132results about How to "Achieve recommendation" patented technology

The invention discloses a personalized recommendation method. The method comprises the following steps of: acquiring basic data; processing and classifying the basic data, and analyzing the interest and preference of a purchaser on the basis of historic operation behavior records of the purchaser; filtering and collecting seller information and product information according to a preset rule; correspondingly acquiring a set of products to be recommended according to the interest and preference data information of the purchaser, the seller information and the product information on the basis of a preset matching algorithm; de-duplicating, sorting, weighting and standardizing all products to be recommended, and thus obtaining N optimally-matched products which serve as a recommendation result; and displaying the final recommendation result to the purchaser. By adoption of the personalized recommendation method, the product information which is in accordance with the interest and preference of a user can be accurately recommended to the user in the conventional electronic-commerce business-to-business (B2B) website.

The invention relates to a commodity recommendation method in electronic commerce and a system using the same. The method comprises the steps of firstly, collecting historical behavior data in an electronic commerce website of a user; secondly, performing commodity feature calculation according to the historical behavior data of the user and outputting commodity purchase probability prediction feature vectors of the user; thirdly, placing the output commodity purchase probability prediction feature vectors of the user in a statistical function according to feature and classification and calculating a user purchase probability prediction model to obtain a purchase probability prediction model; fourthly, performing commodity recommendation according to the purchase probability prediction model for the user and user login information. According to the invention, commodities meeting the requirements of users are recommended, personalized recommendation is realized, the customer satisfaction is improved and the user experience is improved.

The invention discloses a personal credit ecological platform, which is structured by a display layer, a middle layer and a data layer; the display layer is a front client platform, the middle layer is a background service platform, and the data layer is a data warehouse system; the whole ecological platform consists of a management end, a personal credit module, a merchant module, a payment flow, and a mobile APP. The platform data base is deep, the data quality is alive, the accuracy is high, the scale is wide, and the time track is rich, the data volume is huge and the dimension is wide. The platform deeply excavates the personal credit data, realizes the credit evaluation, provides the complete personal credit status, realizes the personal credit tracking management, and further controls the risk; besides, the client complaint procedure is added. The platform achieves the recommendation of potential and sustainable developed individual client for merchant users, and realizes the bidirectional push.

The invention discloses a keyword based evaluation expert intelligent search and recommendation method. The keyword based evaluation expert intelligent search and recommendation method specifically comprises step 1, segmenting an expert information main text into substring sequences, performing ICTCLAS word segmentation of Chinese academy of sciences and performing stop word filtering on the result of the word segmentation to obtain the word collection; step 2, extracting feature words of the expert information according to fields; step 3, building an expert knowledge representation model based on the fields and the weight of the feature words and establishing an expert information index database; step 4, performing automatic prompting according to a search term thesaurus when a user inputs keywords and meanwhile performing real-time update on the search term thesaurus through a search term counter; step 5, calculating the search relevance between the keywords and the expert information based on the semantic information and the like; step 6, listing relevant experts from high to low according to the matching degree. According to the keyword based evaluation expert intelligent search and recommendation method, the intelligent full-text search and recommendation of the expert information can be achieved through the keyword input and accordingly the experts which are matched with a pended science and technology project can be searched out accurately.

The embodiment of the invention discloses an information recommendation method. The information recommendation method comprises the following steps of: recording an operation behavior of a user; recording, searching and acquiring identical taste friends of the user according to the operation behavior of the user; and sending user identification information and / or operation behavior record of the identical taste friends of the user to the user. The embodiment of the invention also discloses an information recommendation system. The method and the system can fulfill the purpose of recommending possibly more interesting information to the user, and improve the efficiency and accuracy of recommending the information to the user.

