Product
Patsnap Eureka
For R&D, Patsnap Eureka makes reading and utilizing patents & technical documents easy.
Patsnap Eureka AIR
Designed for self-driven R&D workflows. Generate viable solutions, solve complex R&D challenges, empower your innovation with AI.
Patsnap Eureka Materials
Designed for material experts only. Revolutionize your material R&D, from search, analyze, to developing new materials.
Feature
TechResearch
Generate reliable direction feasibility study reports for your R&D in just a few steps.
TechSeek
Discover and master advanced knowledge NOW. Basics, ideas, possibilities, all at once.
TechMind
As an expert in R&D Theories, TechMind can generates customized viable solutions instantly.
TechRisk
Analyze your overall solution with one click, know your potential R&D risks in advance.
TechMonitor
Get weekly tech updates, stay abreast of the latest tech innovations and key insights.
Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
69results about How to "Improve the success rate of referrals" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Method and device for recommending keyword
ActiveCN103092877AConsumption Willingness SatisfactionReduce the number of queriesMarketingSpecial data processing applicationsRanking indexData mining
The invention provides a method and device for recommending a keyword. The method comprises the steps of: obtaining a search term of a customer; classifying the customer by utilizing a classifier trained through consuming willingness samples of customers in advance, and determining the consuming willingness of the customer; and selecting the front M keywords from a candidate keyword library according to a comprehensive ranking index to serve as the keywords recommended to the customer, wherein the comprehensive ranking index of the keywords is calculated by utilizing a matching degree of attributive characteristics of keywords and consuming willingness of the customer and semantic relevancy between the keywords and the search item, and the M is a preset positive integer. The method and device for recommending the keyword can save recommendation resource and improve recommendation success rate.
Owner:BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
Contact recommending method and device
The invention discloses a contact recommending method and device. The method comprises the steps of receiving the space-time records, sent by a client side, of a user, wherein the space-time records of the user include the position of the user and the time when the user is at the position; determining a recommendable contact meeting the user at a frequency up to a preset frequency according to the space-time records of the user and pre-stored space-time records of other users; sending the recommendable contact to the client side. Due to the fact that the contact is recommended to the user according to the meeting frequency (which can be regarded as the behavior track of the user) between the user and other users, the success rate of recommendation is increased, and then the hit rate and accuracy of contact recommendation are increased.
Owner:XIAOMI INC
Information recommendation method and device
ActiveCN104615655ARecommended to avoidImprove the success rate of referralsSpecial data processing applicationsThe InternetData science
The invention relates to an information recommendation method and device and belongs to the technical field of internet. The method comprises the following steps of analyzing an obtained message; determining an interest label according to an analytic result, wherein the interest label is used for indicating the interest of a user; transmitting the interest label to a server, wherein the server is used for recommending information to the user according to the interest label. According to the information recommendation method and device, by analyzing the obtained message, the interest label used for indicating the interest of the user is determined according to the analytic result, the interest label is transmitted to the server, then according to the interest label, the server is capable of recommending the information in which the user is interested to the user and avoiding recommending the information in which the user is not interested to the user, and the success rate of recommendation is improved.
Owner:XIAOMI INC
Commodity combination recommendation method and device, electronic equipment and readable storage medium
PendingCN110298725AImprove the success rate of referralsForecastingCharacter and pattern recognitionUser needsData mining
Embodiments of the invention provide a commodity combination recommendation method and device, electronic equipment and a readable storage medium. The commodity combination recommendation method comprises the steps: obtaining user demand information and a commodity provided by a target merchant; generating a candidate commodity combination according to the commodity and the user demand information; obtaining commodity knowledge corresponding to the commodity from a preset commodity knowledge map; predicting candidate scores of the candidate commodity combinations according to the user demand information and the commodity knowledge through a commodity combination score prediction model obtained through pre-training; and recommending the candidate commodity combination to the user accordingto the candidate score. The candidate scores of the candidate commodity combinations can be predicted in real time according to the user demand information for recommendation, and the recommended candidate commodity combinations can be adjusted in real time according to the user demand information, and the recommendation success rate can be improved.
