43results about How to "Improve Personalized Experience" patented technology

A method of network merchandising incorporates contextual and personalized advertising with human input to deliver relevant retail offers to interested online consumers efficiently and intelligently. Catalog content from retailers is downloaded, semantically analyzed and merged. The merged content is filtered using machine- and human-generated specifications to produce a merchandisable universe of products (MUP). Marketers and publishers create and modify corner store ad units and specify product offers from the MUP to display in those units. Publishers deploy the ad units on their web pages. Compensation of publishers by retailers can use a pay-for-performance model. Users visit the publisher's pages, viewing the product offers in the rendered ad unit. Performance data related to context, history, network and geo-location, product attributes and product combinations is derived from server log files is used to dynamically optimize and refine product placement in real time, providing a highly personalized experience for the user.

The invention relates to a group positioning method and terminal equipment for group positioning. The group comprises at least two terminals in communication linkage with a server. The method comprises the following steps: at least one terminal which logs in a group sends a request which obtains the position information of other terminals logging in the group to a server at a preset time interval M; at least one of other terminals logging in the group is selected, the position information is positioned and displayed on an electronic map according to an input checking order and the position information of a selected terminal, which is sent by the server; the position information of the selected terminal is sent by the selected terminal to the server at preset time interval T. The technical scheme of the invention ensures that group members can mutually query position information and realize quick positioning and navigation and can obtain and update continuously changed position information of a certain or a plurality of members, which is expected to know by users in time, and thus, the invention has convenient operation, increases user personalized experience and shortens positioning and checking time.

This invention provides a method for getting EPG and the IPTV service system, in which, the method includes: IMS terminal of the IP multimedia subsystem transmits the EPG applied matched data drafted by a user to the IPTV applied server and assigns EPG media resource based on the data and sends it to the user terminal. The IPTV service system includes: IPTV applied server used in receiving the EPG applied matched data drafted by a user and sent by the IMS terminal and provides them to the IMS center, which is used in distributing EPG media resource according to the matched data and sending it to the user terminal.

The invention discloses a voice control method and device, and a terminal. The example operation of a user can be learned in a voice control process, and a voice response execution model is obtained. The voice response execution model comprises execution instructions corresponding to the execution of all operations, and is enabled to be correlated with a corresponding voice instruction. When a voice instruction inputted by the user is received, the execution instruction in the voice response execution model correlated with the voice instruction can be trigged and executed, so as to start a function application corresponding to a terminal. Therefore, the method can learn the example operation of the user, and obtains the corresponding voice response execution module. In other words, different users can carry out the personalized customization of the voice control function according to the needs, so the method can meet the personalized demands of different users. The method gets rid of a conventional solidified mode of voice interaction with the terminal, improves the personalized experience of the users, and meets the personalized demands of the users.

The invention discloses a control method and system of an air-conditioner, a readable storage medium and an air-conditioner. The control method is applied to a cloud server and the air-conditioner. The cloud server is in communication connection with the air-conditioner and an intelligent terminal. The control method includes the steps that after a control signal of one-key memory is received, theoperation habits of a user in every moment on one day or several continuous days are statically recorded, a historical operation habit database is obtained, and the statistical modes include the usermanual input mode; an automatic operation control instruction of the user is received; under the automatic operation control instruction, the historical operation habit database is acquired; and theair-conditioner is controlled to automatically run in the corresponding moments according to the operation habits in the historical operation habit database. Repeated operation of the air-conditionerin all scattered time periods by the user is avoided, the effect of relieving and saving efforts for the user is achieved, the using experiences of the user are improved, the data statistical modes include the user manual input mode, and thus conveniences and rapidness are achieved.

The invention discloses an intelligent vehicle personalized driving learning system based on a smartphone. The intelligent vehicle personalized driving learning system based on the smartphone comprises an information collection module, a data pre-processing module, a mode identifying module, a statistical analysis module, a model establishing module and a data matching module, wherein the information collection module is used for collecting information by using the smartphone after an automobile owner obtains an artificial intelligence automobile; the data pre-processing module is used for combining collected data into a new data set; the mode identifying module is used for dividing the data collected by the smartphone into seven modes according to daily trip; the statistical analysis module is used for carrying out statistical analysis on the data in different modes; the model establishing module is used for establishing a user driving characteristic model; the data matching module isused for initializing driving characteristics of the trip of the intelligence automobile on the basis of a pre-established user driving behavior characteristic template library; and in the trip process, the user driving characteristic model is directly matched online in real time in different models so that the intelligence automobile trip has personalized driving characteristic of the automobileowner and the personalized demand of the automobile owner is met. According to the intelligent vehicle personalized driving learning system based on the smartphone, the personalized driving of the intelligence automobile is realized by using the smartphone so that the personalized experience of a user is improved.

