42results about How to "Reflect personalization" patented technology

A recommendation method based on collaborative filtering includes: acquiring target user identification, searching user group identification corresponding to the target user identification, acquiringsimilarity between items confirmed according to user-item grade matrix corresponding to the user group identification; and recommending item to the target user according to the similarity between items. By adopting the recommendation method provided by the invention, accuracy of item recommendation can be improved, and user experience can be improved. The invention also provides a recommendation system based on collaborative filtering.

The invention relates to a smart voice processing method and belongs to the technical field of information processing. The smart voice processing method is characterized by achieving smart identification of identities of multiple talkers in the multi-person voice environment and separating mixed voices by building a talker voice model base so as to obtain independent voice of each talker, amplifying voices of the talkers to be heard according to user demands and eliminating voices of talkers not required by the users. Different from the traditional hearing aid, the smart voice processing method can be used for automatically providing needed voices for the users according to user demands, reduces interference of non-target voices except for noise, and has individuation, interaction and intelligentization.

The present invention discloses the dynamic customization method of the menu of a client media player, which can dynamically adjust the sorting sequence of menu items. The regulation method includes four steps; firstly, the data table of the menu items is created on a client, and a menu management module assigns specified initial defaults to the sequence numbers of the menu items; secondly, one menu item on the client media player is clicked for one time, the click count of the menu item is added by one; thirdly, in the data table of the menu items, the menu management module sorts all the menu items according to the click counts of the menu items, and reassigns a new sequence number to each menu item according to the sorting sequence; fourthly, the menu management module adjusts the relative position of each menu item in the sequence of the menu items according to the sequence number of each menu item. The present invention can allow the publisher of a media player to conveniently conduct statistics on the operations of a large number of users and work out accurate statistics in order to design a better, more humanistic media player.

The invention discloses a robot active inquiry method based on a traditional Chinese medicine clinical knowledge graph. In the inquiry process, the robot has the initiative right of the knowledge graph, the information of a patient is collected through multiple times of inquiry, diagnosis and iteration are conducted to complete an inquiry task, and then final diagnosis is conducted. The method relates to the knowledge graph, knowledge expression learning, knowledge reasoning technology and a syndrome type diagnosis iteration model. According to the invention, the problems of high complexity and big difficulty of artificial intelligence traditional Chinese medicine inquiry can be solved.

The invention provides a search method and a search device based on a genetic algorithm. The method comprises the following steps of: analyzing contents according to pages browsed by a user, and clustering the pages according to information subjects to form a user interest model; selecting an individual with the most ideal fitness function value according to a fitness mean value, and optimizing the user interest model; queuing the searched page set, sorting according to degree of association, and preferably searching the pages with high degree of association so as to obtain the pages with high degree of association. The invention reflects the individuality of the user and improves the search accuracy.

The invention discloses a management method and device of Bluetooth services. The management method of Bluetooth services comprises the following steps that: a local Bluetooth device sets different Bluetooth services to be provided for different remote Bluetooth devices; the local Bluetooth device receives a request message of one remote Bluetooth device, wherein the request message is used for requesting for the Bluetooth service in the local Bluetooth device; the local Bluetooth device judges whether the requested Bluetooth service belongs to the set Bluetooth services in the Bluetooth services to be provided corresponding to the remote Bluetooth device; and if so, the local Bluetooth device and the remote Bluetooth device start the requested Bluetooth service. The method and the device solve the problem that the privacy and the security of the information cannot be guaranteed in the management of the Bluetooth services in the prior art, thus, personalization and humanization in use of the Bluetooth services by users are embodied.

Through XML script file, user carries out configuration of script for interface. Parser for script file setup in PMP player parses information of script file customized by user, and reflects parsed result to final interface display. The invention discloses a fast and simple method to let user change interface according to own requirement.

