponding to the title information comprises:

Segmenting the title information to obtain one or more participle phrases;

The review information that matches the one or more participle phrases is separately obtained.
The method according to claim 9, wherein the determining the description information of the business object set according to the comment information comprises:

Sorting the comment information to obtain a second preset number of target comment information;

Determining the description information of the business object set by using the target comment information and the second preset template.
The method according to claim 2, wherein the request further includes user requirement information, and the step of presenting the cluster data table according to the request comprises:

Obtaining a plurality of target business object sets that match user demand information;

Presenting the plurality of target business object sets.
A method for generating a clustering data table, comprising:

Obtaining a plurality of business objects, wherein the plurality of business objects respectively have corresponding attribute information;

Determining, according to attribute information of the plurality of business objects, a degree of association between the plurality of business objects;

And categorizing the plurality of business objects according to the degree of association between the plurality of business objects, to obtain a plurality of business object sets, wherein the plurality of business object sets respectively have a plurality of associated business objects;

Determining, according to the plurality of associated business objects, topic information corresponding to the plurality of service object sets;

Generating a cluster data table according to the plurality of business object sets and corresponding topic information.
The method according to claim 13, wherein the attribute information of the plurality of business objects includes a name, price information, consumer information, brand information, category information, and/or picture information of the plurality of business objects. The step of determining the degree of association between the plurality of service objects according to the attribute information of the multiple service objects includes:

Determining name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity between any two business objects;

The degree of association between any two business objects is determined according to the name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity.
The method according to claim 14, wherein said determining is based on said name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity, respectively The steps of the degree of association between any two business objects include:

The name similarity, the price similarity, the consumer similarity, the brand similarity, the category similarity, and/or the picture similarity are weighted and summed to obtain the degree of association between any two business objects.
The method according to any one of claims 13-15, wherein the step of classifying the plurality of business objects according to the degree of association between the plurality of business objects to obtain a plurality of business object sets include:

The business objects whose association degree is greater than the preset threshold are respectively combined to obtain a plurality of business object sets.
The method according to claim 16, wherein the step of determining the topic information corresponding to the plurality of service object sets according to the plurality of associated business objects includes:

Obtaining attribute information of multiple associated business objects in the business object set;

Determining, according to the attribute information, title information of the business object set;

Determining the description information of the business object set according to the title information.
The method according to claim 17, wherein the determining the header information of the set of business objects according to the attribute information comprises:

Obtaining keywords in attribute information of multiple associated business objects;

Sorting the keywords to obtain a first preset number of target keywords;

Using the target keyword and the first preset template, determining header information of the business object set.
The method according to claim 17, wherein the determining the description information of the business object set according to the title information comprises:

Obtaining comment information corresponding to the title information;

Determining the description information of the business object set according to the comment information.
The method according to claim 19, wherein the step of acquiring the comment information corresponding to the title information comprises:

Segmenting the title information to obtain one or more participle phrases;

The review information that matches the one or more participle phrases is separately obtained.
The method according to claim 19, wherein the determining the description information of the business object set according to the comment information comprises:

Sorting the comment information to obtain a second preset number of target comment information;

Determining the description information of the business object set by using the target comment information and the second preset template.
A display device for clustering data tables, comprising:

a receiving module, configured to receive a presentation request of the cluster data table;

a presentation module, configured to present a cluster data table according to the request; the cluster data table includes a plurality of business object sets, the business object set having a plurality of associated business objects, and corresponding topic information.
The apparatus according to claim 22, wherein said plurality of business object sets are generated by calling a module as follows:

a business object obtaining module, configured to acquire a plurality of business objects, where the plurality of business objects respectively have corresponding attribute information;

An association determining module, configured to determine, according to attribute information of the multiple business objects, an association degree between the multiple service objects;

And a classification module, configured to classify the plurality of business objects according to the degree of association between the plurality of business objects, to obtain a plurality of business object sets.
The apparatus according to claim 23, wherein the attribute information of the plurality of business objects includes a name of a plurality of business objects, price information, consumer information, brand information, Category information, and/or picture information; the relevance determination module includes:

The similarity determination submodule is configured to respectively determine name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity between any two business objects;

The association determination submodule is configured to respectively determine between any two business objects according to the name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity The degree of relevance.
The apparatus according to claim 23 or 24, wherein the classification module comprises:

The combination sub-module is configured to combine the business objects whose degree of association is greater than the preset threshold to obtain a plurality of business object sets.
The apparatus according to claim 22, wherein said topic information comprises title information and description information of said set of business objects, said topic information being generated by calling a module as follows:

An attribute information obtaining module, configured to acquire attribute information of multiple associated business objects in the business object set;

a header information determining module, configured to determine, according to the attribute information, header information of the service object set;

And a description information determining module, configured to determine, according to the title information, description information of the service object set.
The device according to claim 22, wherein the request further includes user requirement information, and the presentation module comprises:

a target business object set obtaining submodule, configured to acquire a plurality of target business object sets that match user demand information;

The target business object presentation submodule is configured to display the plurality of target business object sets.
A device for generating a clustering data table, comprising:

An obtaining module, configured to acquire multiple business objects, where the multiple business objects respectively have corresponding Attribute information

An association determining module, configured to determine, according to attribute information of the multiple business objects, an association degree between the multiple service objects;

a classification module, configured to classify the plurality of business objects according to the degree of association between the plurality of business objects, to obtain a plurality of business object sets, wherein the plurality of business object sets respectively have multiple associated business objects ;

a topic information determining module, configured to respectively determine topic information corresponding to the plurality of service object sets according to the plurality of associated business objects;

And a generating module, configured to generate a cluster data table according to the plurality of business object sets and the corresponding topic information.
The apparatus according to claim 28, wherein the attribute information of the plurality of business objects includes a name, price information, consumer information, brand information, category information, and/or picture information of the plurality of business objects. The association determination module includes:

The similarity determination submodule is configured to respectively determine name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity between any two business objects;

The association determination submodule is configured to respectively determine between any two business objects according to the name similarity, price similarity, consumer similarity, brand similarity, category similarity, and/or picture similarity The degree of relevance.
The device according to claim 28 or 29, wherein the subject information determining module comprises:

An attribute information obtaining submodule, configured to acquire attribute information of multiple associated business objects in the business object set;

a header information determining submodule, configured to determine, according to the attribute information, header information of the service object set;

And a description information determining submodule, configured to determine, according to the header information, description information of the service object set.