Owner:BEIJING SANKUAI ONLINE TECH CO LTD
Audio-based personalized recommendation method and device and mobile terminal
ActiveCN109558512AGet target audio featuresImprove the success rate of referralsDigital data information retrievalNeural architecturesPersonalizationAudio frequency
The embodiment of the invention provides an audio-based personalized recommendation method and device and a mobile terminal, and the method comprises the steps: training an audio recognition model according to an audio sample set, and enabling the audio recognition model to be obtained through the cascade connection of a convolutional neural network and a recurrent neural network; acquiring a target audio feature of the target user; inputting the target audio feature into the audio recognition model to obtain a target audio vector; obtaining a target object from a candidate object list according to the target audio vector; and recommending the target object to the target user. According to the invention, the target audio vector (sound feature) can be obtained through the audio recognitionmodel to recommend the sound liked by the user to the user, which is helpful for improving the success rate of recommendation.
Owner:GUANGZHOU LIZHI NETWORK TECH CO LTD
File recommendation method and device
ActiveCN104699696AImprove relevanceImprove the success rate of referralsSpecial data processing applicationsIndex term
Owner:SHENZHEN TENCENT COMP SYST CO LTD
Client feature library generating method and device
InactiveCN102591872AHigh precisionImprove efficiencySpecial data processing applicationsData miningCustomer analytics
The invention provides a client feature library generating method, which comprises the steps of: calculating the sum d of intra-class distances under different cluster numbers k, and drawing a k-d value curve; finding a turning point according to the k-d value curve, finding a k value corresponding to the turning point, looking for an optimal cluster number kopt within a range near the k value, and utilizing a cluster result corresponding to the optimal cluster number as a final cluster result. The invention also provides a client feature library generating device. The scheme of the invention can improve the cluster searching efficiency and precision, and the method of the invention is used for performing client analysis according to the obtained client feature library to improve the recommendation success rate and client satisfaction degree of a marketing campaign.
Owner:CHINA MOBILE GROUP SICHUAN
Intelligent financing service recommendation method and system
InactiveCN108711107AImprove the success rate of referralsImprove recommendation efficiencyFinanceBiological neural network modelsSupport vector machineDecision model
The invention relates to the technical field of financial service computers, and discloses an intelligent financing service recommendation method and system. According to the method, historical data is used for training a logistic regression model, a decision tree model and a support vector machine model; then the predicted probability values of the outputs of the three models are used as eigenvalues to be input into a neural network for performing secondary training; after the training is completed, the logic regression model, the decision tree model, the support vector machine model and theneural network form a multi-model fusion system so as to predict a success probability of matching a specific customer demand with a specific financing product; and the financing product is recommended to the customer demand according to the success probability, so that the recommendation success rate can be greatly improved.
Owner:上海钱智金融信息服务有限公司
Product pushing method and device, computer equipment and storage medium
PendingCN110297968AImprove the success rate of referralsDigital data information retrievalBuying/selling/leasing transactionsThird partyProduct type
The invention discloses a product pushing method and device, computer equipment and a storage medium. The product pushing method comprises the following steps: receiving identity identification information, a credit state and credit information of a user sent by a third-party service platform, and record data of a preset time period; analyzing a product type that a user is interested in accordingto the record data; determining a target level of the user according to the credit information; obtaining a product object level matched with the target level, and determining a product correspondingto the product object level as a target product; if the identity identification information does not exist in the preset database, pushing the target product to the user; and otherwise, obtaining theeffective product, and pushing the target product different from the effective product to the user. According to the technical scheme, the data resources of the third-party service platform are effectively utilized, and the products capable of being simultaneously matched with the product purchase requirement and the payment capability of the user are recognized, so that the product recommendationsuccess rate is increased.
Owner:CHINA PING AN LIFE INSURANCE CO LTD
Target customer positioning method and device based on micro-expression, equipment and storage medium
PendingCN109858958AImprove the success rate of referralsSave the cost of manpower explanationCo-operative working arrangementsCharacter and pattern recognitionPattern recognitionCorrelation coefficient
The invention discloses a target customer positioning method, device and equipment based on micro-expressions and a storage medium. The method comprises the steps of obtaining a product recommendationrequest which comprises a target product ID; querying a product information database based on the target product ID, and obtaining target product voice data and target product text data; displaying the target product text data and playing the target product voice data, and starting a camera to shoot video data of a potential customer, the video data comprising at least one frame of to-be-identified image; recognizing each to-be-recognized image by adopting a micro-expression recognition model to obtain a corresponding micro-expression type and a correlation coefficient; calculating the micro-expression type and the correlation coefficient by adopting an investment willingness formula to obtain a target investment willingness; and if the target investment willingness is greater than the preset willingness threshold, determining the potential customer as the target customer. The method can achieve the accurate positioning of the target customer, and facilitates the improvement of the recommendation success rate of a target product.