The disclosed transfer method for multimedia information between terminals in calling comprises: the calling terminal starts the process; after negotiation between the calling and called, it builds a transfer path for multimedia information; the called terminal extracts information from itself to send to the calling terminal. By this invention, user can set multimedia information easily for individual experience, and the provider can reduce running cost.

The invention provides a monitoring system working method. The monitoring system working method mainly comprises the following steps: step 1: a monitoring camera sends video information to a snapshotserver, and the snapshot server parse a human face image from the video stream and sends the image and related parameters of the image to a snapshot theme in a distributed issuance subscription message system as snapshot records; step 2: a crowd counting module reads the video information of the monitoring camera, counts the number of people from the video stream, and sends the counted number of people, the camera information and the current time to a crowd counting theme in the distributed issuance subscription message system as crowd counting records; and step 3: a storage module consumes the crowd counting records, and displays corresponding thermodynamic diagram distribution on a display module according to the counting records and a monitoring range corresponding to the camera. Structured extraction is performed on the offline data of customers by using the computer vision technology, the online and offline data are fused by using a human face ID as a bridge, the reconstruction ofpeople, goods and fields is achieved at least, an effective structured data support is provided, and a foundation is laid for the subsequent big data analysis application.

The invention discloses a terminal for performing bidirectional live sharing and intelligent monitoring and a method thereof. The terminal comprises a camera, an audio acquisition unit, a displayer, a loudspeaker and a transceiver. The transceiver transmits videos and audios, which are respectively acquired by the camera and the audio acquisition unit, to a specific address in real time via a dedicated channel, receives the videos and the audios in real time from the specific address via the dedicated channel and outputs the videos and the audios via the displayer and the loudspeaker respectively, and the transceiver is responded to identification of a person or a specific person, or a specific motion, or an abnormal situation in the videos and the audios acquired by the camera and the audio acquisition unit respectively. The transceiver transmits prompt information to the specific address in real time. The dedicated channel is established in advance. The terminal is used for trusted fixed occasions. Compared with terminals in the prior art, user real-time communication experience is enhanced so that a user monitors the onsite situation of the specific occasion or the specific person in a more convenient and safer way.

The invention relates to a resource processing method and device of a mobile terminal, and equipment. The method comprises the following steps: determining a current application scene and use data ofthe mobile terminal; inputting the use data into a machine learning algorithm model corresponding to the current application scene to obtain predicted recommendation parameters; and configuring resources of the mobile terminal based on the recommendation parameters.

The invention provides an adjustment method and an adjustment device of an intelligent television portal interface which can be adjusted according to the requirements of a user. The method comprises following steps: step S1, obtaining a template library of a portal interface for user to adjust and use, and receiving a user instruction to enter an adjustment interaction interface; step S2, receiving an adjustment instruction sent by the user based on the interactive interface, wherein the adjustment instruction is used for adjusting the module position and / or the size of each element in the interactive interface; step S3, receiving the saving instruction sent by the user, saving and generating the adjusted interface. The adjusting device comprises an interface obtaining module, an interfaceediting module and an interface storage module. By simple instruction operation, WYSIWYG page components, functional layout and content presentation, and other page configurations are carried out toget the desired personalized portal, which is truly the realization of intelligent television terminal user interface varies from person to person in a rich form, enhances the intelligent television user self-service definition, and personalized experience, and enhances the user experience.

The embodiment of the invention relates to a method for managing user personalized information in a digital photo frame and a digital photo frame. The method comprises the following steps: receiving the input user identification information; comparing the consistency of the input user identification information and the registered user identification information, and if so, displaying the interactive interface of the digital photo frame at least containing the file write function; receiving a user file sent by an external storage device according to the file write command input on the interactive interface; and storing the received user file and the user identification information in an associative memory. When a plurality of users use the same digital photo frame, the invention can call corresponding system setup parameters and private contents for different users, thereby protecting the personal information and enhancing the personalized experience of users.