The invention provides theme search algorithm based on a body, which comprises steps of establishing theme models based on the body; matching appropriate member search engines according to different theme models; and processing search results. The theme search algorithm based on the body is the theme search algorithm with good performance based on the body, can effectively meet different search requirements for different themes of different users, and obtains a high precision ratio under the premise of ensuring the recall ratio.

The invention discloses an LED light guide strip vehicle decoration product which comprises a light guide strip and an LED light source correspondingly arranged at the end part of the light guide strip, wherein the light guide strip and the LED light source are integrated into a whole through a light source box; the LED light source is fixedly arranged in the light source box; and the LED light source is electrically connected with an external power supply arranged outside the light source box through an LED constant current driving circuit arranged in the light source box. The integrated structure overcomes the defect of difficult mounting in the prior art, has the decoration effect on vehicle trims, achieves the aesthetic effect and embodies the individuation; and moreover, the product is arranged into an obvious light emitting decoration of points, lines and planes as required and arranged on the body of a vehicle, which can guarantee that a third party can timely find the product so as to avoid personal injuries and deaths which are caused by mutual collisions, thereby improving the travelling safety.

The invention provides a daily intelligent mirror and a using method, relates to the technical field of intelligent furniture, and mainly solves the technical problems that an existing daily mirror issingle in function, intelligently recommends for human beings, matches a dressing scheme and purchases a product. The intelligent mirror comprises a mirror frame and a touch screen mirror which is embedded in the mirror frame and provided with a face recognition induction switch, a plurality of cameras are evenly arranged on the mirror frame at equal intervals, and a function module is arranged in the mirror frame. The function module is connected with the camera and the touch screen mirror and used for providing solutions related to dressing up, shopping and communication for a user according to user images collected by the camera and outputting the solutions to the user through the touch screen mirror. The intelligent dressing and dressing system integrates makeup trial and makeup, dressing up and shopping communication, user experience is greatly improved, and the intelligent mirror has the advantages of being intelligent, user-friendly and personalized.

The present invention provides one kind of stone-grain aventurine tile. It consists of transparent color glass 0-80 wt%, optical glass 0-80 wt% and color glass grains and glass aventurine 20 wt%. The making process of the stone-grain aventurine tile is also provided. The stone-grain aventurine tile is noble, magnificent, strong in visual effect and artistic and may be used widely in indoor and outdoor decoration.

The invention discloses a text generation method and device, which are used for acquiring a text model capable of representing a word matching rule of a text type, and generating a target text by utilizing the word matching rule according to words in a user lexicon of a user. Wherein each user has a user lexicon, and words in the user lexicon of each user can reflect the individuation of the user.According to the method and the device, the words in the user lexicon of one user are utilized, and the target text is automatically generated by utilizing the text model, so that the target text canbe quickly generated, and the generated target text can better reflect the individuation of the user.

The invention provides a method and a device for realizing music play in an instant messaging interface. The method comprises the steps of: starting a note input mode in the instant messaging interface; receiving characters in the instant messaging interface input by a current user; determining character information of the characters; determining note playing information based on the character information; and regarding the character information containing the note playing information as an instant message and sending the instant message to an opposite terminal so as to enable the opposite terminal to display the characters in the instant messaging interface based on the instant message and realize the music play based on the note playing information. By using the method for realizing the music play in the instant messaging interface provided by the invention, character content can be displayed in the instant messaging interface of the opposite terminal and notes corresponding to the characters can be played at the same time. Therefore, music play is realized, information interaction modes of the instant communication are enriched, the instant communication information is enabled to have a plurality of presentation modes, and the interestingness of the instant communication is enhanced.

The invention relates to a storage method and a device. The storage device comprises the following steps: classifying storage contents, respectively allocating storage space for each type of the storage contents, and storing the storage contents into corresponding storage space according to types of the storage contents. The storage method and device can reduce the amount of codes for software development, improve the development efficiency, and enable products to be personalized and differentiated.