Owner:ONE CONNECT SMART TECH CO LTD SHENZHEN
Financial product recommendation device and method and computer readable storage medium
InactiveCN108399565AImprove the success rate of referralsFinanceBuying/selling/leasing transactionsMachine learningProduct data
The invention discloses a financial product recommendation device. The financial product recommendation device comprises a memory and a processor; a financial product recommendation program which canbe operated on the processor is stored on the memory; and the program is executed by the processor to realize the following steps of: extracting a matter feature corresponding to a target customer from a matter information table; calculating satisfaction degree levels, for held financial products, of the target customer according to the matter feature of the target customer and a preset classification model; selecting to-be-recommended financial products for the target customer according to product data of the held financial products of the target customer and the satisfaction degree levels for the held financial products; obtaining a contact medium corresponding to each matter, in the matter information table, of the target customer, and predicting common contact media of the customer according to the obtained contact media; and recommending the financial products to the target customer through the common contact media. The invention furthermore discloses a financial product recommendation method and a computer readable storage medium. According to the financial product recommendation device and method and the computer readable storage medium, the financial product recommendationsuccess rate is improved.
Owner:PING AN TECH (SHENZHEN) CO LTD
Recommendation method and device, electronic equipment and computer readable storage medium
PendingCN111859020AImprove accuracyImprove the success rate of referralsMetadata video data retrievalSpecial data processing applicationsEngineeringSocial behavior
The invention relates to a recommendation method and device, electronic equipment and a computer readable storage medium. The recommendation method comprises the steps that recommendation is conducted, obtaining information of a candidate composition set corresponding to the target user, and determining the association degree between the target user and each candidate author according to the social behavior data of the target user, screening out the target author from the candidate authors according to the association degree, and recommending works belonging to the target author in the candidate works set to the target user. The method is based on social behavior data of a target user. According to the method, the association degree between the target user and different candidate authors is determined, the target author which the target user is potentially interested in can be accurately positioned according to the association degree, and then the works of the target author which the target user is interested in are recommended to the target user, so that the recommendation accuracy is improved, the watching time of the user is prolonged, and the recommendation success rate is increased.
Owner:BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
Application recommendation method and electronic device
InactiveCN107544966AImprove satisfactionImprove the success rate of referralsSpecial data processing applicationsData miningComputer science
Owner:BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
Video display method and device
ActiveCN106897398AImprove the success rate of referralsSpecial data processing applicationsUser needsComputer graphics (images)
The invention provides a video display method and device and relates to the field of video search technology. The method comprises the steps that a video search term input by a user is received; the position and size of a cold start window are determined according to the video search term; video sets relevant to the video search term are acquired from a reverse index and divided into a new online video set and a non-new online video set according to uploading time; superior indexes are calculated according to the number of times of display, the click rate and the expected click rate of all videos in the new online video set; and all the videos with the superior indexes ahead in the new online video set are displayed in the cold start window of a search result display region, and all videos in the non-new online video set are displayed in a non-cold start window. In this way, the problem that display of the new online videos does not meet the demand of the user and is poor in quality, and consequently the recommendation success rate of the new online videos is lowered is solved, and the video display method and device have the advantage of increasing the recommendation success rate of the new online videos.
Owner:BEIJING QIYI CENTURY SCI & TECH CO LTD
Intelligent insurance recommendation system and computer storage medium
PendingCN110399559AImprove experienceImprove the success rate of referralsDigital data information retrievalFinanceRecommendation modelComputer science
The invention discloses an intelligent insurance recommendation system and a computer storage medium. The system stores an insurance type recommendation model and a due insurance amount model corresponding to a preset guarantee type. The system comprises an information collection module which is used for obtaining the user information inputted by a user at an input interface and obtaining the existing insurance amount of the user at each preset guarantee type; a guarantee gap calculation module used for calculating the due insurance amount of the user and calculating the guarantee gap of the user according to the existing insurance amount; an insurance type recommendation module used for inputting the user information into the insurance type recommendation model to obtain a to-be-recommended insurance type; and judging whether the to-be-recommended insurance type is used as a primary insurance type recommended to the user or not. According to the technical scheme, objective and customized insurance type recommendation can be realized for the user according to the actual condition of the user and the insurance type recommendation model. Therefore, the user can purchase non-just-needed products without advertisement induction.