The invention discloses a sequence recommendation method and system based on federal learning, and belongs to the field of personalized recommendation and the field of user privacy protection. According to the method, personal information and real-time and historical data of a user are stored locally, each client can perform state representation according to own historical data, an interaction relationship between the user and an article is captured, and a recommendation process is regarded as a serialized decision process based on deep reinforcement learning; according to the method, an attention mechanism is introduced into an aggregation algorithm of federated learning, correlation of feature information extracted by each client and data difference brought by individuation of each client are considered, a weight coefficient is formulated for each client, which is a fine-grained re-weighting means, the individuation degree of data is increased, and the robustness of the data is improved. According to the method, the recommendation accuracy is improved, the method is more suitable for the field of sequence recommendation, and personalized recommendation for the user is realized while personal data privacy is protected.

The invention relates to the technical field of machine learning, deep learning, data mining and the like, in particular to a hierarchical Attention deep learning model course recommendation method. According to the method, dynamic changes of user interests are modeled by utilizing user sequential behavior data and using LSTM, and long-term and short-term preferences of a user are obtained by constructing a hierarchical Attention structure, so that advanced mixed representation of the user is generated, and user personalization and accuracy of a recommendation result are improved. The method specifically comprises the following steps: performing screening and preprocessing by using original online learning related behavior data, dividing the sequential behavior of a user into sessions, and then processing three types of data of fine granularity (information user ID and course ID) and coarse granularity information (course type) by using an embedding layer and a full connection layer to obtain user vector representation; capturing interaction and evolution of different historical session interests of a user by applying LSTM (Long Short Term Memory) to obtain a serialized interest vector, and inputting the interest vector into an Attention network to obtain long-term interest representation of the user; inputting the recent behavior data and the long-term interest representation of the user into a second-layer Attention network to obtain a mixed interest representation of the user; and finally, carrying out inner product on the mixed interest representation and the course vector representation of the user, taking an obtained value as a score of the candidate item, and sorting the scores of the candidate item to obtain a recommendation list for carrying out personalized recommendation on the student.

The invention discloses a cross-dynamic filling method for relieving a data sparsity problem in a recommendation system. The method comprises the steps of (1) preprocessing e-commerce user behavior data and obtaining a user information table and a product information table, (2) establishing a user-commodity-score matrix, (3) calculating a user similarity and a product similarity according to the established user information table and product information table, and (4) carrying out data sparsity processing: gradually filling the user-commodity-score matrix through a user similarity and productsimilarity cross-dynamic filling method. Compared with a single user and commodity similarity information filling method, the method has the advantages that the user similarity and the product similarity are skillfully combined, the user-commodity-score matrix can be filled well, and thus the data sparsity problem in recommendation can be relieved. An accurate recommendation can be carried out foreach user, a user personalized experience is improved, merchant sales are promoted, and merchant revenue is increased.

The invention relates to an elevator system. The elevator system comprises a power supply, a main controller, a control circuit, a fingerprint information acquiring module, a fingerprint storing module, a fingerprint verifying module and a fingerprint control module, wherein the fingerprint information acquiring module, the fingerprint storing module, the fingerprint verifying module and the fingerprint control module are sequentially connected; the fingerprint information acquiring module is connected with the power supply and is used for acquiring, extracting and storing fingerprint characteristic information of an elevator user; the fingerprint storing module is used for storing a fingerprint template of a user and floor information used by the user; the fingerprint verifying module is used for comparing the fingerprint characteristic information acquired by the fingerprint information acquiring module with the fingerprint template pre-stored in the fingerprint storing module and verifying the identity of the user; the fingerprint control module is connected with the main controller and is used for sending the floor information used by the user to the main controller when the fingerprint identity verification passes. The legal identity of the elevator user is verified by acquiring a fingerprint, the floor used by the user and reached by the user can be controlled according to the identified user floor information, the safety of the use of an elevator is improved, and the individual experience of the user is enhanced.

The invention provides an electronic device based on MEMS technology, comprising a rollover sensor which comprises: a rollover sensing element for detecting rollover angle of the electronic device and outputting a corresponding electric induction signal; and a wafer layer connected with the rollover sensing element for outputting a control signal corresponding to the electric induction signal. The rollover sensing element of the rollover sensor is used for detecting the rollover angle of the electronic device and outputting the corresponding electric induction signal, and the wager layer is used for receiving the electric induction signal for outputting the corresponding control signal. Compared with the prior art, users can operate the electronic device without carrying out a series of complex operations on the control panel, the corresponding control signal is formed through an intuitionistic rollover instruction to enable and disable or switch an application function, and accordingly the electronic device compatibility is improved and the user customized experience is enhanced.

