111results about How to "Quick recommendation" patented technology

The invention discloses an internet information product recommending method based on matrix decomposition. The method comprises the following steps of: 1) obtaining the user scoring record to the information product; 2) obtaining the social relationship record between internet users; 3) respectively building a scoring matrix and a social matrix according to the types of a target user and a target product; 4) learning a user feature vector and a product feature vector through a matrix decomposition technology; 5) calculating the scores of different products scored by the target user according to the feature vectors, so as to recommending the favorite products of the user according to the scores. In the method, analysis on user social relationship is introduced, and personalized product recommendation is provided for the target user based on the production type information. The calculation is simple and quick, and the method has better expandability and adaptability, so that the method is suitable for highly dynamic and immense amount of product-oriented recommendation for the internet users.

The invention discloses a network music aggregation recommendation method based on label digraphs, and belongs to the field of network music aggregation. The network music aggregation recommendation method based on the label digraphs can effectively solve the problem that a user classification preference sequence cannot be reflected in an existing traditional label classification recommendation method. According to the network music aggregation recommendation method based on the label digraphs, a quaternary relation formed by users, labels, music and a cognition sequence is taken into adequate consideration; the relational network is utilized for further improving music recommendation accuracy and the degree of satisfaction of the network users. According to the technology, network music features and user interest features are described through the digraphs, and a music feature digraph set is divided into a plurality of digraph clusters, so that the digraphs in each cluster are isomorphic to the greatest extent while the digraphs in different clusters are different to the greatest extent (representing the difference between the digraphs). At the time of similarity matching, it is not needed that the whole music feature digraph set is searched, most of suitable digraphs of a target can be found through inquiries from a plurality of digraph clusters with the highest similarity to a target user interest digraph, and therefore the purpose of recommending music to the music network users quickly and accurately can be achieved.

The invention provides a knowledge document recommendation method based on user historical behavior features. According to the knowledge document recommendation method, the word frequency of each word in an article is calculated, the words and the word frequencies are used as items and support degrees respectively, and the article which is most relevant to the article which is uploaded by a user is excavated by means of the FP-Tree method. The knowledge document recommendation method comprises the steps that a knowledge base word library is extracted through word segmentation of articles which the user has read and are stored in a knowledge base; word tables in the user word library are scanned and optimized, the support degrees of the FP-Tree method is replaced by TF word frequencies so as to establish a FP tree, and a frequent item set containing user reading features is excavated; the most relevant articles are determined finally, the most relevant articles are ranked according to the importance degrees, and the ranked most relevant articles are recommended to the user. According to the knowledge document recommendation method based on the user historical behavior features, the words in the articles are used as excavation features, modeling is conducted on the historical reading behavior of each user, dependence on the reading behaviors of other users is avoided, and therefore the problems that a great number of valuable articles in an enterprise knowledge base are not read by people and the users cannot find the articles containing relevant knowledge at the same time are solved.

The invention provides a knowledge base construction method and system for an intelligent clinical assistant decision making supporting system, and relates to the field of knowledge base construction. The method comprises the steps that input information is acquired, word segmenting processing, part-of-speech tagging and grammatical analysis are conducted on the input information, a relational dependence tree is acquired, and concepts, entities and entity modifiers in the relational dependence tree are extracted; the relation among all the entities in the relational dependence tree is acquired through relational semantic rules according to the concepts, the entities and the entity modifiers; an extending ternary group is set, the relation among all the entities in the relational dependence tree is stored through the extending ternary group, and then knowledge base construction is completed. The method and the system can be applied to the condition of more clinical examples and characteristics and can be flexibly expanded for case description information.

The invention discloses a method and device for providing link recommendation. The method comprises the steps of: extracting link information contained in community share according to a predetermined time period; acquiring microblog messages containing links and microblog message attribute in the link information; scoring the links corresponding to the microblog messages according to a predetermined scoring policy on the basis of the microblog message attribute acquired; acquiring the links which are ranked top N, extracting webpages corresponding to uniform resource locator URL of the links to classify the contents, and acquiring abstract data of the URL, wherein N is a predetermined natural number; and generating link recommendation and providing the link recommendation to users. With application of the invention, the availability of link recommendation can be improved, and the cost of manual operation can be lowered.