Owner:阳光保险集团股份有限公司
Building house type and recommender matching method, device and equipment and storage medium
PendingCN109872258AImprove the success rate of referralsAvoid self-choiceBuying/selling/leasing transactionsData matchingComputer terminal
The invention discloses a building type and recommender matching method and device, equipment and a storage medium, and the method comprises the steps: reading a corresponding building keyword in a cooperation information query instruction when the recommender receives the cooperation information query instruction sent by the recommender based on a terminal, and determining a target building according to the building keyword; searching for cooperation information corresponding to the target building, judging whether the cooperation information is effective cooperation or not, and if the cooperation information is effective cooperation, obtaining historical sales data of the target building based on the cooperation information; and according to the identity information of the recommender, capturing historical recommendation data of the recommender, and according to the historical recommendation data and the historical sales data, carrying out matching between the building type of the target building and the recommender. According to the scheme, the historical sales data and the historical recommendation data are matched based on data processing in the big data technology, the building house type suitable for recommenders to recommend is searched, and the recommendation success rate of the recommenders to the building house type is improved.
Owner:PINGAN CITY CONSTR TECH SHENZHEN CO LTD
Application recommendation method and device
InactiveCN107305559AImprove the success rate of referralsEfficient recommendationData processing applicationsSpecial data processing applicationsComputer scienceUser information
The embodiment of the invention discloses an application recommendation method.The method includes: acquiring application preference scores of users and user information; determining a comprehensive similarity degree between the users according to the user information; and determining recommended applications according to the application preference scores and the comprehensive similarity degree. The embodiment of the invention also discloses an application recommendation device at the same time.
Owner:CHINA MOBILE GRP GUANGDONG CO LTD
Product recommendation device and method and computer readable storage medium
ActiveCN107818492AImprove the success rate of referralsFinanceBuying/selling/leasing transactionsData science
The invention discloses a product recommendation device based on the user influence, which comprises a memory and a processor, and is characterized in that the memory stores a product recommendation program capable of running on the processor. When being executed by the processor, the program implements the steps of acquiring identity information of a target user and a pre-constructed social relation network diagram, wherein the social relation network diagram is constructed according to social relation data and wealth scores of users having insurance service data and banking service data simultaneously; searching associated users of the target user in the social relation network based on the identity information, and calculating an influences score of the target user according to the wealth scores of the target user and the associated users; and selecting a bank product and / or an insurance product corresponding to the influence score for the target user, and recommending the band product and / or the insurance product to the target user. The invention further provides a product recommendation method based on the user influence and a computer readable storage medium. The success rateof product recommendation is improved according to the invention.
Owner:PING AN TECH (SHENZHEN) CO LTD
Method and apparatus for presenting information to be issued
ActiveCN104918210AImprove accuracyImprove the success rate of referralsLocation information based serviceWorld Wide Web
Owner:BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
Application program recommendation method and device
ActiveCN110134863AImprove the success rate of referralsImprove experienceData processing applicationsDigital data information retrievalPersonalizationCognitive power
The invention discloses an application program recommendation method and device which are applied to teaching equipment. The method includes: obtaining user information in the running process of an application program, wherein the user information comprises user identity information, age information and operation information of a user on the application program; assessing the user capability according to the user information, and obtaining capability information of the user, the capability information comprising one or a combination of more of the thinking capability, the language capability,the action capability, the cooperation capability and the self-cognition capability of the user; and recommending one or more application programs to the user according to the capability information of the user, the one or more application programs being matched with the capability information of the user. According to the application program recommendation method and device provided by the invention, the application can be recommended to the user adaptively and individually, the application program recommendation success rate is improved, and the user experience is improved to a great extent.
Owner:北京小红果文化科技有限公司
Painting recommendation method, painting recommendation device, equipment and storage medium
PendingCN108510373ASolve the low recommendation success rateImprove the success rate of referralsBuying/selling/leasing transactionsKnowledge representationMatrix decompositionComputer science
The invention discloses a painting recommendation method, a painting recommendation device, equipment and a storage medium. The painting recommendation method comprises the following steps of: acquiring user behavior information, wherein the user behavior information comprises single behavior information and combined behavior information, single behaviors indicate behaviors generated through operating a class of intelligent terminals by users, and combined behaviors indicate behaviors through operating at least two classes of intelligent terminal by users; calculating preference values, to paintings, of users according to user behavior information, to the paintings, of the users, and constructing a two-dimensional preference matrix, for the paintings, of the users; and carrying out collaborative filtering-based matrix decomposition on the two-dimensional preference matrix so as to output predicted preference values, for paintings, preference of which is unknown, of the users, and realizing painting recommendation according to the predicted preference values. According to the method, the problem that the traditional painting recommendation method is low in recommendation precision can be solved through importing a plurality of user behaviors.