The invention discloses a picture processing method, a mobile terminal and a device. The method comprises that a first instruction for editing a first specific picture is received; in response to thefirst instruction, a suspended editing layer is displayed in the first specific picture; handwriting information input by handwriting is received in the suspended editing layer; and the handwriting information is synthesized with the specific picture, and a synthesis picture is generated. Thus, the handwriting information can be added to the picture, so that a user can share mood and stories related to the picture, and the customized experience is improved.

The invention provides a medical information system based on the Internet of Things and a control method thereof. The medical information system is connected to a gateway of the Internet of Things ofa family, connection between the medical information system and all intelligent home devices in the family is achieved, the individuation using requirements of different family members for the different intelligent home devices in the illness state are met accordingly, and user experiences are improved; through the method, control instructions can be sent to the intelligent home devices based on medical record information, the usage condition of the intelligent home devices can also be fed back to the family members, and as the method is a bidirectional information transmission mechanism, thefamily members and doctors can know the illness condition of users in time, and therefore the treatment effect is improved; identities of patients are distinguished based on information such as ages of the users, different intelligent-home and guardian managing methods are executed respectively according to the condition with guardians and the condition without guardians respectively, the method is more pertinent, and individuation experiences are improved.

The invention discloses a dual system-based shortcut menu management method and a mobile terminal. The method comprises the following steps of: in a first operation system, obtaining an instruction for adjusting the state of a first shortcut switch in a first shortcut menu bar from a second state to a first state; if the state of a currently set first shortcut switch in a second operation system is the second state, storing the state of the set first shortcut switch in the second operation system, and adjusting the states of the first shortcut switches in the first operation system and the second operation system to the first state; and when the fact of switching from the first operation system to the second operation system is monitored, switching the state of the first shortcut switch of the second operation system back to the second state from the first state. Through above manner, the shortcut switches can keep different settings when different operation systems are used, so as to enhance the individualized experiences, for the different operation systems, of the users.

The invention discloses a method and a system for adjusting the color of a browser. The method comprises the following steps of: receiving a color call instruction of adjusting the browser of a user; enabling the browser to call a color application program interface API of an OS (Operation System), providing a browser color call scheme according to the API and ensuring that a corresponding mapping relation exists between the browser color call scheme and an OS color call scheme; and appointing the OS color call scheme called for displaying the color of the browser according to the color call instruction of the user. With the adoption of the technical scheme, the method and the system have the beneficial effects that the user can directly utilize the existing color configuration scheme of the operation system and does not need to download a resource packet, so that the network width and the resources are saved; and moreover, color schemes capable of being configured by the user are more, so that the personalized experience of the user is improved.

The invention relates to the technical field of natural language processing, in particular to an end-to-end target guide type conversation method based on deep learning, which comprises the followingsteps: S1, acquiring a previous round of user conversation and a current conversation history, and initializing a sequence to a sequence model according to the previous round of user conversation andthe current conversation history; S2, determining a row number of a current knowledge base entity; S3, determining a column number of the current knowledge base entity; S4, obtaining an optimal matching entity through an attention mechanism; and S5, iteratively executing the steps S2-S4 until the next round of conversation is finally output. According to the invention, the technical defects of lowend-to-end conversation efficiency and influence on personalized experience of users in the prior art are overcome, and good user service is provided through the accuracy of natural language conversation.

The invention discloses a terminal and a method for two-way live sharing and intelligent monitoring. Wherein, the terminal includes: a camera, an audio collection unit, a display, a loudspeaker, and a transceiver, wherein the transceiver sends the video and audio collected by the camera and the audio collection unit to a specific address in real time through a dedicated channel, and transmits the video and audio collected by the audio collection unit through a dedicated channel. Receive the video and audio from the specific address in real time and output them through the display and speakers respectively, and identify people or specific people, or specific actions, or abnormal conditions in response to the video and audio collected from the camera and audio acquisition unit respectively , the transceiver sends reminder information to the specific address in real time, wherein the dedicated channel is established in advance, and the terminal is used in a trusted fixed place. Compared with the prior art, the present invention improves the user's real-time communication experience, and is beneficial for the user to more conveniently and safely monitor the on-site situation of a specific place or a specific person.