The embodiment of the invention provides a direct broadcasting room recommend method and device. The method comprises: a recommend server determines each direct broadcasting room where users have access and interaction parameter values of each direct broadcasting room according to the users' direct broadcasting room watching records in a preset historical time quantum, obtaining the current heat degree parameter values of each accessed direct broadcasting room; and calculating the preference scores of each accessed direct broadcasting room according to the interaction parameter value of each accessed direct broadcasting room and the current heat degree parameter values, and recommending direct broadcasting rooms for the users according to the sequence of the preference scores. Based on the direct broadcasting room push method, the interaction parameter values are employed to recommend direct broadcasting rooms according with user watching demands for users, the heat degree parameter values are employed to recommend current popular direct broadcasting rooms for the users, and the two parameters are combined for usage to realize that each direct broadcasting room recommended to each user has difference and pertinency and accords with user watching demands.

The invention relates to a public culture knowledge graph platform-based comprehensive recommendation system. The system comprises a labelling unit, a label library, a label mining unit, a recommendation unit and a visualization unit, wherein the labelling unit is used for distributing resource labels for extracted resources and distributing user interest labels for extracted user data; the label library is used for storing the resource labels and the user interest labels; the label mining unit is used for carrying out mining analysis on the labels in the label library; the recommendation unit is used for carrying out comprehensive public culture information recommendation according to a mining analysis result of the label mining unit; and the visualization unit is used for carrying out visualized display on a comprehensive recommendation result of the recommendation unit. According to the system provided by the invention, the cross-field, cross-category, cross-data structure and cross-data source public culture knowledge recommendation is realized.

The present invention belongs to the education informatization field and provides a cognitive emotion sensing-based cloud classroom learning evaluation method and device. The method comprises the following steps that: (1) cloud classroom learning is classified into the four learning targets of acquiring target capabilities, solving problems, performing random learning and obtaining happiness; (2) facial expression change data are integrated into emotion units; (3) the facial expression change data of a user during a curriculum resource learning period are acquired; (4) the emotion unit data are integrated into a data sequence; (5) a weighted positive emotion index is calculated; and (6) a calculation result is outputted and displayed. With the cognitive emotion sensing-based cloud classroom learning evaluation method and device of the invention adopted, emotion analysis can be related in MOOC education on the basis of the facial expression data of the user, and therefore, analysis on the learning behavior of the user can be completed, effective evaluation index data of curriculum resources can be obtained, and the realization of the performance evaluation and recommendation of teaching resources and design modes can be facilitated.

The invention provides a friend recommendation method and system in the SNS network. The friend recommendation method in the SNS network comprises the steps that face detection is carried out on head pictures of users in the SNS network, and face areas in the head pictures are extracted to obtain corresponding face pictures; evaluation information of the face pictures is received from a target user; the face pictures with the evaluation information are trained, and an appearance evaluating model with respect to the target user is obtained; the face pictures of candidate friends are input into the appearance evaluating model to obtain the evaluation result of the face picture of each candidate friend; friends are recommended to the target user according to the valuation result of the face picture of each candidate friend. By means of the technical scheme, the friend recommendation method and system in the SNS network can realize the function of friend recommendation in the SNS network on the basis of accurately meeting the preference for the appearances of friends for the target user.

The invention provides a video recommendation method and system. The method comprises the steps of obtaining long and short video features and user features of a user; inputting the user features andthe long and short video features into a preset recommendation model for click rate prediction to obtain a predicted click rate of each to-be-recommended long video and a predicted click rate of eachto-be-recommended short video; and sorting all theto-be-recommended long videos to be recommended and all the to-be-recommended short videos to be recommended according to the predicted click rate ofeach to-be-recommended long video to be recommended and the predicted click rate of each to-be-recommended short video to be recommended, and feeding back a sorting result to the user. In the scheme,the user characteristics and the long and short video characteristics obtained by combining the long video characteristics and the short video characteristics are input into the pre-trained recommendation model to obtain the predicted click rates of the to-be-recommended long video and the to-be-recommended short videos. Sorting t The to-be-recommended long videos and the to-be-recommended short videos are sorted according to the predicted click rate, and feeding back a sorting result is reported to the user, thereby realizing recommendation of different types of information, and improving theuse experience of the user and the accuracy of information recommendation.