An improved approach is described for performing analysis and display of revenue opportunities for large data sets. A user interface is provided to the CSR which provides real-time data relevant to the sales process. The information includes, for example, up-selling opportunities, cross-selling opportunities, profitability analysis, and/or fulfillment analysis.

The invention discloses a resume intelligent recommendation algorithm based on a natural semantic analysis technology. Based on massive user behavior data of delivery, screening, interview, job entryand the like of the cloud recruitment platform, a resume and position matching recommendation algorithm is designed, and proper resumes or positions can be automatically recommended to the recruitersand job seekers according to the algorithm, so that the efficiency of network recruitment and job hunting is improved; the traditional recommendation algorithm includes content-based recommendation orpreference-based recommendation, the algorithm of the invention is based on the combination of the synergisms of the content-based recommendation or preference-based recommendation and adds some potential influence factors such as industries and companies at the same time so as to achieve accurate and rapid recommendation; the method has the advantages that on the basis of a cloud recruitment platform, hundreds of billions of recruitment behavior data are deposited on the platform, a recommendation algorithm is based on the matching degree of posts and the preference of user behaviors, afterrecommendation, the recommendation algorithm feeds back to a recommendation system according to a processing result of a user, and the recommendation system learns a data model again, so that the accuracy is higher and higher.

Disclosed herein is an information processing apparatus including: storage means for storing a recommendation degree that indicates a degree of recommendation of a content for a user; similarity degree calculation means for calculating a degree of similarity between a part of a user profile as updated and a content profile; recommendation degree variation calculation means for calculating, based on the degree of similarity calculated by the similarity degree calculation means, an amount of variation of the recommendation degree of the content for the user; and recommendation degree calculation means for calculating a new recommendation degree by adding the amount of the variation of the recommendation degree calculated by the recommendation degree variation calculation means to the recommendation degree stored in the storage means.

The invention discloses a product recommending method and system, wherein the product recommending method comprises the following steps that historical operation behavior records of buyers are collected from an e-commerce website platform; hobbies and interests of the buyers are analyzed according to the collected historical operation behavior records of the buyers; users with the similar hobbies and interests are found; products concerned by the users with the similar hobbies and interests are recommended to the buyers. The product recommending method provided by the invention has the advantages that the products concerned by other users with the similar hobbies and interests can be recommended to the buyers, so the fast recommendation of the products is realized, and the product resource sharing is also realized.

The invention discloses a medicine matching system based on big data analysis. The medicine matching system comprises the components of a memory which comprises a first storage module for storing patient information and a second storage module for storing medicine information; a big data analysis module which can call the patient information and the medicine information in the memories and performs analysis according to the symptom main description of the patient for analyzing the affected disease and matches the suitable medicine in the medicine information according to the patient information; an information exchange module which is used for information exchange. The invention further provides a coupling method of the medicine matching system based on big data analysis. The medical records, the medicines and the diagnosis of million patients are stored as samples. Modeling is performed through big data analysis. Then the disease is diagnosed according to the information such as symptom main description of the patient. Furthermore all in-selling medicine information of a pharmacy is recorded in the system. When the information such as patient symptom and allergy is input, the suitable medicine can be accurately matched, thereby realizing high effect for new medicine popularization.

The invention provides a method for quickly establishing a communication group, comprising the steps of: receiving a grouping instruction of the preset button acting on a personal homepage of a firstaccount accessing a second account; displaying a friend relationship list of the first account in response to the grouping instruction; receiving a selected instruction of a third account in the friend relationship list; and submitting a grouping request to the server, wherein the grouping request is used for requesting the server to establish a communication group based on the account informationof the first account, the second account, and the third account. The invention is capable of quickly starting the group building on the user's personal homepage without entering the chat interface, improving the efficiency of group building, and improving the user experience.