Embodiments of the invention disclose a Do Not Disturb (DND) method for instant communication and an instant communication client, applied to the technical field of information processing. In the method provided by the embodiments, by obtaining the first user setting information, including the start time, the ending time and the application date information of the instant messaging client enteringthe DND mode by the instant messaging client, it may be determined that whether the instant messaging client needs to enter the DND mode according to the current time of the instant messaging clientand the first user setting information, so that the instant messaging client automatically switches between the non-Do Not Disturb mode and the Do Not Disturb mode. The instant messaging client sendsthe first time zone information of the current area to the instant messaging server, so that the instant messaging server may determine that the instant messaging client does not send the informationreceiving notification to the instant messaging client when entering the Do Not Disturb mode in the current area, and the instant messaging client does not trigger the ringing logic for the information receiving notification, and further does not affect the user.

The invention discloses a picture operation method based on a knowledge graph. The picture operation method is picture search operation and comprises the steps of receiving keywords, 1, obtaining pictures labeled with search words, identifying the labeled search words of the pictures, and if the search words are any one of the keywords, synonyms, hypernyms, subordinate words and related words, returning to the pictures; 2, in the returned picture, the marked search words are in front of a picture row of keywords and keyword synonyms, the marked search words are behind a picture row of keywordhyponyms, keyword hyponyms and keyword related words, and if a user finds a target picture from the arranged picture, the search is completed; If the user does not find the target picture from the arranged pictures, executing the step 3; And step 3, after the associated keywords and the returned picture are labeled with the search words, repeating the step 1 and the step 2 until the target pictureis found in the returned picture. The method can improve the picture search efficiency with small calculation overhead.

The invention relates to the field of information, in particular to a system and a method for displaying commodity information on electronic tag screens, an issuer and a manager. The system comprises the issuer, the manager and more than one electronic tag screen. The method which corresponds to the system comprises the following steps that: A, the manager receives dynamic commodity display information which is edited by the issuer and corresponds to the more than one electronic tag screen, wherein the dynamic commodity display information comprises serial numbers of the electronic tag screens, and commodity information display contents and a commodity information display mode, which correspond to a certain electronic tag screen; B, the manager processes the dynamic commodity display information and converts the dynamic commodity display information into the displayable information of the electronic tag screens; and C, the managers transmits the processed displayable information to the electronic tag screens which correspond to the dynamic commodity display information, and the electronic tag screens display the displayable information. By the invention, the commodity information can be electronically operated.

The invention discloses a doll machine system capturing a player expression automatically. An inner cavity of a doll machine main box body carries a pad display screen; the bottom of the pad display screen is provided with a doll falling window, an ultrasonic detection radar is clamped on the inner wall of the doll falling window, an output end of the ultrasonic detection radar is provided with abackground control system, and an output end of the background control system is provided with a viewfinder camera. According to the doll machine system capturing the player expression automatically,the ultrasonic detection radar transmits an electric signal generated during falling of a doll to the background control system, the background control system transmits a photographing command to theviewfinder camera, the pad display screen receives and displays a real picture, and the player can see the real-time expression picture when grabbing the doll. The player expression capturing functionhelps make the player happier, records moments, embodies difference and characteristic of the product, and maximizes the psychology of entertainment of the player.

The invention provides an interactive face identification system and method. The method comprises the following steps that: firstly, a face graph is searched in a face database according to a requirement from a user or a face graph is generated randomly in the face database; secondly, when the face graph is searched in the face database according to the requirement from the user, a face graph meeting the requirement is estimated and recorded, a genetic algorithm operation is carried out on the face graph, and whether the user is satisfied with the face graph is determined; if so, the face graph is outputted; and if not, a searched face graph meeting the requirement is estimated again and recorded; and thirdly, when the face graph is randomly generated in the face database, a new fitness value of the face graph that is generated randomly is obtained, a genetic algorithm operation is carried out on the face graph, and whether the user is satisfied with the face graph is determined; if so, the face graph is outputted; and if not, a new fitness value of the face graph that is generated randomly is obtained.