The invention discloses a cross-commodity-category commodity recommendation method and device. The method comprises the steps that user transaction data including first commodity information are acquired; a pre-established commodity association data table is queried according to the user transaction data to acquire at least one second commodity information which is associated with the first commodity information and belongs to a different commodity category, wherein the commodity association data table is acquired by statistical analysis based on commodity transaction historical data; and commodity recommendation is carried out according to at least one second commodity information. The association relationship of cross-commodity-category commodity information is established by pre-establishing the commodity association data table. The commodity association data table is queried to acquire at least one second commodity information which is associated with the first commodity information and belongs to a different commodity category, and cross-commodity-category commodity recommendation is realized. Barriers between different commodity categories are broken, and the purchase rate ofrecommended commodities is improved.

The invention relates to a recommendation method and device for a search keyword. The recommendation method for the search keyword is applied to a server, and comprises the following steps: receivinga search keyword recommendation request transmitted by a client, wherein the search keyword recommendation request is transmitted by the client according to search word information inputted by a user;in a plurality of branches contained in a pre-built keyword search tree, matching the search word information with characters on nodes in the plurality of branches, and obtaining branches that the characters on the nodes are matched with the search word information; based on the branches obtained by matching, performing string extraction on the nodes included in the branches, and generating a candidate keyword result according to an extracted string; and transmitting the candidate keyword result to the client. The recommendation method and the device for the search keyword provided by the invention can effectively improve the accuracy of the search keyword, thereby helping to improve the searching accuracy.

The invention discloses a multi-source heterogeneous remote sensing data association construction and multi-user data matching method. The multi-source heterogeneous remote sensing data association construction and multi-user data matching method comprises the following steps of 1, inputting a remote sensing service data set and a remote sensing product data set; 2, performing data cleaning and preprocessing; 3, performing data classification modeling; 4, performing knowledge extraction, including attribute extraction of remote sensing business data and feature extraction of remote sensing product data; 5, performing multi-source heterogeneous knowledge fusion, constructing a link relationship for the plurality of knowledge, and fusing attribute similarity of different ontology data according to metadata information extracted from the remote sensing data to construct the link relationship of a plurality of knowledge systems; 6, constructing an association relationship model; 7, miningand analyzing a large amount of collected user identities and behavior data, and constructing a user portrait label; 8, carrying out similarity calculation on the identity and behavior of the user; and 9, constructing a personalized user portrait model, and matching the personalized user portrait model with a result in the association relationship construction model.

The invention provides a website recommendation method, device and system in website navigation. The method includes the following steps: receiving website click behaviors identified by flash IDs and collected by javascript arranged in a preset page, storing the received website click behaviors and the corresponding flash IDs in a user behavior log, and performing the following steps on the flash IDs to be recommended respectively, wherein the steps include obtaining the user click behaviors corresponding to the flash IDs to be recommended in a set period from the user behavior log, determining recommended websites corresponding to the flash IDs to be recommended on the basis of the click number of each website, and enabling the determined recommended websites to be contained in navigation pages corresponding to the flash IDs to be recommended. For user equipment, the flash IDs used by all browsers or clients for visiting webpage are exclusive, and therefore non-login user and cross-browser personalized website recommendation is achieved.

The invention discloses a method for obtaining and identifying customer information and a device thereof. The method is used for establishing a video acquisition area, and comprises the following steps of: A, acquiring customer information entering the video acquisition information, and generating a customer identity data package via face feature values in the customer information; B, processing the received customer identity data package to form customer information data and sending the customer information data; and C, matching face features in the customer information data package, if no face matching item exists, storing the customer information data into a database, and if the face matching item exists, merging the customer information data package into the existing data, storing the merged customer information data package into the database and outputting identification information. According to the method and the device, the user faces and the consumption-related information are combined on the basis of a face obtaining and identification technology, so that a method for three-dimensional describing the consuming habits, preferences and abilities of the users is realized.

The invention discloses an advertisement data recommendation method and system. The advertisement data recommendation method includes the steps: receiving a request of browsing target advertisement data, from a user, obtaining the user characteristic information of the user, inputting the user characteristic information into a pre-established correlation degree prediction model, obtaining the correlation degree between each advertisement showing mode of the target advertisement data and the browsing request, and recommending the target advertisement data of the advertisement showing mode thatthe correlation degree satisfies the preset conditions to the user. As the advertisement data recommendation method determines the advertisement showing mode according to the user characteristic information of the user so as to determine the recommended advertisement data, the interest of the user on the shown advertisement data is improved; the user experience is improved; and ineffective exposure with low advertisement data clicking rate.