The invention discloses an intelligent control system and control method based on a slide rail television. The intelligent control method comprises: starting; a somatosensory interaction device acquires user gesture information, and sends a moving or stopping instruction to a mobile control module; the mobile control module controls a main body of the slide rail television to move; a displacementsensor acquires the position information of the main body of the slide rail television to determine whether the main body of the slide rail television is stationary; if "Yes", the process proceeds tothe next step, and if "No", the position information of the main body of the slide rail television is continuously acquired; the play control module determines the area where the slide rail televisionis located and plays an associated video according to the position information of the main body of the slide rail television main body; and ending. Therefore, the method realizes the intelligent movement of the slide rail television and the intelligent playing of the video, eliminates the complicated and solidified control process, can allow a user to control the slide rail television to move tothe designated position and play the specific promotional video, makes promotion video playing in a business place or an exhibition hall more concise and efficient, and can save the time of the user.

The invention belongs to the field of automobile parts, and particularly relates to a multifunctional automobile lampshade which can charge an automobile storage battery or directly supply power to other automobile power consumption parts through a transparent photovoltaic cell panel and can intelligently adjust the transmissivity and color of electrochromism according to information such as music rhythm to generate dynamic change patterns. The multifunctional automobile lampshade comprises a photovoltaic cell panel (1), an electrochromic film (2), an electrochromic driving module (3), a storage battery (6) and a lampshade (8), the electrochromic film (2) is arranged on the inner surface of the photovoltaic cell panel (1), the lampshade (8) is arranged on the outer surface of the photovoltaic cell panel (1), the photovoltaic cell panel (1) is electrically connected with the storage battery (6), the storage battery (6) is electrically connected with the electrochromic driving module (3), the electrochromic film (2) comprises a film base material (21), a plurality of sub-pixel modules are arranged in the film base material (21), and the electrochromic driving module is electrically connected with the sub-pixel modules.

The embodiment of the invention discloses a method, device, server and storage medium for generating a virtual gift list in a live broadcast room. Among them, the method includes: obtaining the information of the live broadcast room, the information of the target audience in the live broadcast room and the information of each virtual gift; according to the information of the live broadcast room, the information of the target audience and the information of each virtual gift, the Degree of liking: according to the degree of liking of each virtual gift by the target audience, a list of virtual gifts corresponding to the target audience is generated. The method provided in this embodiment can generate a list of virtual gifts according to the personalized needs of the target audience for virtual gifts, and improve the audience's personalized experience of sending virtual gifts.

The invention provides a device and a method for classifying users based on identification information. The device includes acquiring a page request sent by the users through a user device; acquiring identification information corresponding to the page request according to the page request; and classifying the users based on a preset classification algorithm according to the identification information to acquire category information of the users. By the method compared with the prior art, the identification information corresponding to the page request is acquired and a large number of users are classified according to the identification information, and accordingly the user category information corresponding to the page request is convenient to determine. Further, the device and method for classifying users based on identification information are applied to the fields of network browsing, search application and the like, different response pages can be provided for users of different categories based on the acquired user category information, and individual user experience is enhanced while processing capacity of network application is continuously improved.

The invention discloses a dual system-based shortcut menu management method and a mobile terminal. The method comprises the following steps of: in a first operation system, obtaining an instruction for adjusting the state of a first shortcut switch in a first shortcut menu bar from a second state to a first state; if the state of a currently set first shortcut switch in a second operation system is the second state, storing the state of the set first shortcut switch in the second operation system, and adjusting the states of the first shortcut switches in the first operation system and the second operation system to the first state; and when the fact of switching from the first operation system to the second operation system is monitored, switching the state of the first shortcut switch of the second operation system back to the second state from the first state. Through above manner, the shortcut switches can keep different settings when different operation systems are used, so as to enhance the individualized experiences, for the different operation systems, of the users.

The invention provides a customizable position privacy protection method and system based on a user portrait, and the method comprises the steps: firstly, constructing a decentralized communication network, obtaining the position of a stay point in a movement track of a user, and querying the semantic information of the position from a position server through the decentralized communication network; secondly, portraying the user from two aspects of basic attributes and psychological characteristics of the user, and quantifying privacy requirements of the user through the characteristics of the user; and finally, according to the privacy demand of the user, the position server carries out privacy intensity recommendation on the user, and the local end carries out personalized dynamic adjustment according to the local real-time scene information of the user. According to the method, the customized dynamic protection of the user position data can be realized, the problem that the leakage of sensitive position information of the user cannot be effectively solved in an actual position social network environment is solved, and the personalized experience of the user is improved.