The invention relates to the technical field of data analysis and recommendation systems, in particular to an e-commerce recommendation method based on a dynamic interest group identifier and a generative adversarial network, which comprises the steps of inputting scoring characteristics of user behavior data, performing prediction by using a trained scoring prediction model, and outputting a scoring prediction value by the scoring prediction model, and generating a recommendation list according to the predicted value of the score to recommend items for the user. The generative adversarial network is utilized to compensate the data, interest group categories are identified for the compensated data, the problems that the user has no interest preference information and interest is generalized are solved, and the invention has important application value for the user and a merchant.

The invention discloses an Android application recommendation method. The method includes the steps that all Android applications needing to be recommended are executed, and network flow traffic data generated by the Android applications are captured; the Android applications needing to be recommended are counted; a bipartite graph of the Android applications and network traffic overheads of the Android applications is constructed; the network traffic overheads of the Android applications are scored; the network traffic overheads of the Android applications are graded; the Android applications are sequenced; an Android application Hash matrix is constructed to finish Android system network application recommendation. According to the method, network overheads and popularity of the Android applications are fused to serve as bases of Android application recommendation, and accordingly when application recommendation is conducted on users, mobile data overheads can be effectively saved for the users. When the method is implemented, calculation speed is high, massive applications in an Android application market can be quickly recommended online, and practicality is extremely good.

The embodiment of the invention discloses a service information pushing method, a related apparatus and a storage medium. The method is applied to a mobile terminal comprising a positioning module anda camera. The method comprises the following steps: the mobile terminal starts a positioning module to determine the position information of the mobile terminal, and determines a target scene in which the mobile terminal is located based on the position information; the camera is started to take pictures; the target image processing algorithm corresponding to the target scene is obtained, and thekey information in the image is extracted by the target image processing algorithm; a first message including key information and location information is sent to the server, and the first message isused for the server to return corresponding service information according to the key information and location information. Embodiments of the present application can quickly and conveniently recommendrelated services based on image and location information.

The invention provides a method applied to assembly and delivery of e-commerce products. In the method, dimension parameters and total volumes of all commodities in orders are compared with dimensionparameters and fillable volumes of packaging boxes, only after the requirements that the dimension parameters of the commodities are smaller than or equal to the dimension parameters of the packagingboxes and the total volumes of all the commodities are smaller than or equal to the fillable volumes of the packaging boxes are met, proper packaging boxes and packaging schemes can be recommended. The method aims at achieving the purpose of e-commerce high-commodity-flow precise and efficient packaging and delivery. By means of the method, the packaging boxes with proper sizes can be accurately and rapidly recommended according to system logic to be rapidly taken and used during production.

The embodiment of the invention discloses a maintenance scheme recommendation method, related equipment and a computer storage medium, and the method comprises the steps that a server obtains N faultphenomena provided by a professional maintainer and Q professional maintenance schemes provided by the professional maintainer for the N fault phenomena, and N and Q are both positive integers; the server updates a system database according to the N fault phenomena and the Q professional maintenance schemes; the server obtains a target fault phenomenon input by a user; the server selects a professional maintenance schemes provided by the professional maintainer for the target fault phenomenon from the system database; and the server provides the A professional maintenance schemes to the user,wherein A is a positive integer. By adopting the embodiment of the invention, a mature and standard automobile maintenance scheme can be quickly recommended to a user and an automobile repairer.

Disclosed are a test case recommendation method and device, a readable storage medium and electronic equipment. The test case recommendation method comprising: performing information extraction on document data of a software test item to extract attribute information of each entity, the entities in the software test item comprising test cases; constructing a knowledge graph of the software test item according to the association relationship between the entities and the attribute information of the entities; obtaining test case demand information, and searching a preset number of test cases with the maximum similarity from the knowledge graph according to the demand information to serve as candidate test cases; and inputting the historical test case clicked by the user and the candidate test case into a DKN model, and outputting the click probability of the candidate test case. The test cases are recommended based on the knowledge graph technology, and the aim of accurately and rapidly recommending the software test cases is achieved.