The invention discloses a social network friend recommending method based on multiple personal characteristic hybrid architecture. The method comprises: defining intimacy degree characteristics according to attribute information of users in conjunction with inter-user interactive information, constructing an intimacy degree probability transfer matrix, and introducing a random walk model to calculate inter-user interaction degree scores; on this basis, defining personal node characteristics of the users, using a weighted average method to assign different weights to the characteristics, and using a random walk algorithm to obtain a Top-N recommendation list for recommending. The method of the invention has the advantages that attribute information and interactive information of users are fully considered, interest characteristics of the users are considered, behavior characteristics of the users in a social network are also considered, real friend needs of the users can be truly reflected through these personal network characteristics and node characteristics, and friend recommending accuracy is greatly improved.

The embodiment of the invention provides an information processing method, device and equipment, and relates to the technical field of communication. The method comprises the steps that a bad information iris filtering mode is triggered; iris features of a current user are acquired; age information of the current user is sought according to the iris features; the first grade of the age information of the current user is determined; bad information in a webpage document is filtered according to filtering rules on the bad information in the corresponding first grade. Accordingly, the method for judging the age information of the user by acquiring the iris features of the user for the problem that the network bad information cannot be effectively shielded or filtered according to the age grade of juveniles on the basis of a diversified open network environment is presented, therefore, the purpose that the network bad information is filtered for the user according to the age grade of the user is improved, and the advantage that the protection effect on the juveniles is improved in the open network environment is achieved.

The invention provides a refrigerator which is used for solving the technical problem that a refrigerator in the prior art cannot recommend food suitable for users. The refrigerator comprises a refrigerator body, a refrigerating system and an intelligent control system. The intelligent control system comprises a control unit, a recognition unit, a first data unit and a second data unit. The recognition unit is used for recognizing and acquiring N pieces of food information of at least N food objects in a food containing space. The first data unit is used for acquiring at least one piece of user preference information and the N pieces of the food information and transmitting first recommending food information to the control unit based on the at least one piece of the user preference information and the N pieces of the food information. The second data unit is used for acquiring first time information, first geographic information and the N pieces of the food information and transmitting second recommending food information to the control unit based on the first time information, the geographic information and the N pieces of the food information.

The invention relates to the technical field of digital televisions, and discloses a content recommendation method and a device for digital television value added services. The method comprises the steps: obtaining assessing information on different contents by a user, wherein the contents are objects which militate with the user on a platform of the digital television value added services; converting the assessing information to assessing scores with a uniform format; building an assessment input matrix according to the assessing scores, wherein the assessment input matrix is a two-dimensional matrix, and a line index of the matrix is user identification, a column index of the matrix is content identification, and elements in the matrix are the assessing scores on the contents by the user; calculating similarity of different contents in every two terms in the assessment input matrix; and confirming recommendation contents which aim at the user according to the obtained similarity. Through the content recommendation method and the device for the digital television value added services, recommendation of the personalized contents for the user can be achieved by aiming at the digital television value added services.

Provided are an information searching system and a method. The system comprises a personalized information statistic module, an inquiring module and a displaying module. The personalized information statistic module is used for acquiring a user friend list, acquiring corresponding friend internet information data according to the user friend list, and counting personalized information of user friends. The inquiring module is used for acquiring inquiring requests of users and acquiring personalized information of the user friends according to the inquiring requests. The displaying module is used for displaying the personalized information of the acquired user friends. The information searching system and the method acquire the user friend list, inquire the internet information data according to the user friend list, and count personalized information of the user friends according to the internet information data. Users can acquire personalized information of the user friends by inquiring and know about hotspot information which the user friends concerned. Personalized information of the friends can be recommended to the users in targeted mode, thereby reducing bandwidth pressure brought by acquisition of unneeded information and improving downloading speed.