The present invention relates to a portable radio frequency identification integrated management control electronic guide communication method which, through an electronic display control unit, carries out real-time monitoring on signal transmissions of a miniature piezoelectric type buzzer, a portable radio-frequency circuit chip, a double-layer cavity filter, a signal-tuning monitor unit, a frequency allocation deposit recognizer and an indication sensing positioner respectively connected to the electronic display control unit, and finishes the portable radio frequency identification integrated management control process of the electronic guide communication signal transmission in the following way. Long-standing problems in a guide communication method of the prior art such as low transmission speed, low anti-interference capability, low expandability, high unit cost of user side application, and high system management maintenance cost in the guide communication system.

A double stitching needle and thread presser foot device for a crank arm type sewing machine comprises a single cut presser foot and a mesh pattern hook drive sector piece. A presser foot push rod ofa sewing machine head penetrates the single cut presser foot and the mesh pattern hook drive sector piece, a right mesh pattern long curved needle fixing sleeve and a right mesh pattern short curved needle fixing sleeve are arranged on two sides of a presser foot push rod through hole of the single cut presser foot, a left mesh pattern frame fixing cylinder is arranged at the edge of the upper endof a presser foot push rod through hole of the mesh pattern hook drive sector piece, a rotating shaft of a right mesh pattern long curved hook drive rod vertically penetrates the right mesh pattern long curved needle fixing sleeve, a right mesh pattern long curved hook with a hook body wound on the right side is fixed to the lower end of the right mesh pattern long curved hook drive rod, a horizontal portion of the right mesh pattern long curved hook drive rod is rotatably connected with the left side of the mesh pattern hook drive sector piece through a right mesh pattern long curved hook drive connecting rod, and a rotating shaft of a right mesh pattern short curved hook drive rod vertically penetrates the right mesh pattern short curved needle fixing sleeve. Two parallel stitches can be simultaneously sewn, and individuation of products and beauty of seam lines can be more effectively embodied.

The invention provides a processing method based on various electronic files and business data needed by making out a bill and applicable to the field of civil aviation passenger transport combined transport, and an electronic entitative bill exported and generated by using the processing method. A civil aviation passenger transport combined transport electronic data processing method and the electronic bill generated by using the civil aviation passenger transport combined transport electronic data processing method have the advantages of achieving unified storage, relevance, management, retrieval and display of electronic files which are multiple in format, type and source, reducing repeated storage of the electronic files, achieving relevance and retrospect of whole process of the electronic files and various business data, improving efficiency and accuracy of business of making out the bill in actual operations, enabling the sources of the business of making out the bill to be clear, and being good in operability.

The invention belongs to the technical field of building thermal environment, and discloses a dynamic temperature control method and system for a personalized air conditioning system based on user status. The method provides users with an indoor environment with dynamic temperature changes by applying the law of outdoor temperature changes to the room, provides users with reasonable thermal stimulation, and well maintains the thermal adaptability of the human body, thereby reducing the user's long-term exposure to The probability of a series of building syndromes such as "air conditioning disease" caused by the steady-state thermal environment, this method sets the user's personal temperature comfort zone as the temperature variation and applies it to the dynamic temperature control method, fully considering individual differences, and more Personalization is embodied; the invention, which takes user comfort as the thermal environment control goal, is more in line with the theoretical viewpoint of thermal adaptation and more satisfying the environmental preferences of people compared with the traditional dynamic temperature control method.

The embodiment of the invention discloses a do-not-disturb method for instant messaging and an instant messaging client, which are applied in the technical field of information processing. In the method of this embodiment, the instant messaging client will obtain the first user setting information, including the start time when the instant messaging client enters the do-not-disturb mode, the end time and the application date information. The first user setting information determines whether the instant communication client needs to enter the do-not-disturb mode, so that the instant communication client automatically switches between the non-do-not-disturb mode and the do-not-disturb mode. The instant messaging client will send the first time zone information of the current area to the instant messaging server, so that the instant messaging server can determine that when the instant messaging client enters the do-not-disturb mode in the current area, it will not send a message reception notification to the instant messaging client , the instant messaging client will not trigger the logic of ringing the message receiving notification, and will not affect the user.