The invention discloses a recommendation method and device of search words, and relates to the field of computer technology. One specific embodiment of the method includes: acquiring a search word input by a user and product information clicked by the user in a query result of the search word; obtaining all the search words, which can be obtained by searching, of the product information according to the product information, and respectively calculating similarity values of the obtained search words and the search word input by the user; and recommending the obtained search words in sequence according to the similarity values. According to the embodiment, search recommendation in the true sense can be carried out according to the search word input by the user.

The embodiment of the invention discloses an indoor route recommending method and a user terminal. The method comprises the following steps that after indoor environment parameters of a located building of the user terminal are obtained, whether harmful gas parameters reach the preset condition or not is detected, wherein the indoor environment parameters include the harmful gas parameters; when the harmful gas parameters reach the preset conditions, the navigation route set from the current position of the user terminal to an emergency exit is obtained, so that a user is navigated to the emergency exit. Therefore routes including the emergency exit can be precisely and fast recommended.

The invention discloses a data processing method and a data processing device used for matching a spokesperson for a product brand. The data processing method comprises the following steps: acquiring brand positioning information of a product brand needing a spokesperson, wherein the brand positioning information is used for describing brand characteristics of the product brand needing the spokesperson; acquiring spokesperson positioning information of a target spokesperson, wherein the spokesperson positioning information is used for describing personal characteristics of the target spokesperson; matching the similarity level of the brand positioning information and the spokesperson positioning information so as to obtain a positioning overlapping degree, wherein the positioning overlapping degree is used for quantifying the matching degree of the product brand needing the spokesperson and the target spokesperson; confirming whether the target spokesperson is recommended to speak for the product brand needing the spokesperson or not according to the positioning overlapping degree. By adopting the data processing method and the data processing device, the technical problem that an optimal spokesperson cannot be rapidly recommended as a spokesperson is recommended by a consulting company in an artificial analysis mode can be solved.

The invention provides a financial product recommendation method and device, and relates to the technical field of big data analysis and artificial intelligence. The recommendation method comprises the steps: obtaining financial management data of a family customer, wherein the financial management data comprises an investment type; carrying out tagging processing on investment types in the financial management data to obtain customer tags of family customers, and carrying out clustering division on financial management types of the family customers according to the customer tags; determining customer portraits of the family customers in each type and preference degrees for different financial products; and determining a financial product recommendation list corresponding to the family customers based on the customer portraits, the preference degree and a preset classification model. According to the invention, financial products can be quickly and accurately recommended to users from massive financial products.

The invention discloses a data label recommendation method based on machine learning, and belongs to the technical field of information identification. The method comprises the following steps: S1, receiving to-be-predicted data; S2, preprocessing the to-be-predicted data, wherein the preprocessing comprises Chinese word segmentation, keyword extraction and word vector conversion; S3, calculating a similarity score between the to-be-predicted data and the data corresponding to each label; and S4, recommending the labels with the highest similarity score. According to the invention, accurate labels can be efficiently recommended for the data.

The embodiment of the invention provides a live broadcast room recommendation method and a related device, which are used for quickly recommending a live broadcast room to a user. The method comprisesthe steps: obtaining a user watching sequence of a live broadcast platform in a preset time period; determining a transfer weight between live broadcast rooms in the live broadcast platform accordingto the user watching sequence; determining a first directed graph of the live broadcast platform according to the transfer weight between the live broadcast rooms in the live broadcast platform; cutting the first directed graph based on a preset out-degree and/or a preset in-degree to obtain a second directed graph; calculating the transition probability of each node in the second directed graph;calculating the target arrival probability of each node in the second directed graph according to the transition probability of each node in the second directed graph; determining live broadcast roomclustering of the live broadcast platform in a preset time period based on the target arrival probability of each node in the second directed graph; and recommending a live broadcast room to the target user according to a set of live broadcast rooms watched by the target user in the preset time period and the live broadcast room clustering of the live broadcast platform.