The invention provides a content-based cross-domain recommendation method. The content-based cross-domain recommendation method comprises the following steps: S1, obtaining a user interest word list;S2, taking the text information of projects in a user behavior sequence of a source domain as source domain training data, and taking the text information of each project in the target domain as target domain training data; S3, constructing a content semantic coding network model; S4, using the content semantic coding network model trained in the step S3 to carry out content semantic coding on theuser behavior of the source domain and the project of the target domain to obtain a user behavior interest vector and a project semantic vector; and S5, for each user, calculating the similarity by using the interest vector and the project semantic vector of the user, and obtaining k most similar projects as recommended projects. Due to the content-based cross-domain recommendation method, the user interest vectors can be coded based on the text information of the projects in the source domain user behavior sequence and are matched with the projects in the target domain, so that cross-domainrecommendation is realized.

The invention relates to the technical field of information retrieval, in particular to a method, a system, equipment and a medium for matching positions and resumes. The method comprises the following steps: extracting position features and resume features by utilizing a natural language processing technology; Carrying out importance sorting on the position features; Retrieving the resumes according to the position features, wherein the retrieved resumes at least comprise resume features corresponding to the position features; And based on the ranking of the position features in the importance ranking, screening the resumes obtained through retrieval. The resume screening method solves the problem of man-post matching accuracy and individuation, and improves the resume screening efficiency.

The invention provides an information recommendation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a plurality of different types ofinformation in advance, and analyzing to obtain a label corresponding to each piece of information; performing word embedding processing on the name of each label corresponding to each piece of information to obtain a vector corresponding to each piece of information; clustering the vectors corresponding to the plurality of different types of information to obtain a similar information set composed of similar information; and acquiring information related to user behaviors, determining a similar information set matched with the related information, and sending information included in the matched similar information set to a terminal of the user. Cross-type information recommendation can be realized, and the diversity of recommended contents is enriched.

The invention relates to the technical field of recommendation systems, in particular to a personalized intelligent clothes matching recommendation method in combination with a knowledge graph, which comprises the following steps: acquiring clothes commodity information and user clothing interaction information of an e-commerce platform, and constructing the knowledge graph; modeling the knowledge graph, and learning each entity and relationship in the knowledge graph to obtain an entity vector and a relationship vector; combining the entity vector and the relationship vector with a hybrid recommendation system, and performing score prediction on the single clothing to obtain a clothes single recommendation result; and calculating a matching index of every two clothes single items, automatically matching the two clothes single items with high matching indexes, performing score prediction, and performing a final TOP-N suit recommendation result according to scores. Online clothes suit recommendation is more intelligent.

The invention provides a system and method for realizing intelligent matching recommendation through natural semantic analysis, and the system comprises a natural semantic processing module which receives enterprise information, policy information and enterprise service business handling information from a government affair network, and carries out the extraction and processing of information dataaccording to a natural language processing method, an enterprise portrait generation module which is used for analyzing and obtaining an enterprise corresponding portrait and a portrait label throughthe extracted information data, a policy analysis module which is used for disassembling the application range and the evaluation standard of policies according to the extracted information data, anda recommendation module which is used for matching and recommending the enterprises and the corresponding policies according to the portrait tags, the policy ranges and the evaluation standards. According to the invention, enterprises and policies are matched, intelligent matching and recommendation of enterprise portraits and government affair items are realized, more opportunities and consultations are provided for the enterprises, and enterprise development is promoted.

The invention provides a location-based service travel recommendation method comprising the steps that step one, entity track-event information is acquired, and user-location-activity associated modeling is performed on the entity information through a three-dimensional tensor; step two, user track-event information is recorded; and step three, similarity matching is performed through user analogy, and the user track-event information with high similarity is actively pushed, wherein the user track-event information (from location information of mobile phones, sports bracelets and sports watches) is integrated and then matched with the related user track-event information, and pushing is performed. According to the method, mass user data are integrated and similar users and activities are found in different locations by using a collaborative filtering algorithm, modeling of the mutual relation of user-location-activity is performed through the tensor and a regularized tensor / matrix decomposition algorithm is put forward. The problem of sparsity of single user movement location data can be effectively alleviated by the algorithm and thus mining of the movement mode of the users can be performed.