Owner:BOE TECH GRP CO LTD
Data recommendation method and apparatus
ActiveCN106445974AExpand the scope of information matchingImprove matchWebsite content managementSpecial data processing applicationsData miningWeb page
Owner:TENCENT TECH (SHENZHEN) CO LTD
Platform parking system, method and device and storage medium
PendingCN110322151AExpand the scope of recommendationsFlexible displayResourcesMarketingThe InternetComputer terminal
The invention discloses a platform parking system, method and device and a storage medium, and belongs to the technical field of the Internet. The method comprises the following steps that: a first terminal acquires entry auditing information, wherein the entry auditing information comprises personal information of a first user and authorization information of a target platform; and the first terminal sends the entry auditing information to the management background, and the management background audits and confirms the entry auditing information; the personal information of the first user isdisplayed on a related page of a target platform managed by the merchant in response to check confirmation of the check-in check information through the management background. Personal information ofa first user is displayed on a target platform managed by a merchant, so that the first user and the merchant coexist on the target platform. The display mode is flexible, so that more second users can obtain the personal information of the first user through the target platform, the first user can recommend merchants to the second users conveniently, the recommendation range of the merchants is expanded, the number of the merchants is increased, and the recommendation success rate is increased.
Owner:BEIJING SANKUAI ONLINE TECH CO LTD
Product recommendation method and device, server and storage medium
PendingCN111932296AImprove the success rate of referralsAdvertisementsSpeech recognitionEngineeringData mining
The embodiment of the invention discloses a product recommendation method and device, a server and a storage medium. The method comprises the steps: obtaining the user data of a target customer, and determining a user feature vector X = (x1, x2,..., xn) T according to the user data; calculating according to the user feature vector X = (x1, x2,..., xn) T and the weight vector Wi = (wi1, wi2,..., win) T of the ith product in the products to obtain a recommended predicted value zi = WiT * X of the target client for the ith product; converting the recommendation prediction value of the ith productinto a probability, obtaining a recommendation success probability value of the target client for the ith product, and determining the product corresponding to the maximum recommendation success probability value of each product as the target product; obtaining customer service corpora of the target product from a customer service corpus; and when the recommendation triggering condition is met, sending customer service corpus to the target client. By adopting the method, the product recommendation success rate can be improved.
Owner:CHINA CONSTRUCTION BANK
Notice recommendation method and mobile terminal
InactiveCN107423147AImprove the success rate of referralsInterprogram communicationInformation typeComputer science
The invention provides a notice recommendation method and a mobile terminal, and relates to the technical field of communication. The notice recommendation method is applied to the mobile terminal and comprises the following steps that: obtaining effective information collected by a preset sensor, wherein the effective information comprises environment information and / or biological information; according to a preset corresponding relationship between a pre-installed application and an information type, determining a target application corresponding to the effective information; and according to the notice recommendation template of the target application and the effective information, generating a target notice message. By use of the scheme disclosed by the invention, the problems that notice recommendation is disordered and messy and the effective information is difficult in acquisition are solved.
Owner:VIVO MOBILE COMM CO LTD
Product recommendation method and device, electronic equipment and readable storage medium
PendingCN112148995AAccurate recommendationImprove the success rate of referralsDigital data information retrievalFinanceAnalytic modelEngineering
The invention relates to an intelligent recommendation technology, and discloses a product recommendation method, which comprises the steps of determining a first feature of each user, and grouping the users based on the first features to obtain a plurality of user groups; calculating a product permeability array corresponding to each user group in the plurality of user groups; determining a target user group corresponding to the to-be-recommended user; obtaining a second feature factor corresponding to the product recommendation request, determining a second feature of the to-be-recommended user based on the second feature factor and the second historical data, and inputting the second feature into the attribute analysis model to obtain a target attribute value of the to-be-recommended user; and when the target attribute value is smaller than a preset threshold, recommending a target product to the to-be-recommended user based on the product permeability array corresponding to the target user group. The invention further provides a product recommendation device, electronic equipment and a readable storage medium. The product recommendation success rate is improved.