The present invention is an intelligent voice processing method, which belongs to the field of information processing technology. By establishing a voice model library of interlocutors, the present invention realizes intelligent identification of the identities of multiple interlocutors in a multi-person voice environment and simultaneously separates mixed voices to obtain the identity of each interlocutor. Independent voice, according to the user's needs, amplifies the voice of the interlocutor that the user wants to hear while eliminating the voice of the interlocutor that is not required by the user; unlike traditional hearing aids, this method can automatically provide the user with the sound he or she needs based on the user's personal needs. The interference of non-target human voices in addition to noise is reduced, which reflects the personalization, interaction and intelligence of this method.

The invention relates to a head portrait generation method and device, equipment and a storage medium. The method comprises the following steps: acquiring an identification text of an object; converting the identification text into an identification numerical value; obtaining a background color value corresponding to the identification numerical value based on a mapping relation between the numerical value and the background color value; the obtained background color value is set to be the background color of the head portrait of the object, the head portrait of the object is generated, and the head portrait comprises the name indication text of the object. The method is used for providing a solution for the problems that head portraits of different users are difficult to distinguish and head portrait backgrounds and characters are difficult to distinguish in an existing head portrait generation process.

An embodiment of the invention provides a fingerprint module manufacturing method and a fingerprint module. The fingerprint module manufacturing method comprises the steps of: arranging a metal electrode lead wire on a fingerprint identification chip, wherein one end of the metal electrode lead wire is arranged on the top surface of the fingerprint identification chip, and the other end of the metal electrode lead wire is connected with a welding pin on the bottom surface of the fingerprint identification chip; preparing a temperature control heating film on the top surface of the fingerprint identification chip, so as to cover the top surface of the fingerprint identification chip; and preparing a thermochromic ink layer on the top surface of the temperature control heating film, so as to cover the top surface of the temperature control heating film. The fingerprint module prepared by adopting the fingerprint module manufacturing method can exhibit different colors along with different temperatures.

The invention belongs to the technical field of building thermal environments, and discloses a dynamic temperature regulation and control method and system for a personalized air conditioning system based on a user state. According to the method, the outdoor temperature change rule is applied indoors, an indoor environment with dynamic temperature change is provided for a user, reasonable thermal stimulation is provided for the user, and the thermal adaptability of a human body is well maintained, so that the probability of a series of building syndromes such as "air condition syndrome" caused on the user staying at the steady thermal environment for a long time is reduced. According to the method, a personal temperature comfort interval of the user is set as the temperature variation to be applied to the dynamic temperature regulation and control method, and the individual difference is fully considered, so that individuation is better embodied. Compared with a traditional dynamic temperature regulation and control method, the method taking user comfort as a thermal environment control target has the advantages that the method better conforms to the theoretical viewpoint of thermal adaptation and better meets the environmental preference characteristics of people.

The invention discloses a personalized learning recommendation method based on deep reinforcement learning. The method comprises the steps of: defining knowledge points and difficulty attributes of questions, and constructing a knowledge point network graph according to relationships among the knowledge points; determining relationships among the questions under the knowledge points according to the relationships among the knowledge points, and constructing a question network graph; obtaining a sub-graph for a current state of a specified user in the question network graph according to user behavior data to use the same as a learning boundary; and then using a deep reinforcement learning algorithm and user history records for modeling, and obtaining, by training, a strategy of how to select a cut set in the sub-graph under the current state of the user. According to the method of the invention, a best question can be intelligently recommended for the user, user learning time can be saved, learning efficiency thereof can be enabled to be improved, and learning experience can be improved.