Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

34 results about "Customer reviews" patented technology

System, mechanisms, methods and services for the creation, interaction and consumption of searchable, context relevant, multimedia collages composited from heterogeneous sources

The current invention provides an enhanced user experience for consumers by minimizing the number of click-throughs, and optimizing time spent by providing customizable, interactive visual multimedia collages of information created from several sources of information in scrollable snapshots. Moreoyer, the same experience is made available for the users on-the-go on their mobile device where they can access the same collages and interact with them in a manner meaningful to the modalities provided on the mobile device, such as phone calls, text messaging, and Wireless Application Protocol (WAP) browser viewing. On the desktop Internet, interested consumers will be referred from the image collage result sets to content provider or retailers' web sites. Each image has all the information: the advertisement from the seller, customer review, product rating, and seller rating composited together. In one embodiment, the consumer can click on any of the regions of the collage (e.g. customer surveys) to click through to the WAP site or Internet site housing the information. In other embodiments, the consumer can just browse the information, consummate a buy transaction on-line: get it shipped or pick it up himself, place a bid for a used product, and/or call a number for more information. Through the system's analytics engine, the invention provides to the retailers competitive location-based information, consumer behavior data for advertising, and location based product demand. The consumer can save any of the interactive images and forward to others. For enterprises, retailers, and individuals interested in selling new/used products, they can create advertisements for their products using the Internet web based information collage authoring tool.
Owner:MELKOTE RAMASWAMY N +1

Method for identifying substance features of customer reviews

InactiveCN102968408ARealize targeted search and readingAvoid readingSpecial data processing applicationsFeature setSimilarity computation
The invention discloses a method for identifying substance features of customer reviews, which is mainly used for solving the problem of poor accuracy of the conventional automatic substance feature extraction technology on Chinese customer reviews. The method comprises the following implementation steps of: sampling an appropriate quantity of reviews serving as a training set, and performing secondary part-of-speech tagging on the training set; excavating a frequent item set based on a Classification Based on Association (CBA) method; and correcting centralized substance features in the frequent item set according to a dependence relationship to form a candidate substance feature set, performing reliability judgment, removing unreliable substance features, combining synonymic substance features through lexical meaning similarity computation to form a substance feature adjacency set, and screening valuable customer reviews from the substance feature adjacency set to prevent customers from reading a large amount of invaluable information and realize specific lookup and reading of certain substance features for the customers. The method is suitable for identifying the substance features of Chinese network reviews, and has the advantages of high accuracy, portability, simple structure and convenience in implementing.
Owner:XIDIAN UNIV

Enterprise customer association relationship graph construction method and device, memory and computer

ActiveCN111414485ASolve the difficulty of identificationImprove accuracyFinanceSpecial data processing applicationsBusiness enterpriseAssociation control
The invention discloses an enterprise customer association relationship graph construction method and device, a memory and a computer. The method comprises: establishing a basic association relationship and other association relationships between enterprise customers according to data of the enterprise customers; affirming a core enterprise in the enterprise customer according to the basic association relationship; on the basis of the core enterprise, establishing a basic association relationship graph between enterprise customers according to the basic association relationship; and superposing other association relationships on the basic association relationship graph to generate an enterprise customer association relationship graph. Various public and implicit association relationships of enterprise customers are mined, a core node and a relationship circle of an enterprise main operation association control relationship network are discovered, an enterprise multi-dimensional association relationship graph is accurately established, a customer association relationship panoramic view is constructed, the problems of difficult association relationship customer identification and difficult risk discovery are solved, financial customer review management, risk control, post-loan management and other work are assisted, and enterprise risk prevention and control are well performed.
Owner:北京恒通慧源大数据技术有限公司

Merchant multi-view feature extraction and model construction method based on online comment data

The invention discloses a merchant multi-view feature extraction and model construction method based on online comment data. According to the method, firstly, based on comments, sign-in and merchant business attribute data of online comment software, semantic information of customer comments is mined by constructing an emotion classification neural network model, merchant semantic features are generated in combination with customer comment habits, the merchant business features are formed by screening important business attributes, a merchant cluster is generated through density clustering, merchant cluster features of merchants in the cluster are calculated, and finally the three kinds of features are integrated to form multi-view features of the merchants. Then the multi-view features are input into a LightGBM model to realize the prediction of commercial tenant operation conditions. According to the method, the multi-view features of the merchant are extracted from the multi-view perspective based on the online comment data, and the merchant operation state model is constructed based on the features, so that the method has the characteristics of high precision, high expandability and the like, and can provide decision support for merchant operation, commercial investment and the like.
Owner:HANGZHOU DIANZI UNIV

A merchant multi-view feature extraction and model construction method based on online review data

The invention discloses a merchant multi-view feature extraction and model building method based on online comment data. Firstly, based on the comments, check-ins and merchant business attribute data of online review software, the semantic information of customer reviews is mined by constructing an emotional classification neural network model, and the semantic features of merchants are generated by combining customer comment habits, and the merchant business is formed by screening important business attributes. Features, generate merchant clusters through density clustering and calculate the merchant cluster features of each merchant in the cluster, and finally integrate the three types of features to form the multi-view features of the merchants. Then input the multi-view features into the LightGBM model to realize the prediction of the merchant's operating conditions. Based on the online review data, the present invention extracts the multi-view characteristics of merchants from the perspective of multi-view, and constructs a merchant operating status model based on the characteristics, which has the characteristics of high precision and strong scalability, and can provide decision-making for merchant operations and commercial investment. support.
Owner:HANGZHOU DIANZI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products