Owner:ONE CONNECT SMART TECH CO LTD SHENZHEN
Multimedia recommendation method and apparatus
InactiveCN106547874AImprove interaction abilityImprove the success rate of referralsSpecial data processing applicationsFile sharingWeb technology
The present invention discloses a multimedia recommendation method and apparatus, and belongs to the field of network technologies. The method comprises: when a camera starting instruction is received, acquiring a location of a mobile terminal; sending a recommendation information acquisition request to a server, wherein the recommendation information acquisition request carries a location; receiving target multimedia recommendation information sent by the server, wherein the target multimedia recommendation information is used for recommending a multimedia file shared by any user at a specified location, and the specified location is within a geographical region with the location of the mobile terminal as a center; and displaying the target multimedia recommendation information in a viewfinder of a camera of the mobile terminal. According to the method and apparatus disclosed by the present invention, when the mobile terminal starts the camera, the viewfinder of the camera is used as a display background, and the multimedia recommendation information that is acquired based on the location of the mobile terminal is displayed in the viewfinder, so that a display effect of combining with the actual scenario is achieved, and the display method is highly interactive, and a recommendation success rate can be effectively increased.
Owner:GUANGZHOU KUGOU TECH
Intelligent service recommendation algorithm based on big data and computer readable storage medium
PendingCN110348877AImprove the success rate of business recommendationImprove the success rate of referralsBuying/selling/leasing transactionsMarket data gatheringGenerative adversarial networkRecommendation service
The invention provides an intelligent service recommendation algorithm based on big data and a computer readable storage medium, and the algorithm mainly comprises the steps: generating an adversarialnetwork based on an embedding algorithm, so as to map object data Ce into a feature two-dimensional matrix Ct; training a service recommendation neural network Nr based on a service recommendation deep learning algorithm of the object features, and inputting the feature two-dimensional matrix Ct to generate an initial recommendation service probability RS matched with the object; training a neural network to learn historical service data of the recommender based on a personalized matching algorithm of the neural network to form a personalized network Nci; and the personalized network Nci takes the initial recommended service probability RS data as input to show the target service recommendation probability PRS of the object to the recommender, so that the service recommendation success rate of the recommender is improved.
Owner:SHANGHAI UNIV
Information recommendation method and device based on question contribution degree and computer equipment
ActiveCN110502639AImprove the success rate of referralsFinanceSpecial data processing applicationsKnowledge graphMachine learning
The invention discloses an information recommendation method and device based on question contribution degree and computer equipment. The information recommendation method comprises the steps: obtaining an initial association question list corresponding to each topic in a constructed initial knowledge graph; obtaining a first value question chain set and a second value question chain set accordingto the question chain of each user in the selected target user community and the corresponding operation result information; obtaining a question retention degree queue ranked in an ascending order according to the question retention degrees of the questions in the second value question chain set; obtaining a target question set of each topic; obtaining the number of questions, the same as that of the target question set, in the initial association question list; and obtaining the questions of which the descending rank of the question contribution degrees in the question contribution degree queue does not exceed the target question replacement number to serve as a replacement question set. According to the information recommendation method, different user communities are divided accordingto interests, historical access records are divided into valuable and non-valuable question chains, and question contribution degree queues in the user communities are periodically calculated and adjusted.
Owner:PING AN BANK CO LTD
Commodity recommendation method, system and related device
PendingCN112053213AIncrease salesImprove the success rate of referralsMarket predictionsBuying/selling/leasing transactionsOperations researchIndustrial engineering
The invention provides a commodity recommendation method, which comprises the steps: acquiring the purchase quantity of target commodities by a target user in a past preset time period and the actualsales quantity of the target commodities in the preset time period; determining the purchase permeability of the target user according to the purchase quantity; determining a predicted purchase quantity of the target commodity according to the purchase permeability; determining a suggested purchase quantity of the target commodity according to the actual sales quantity, the predicted purchase quantity and a temperature coefficient; and taking the target commodity of which the suggested purchase quantity is greater than a preset threshold as a recommended commodity. According to the invention,the influence of the sales rate, the purchase quantity and the temperature of the target commodity on the sales quantity is comprehensively considered, and the recommended commodity is determined based on the suggested purchase quantity, so that the sales quantity of the recommended commodity is improved. The invention further provides a commodity recommendation system, a computer readable storagemedium and an e-commerce management terminal, which have the above beneficial effects.
Owner:杭州拼便宜网络科技有限公司
Who we serve
- R&D Engineer
- R&D Manager
- IP Professional
Why Patsnap Eureka
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com