31results about How to "Good personalized service" patented technology

The invention provides an individualized online news comment mood forecast method capable of fusing multiple information sources. The online news comment mood forecast method capable of fusing multiple information sources is put forward on the basis of online news comment mood forecast based on a single information source. Online news comment mood forecast is achieved through the single information source on the three aspects of user comments, news texts and user mood votes. By combining the various heterogeneous information sources, the forecast accuracy is greatly improved. The method put forward is remarkably superior to other alternative methods of online news comment mood forecast and has higher superiority when processing a large number of comment sets large in difference. The method can be used for user sentiment analysis and public sentiment supervision.

The invention discloses a webpage text and image ordering method based on the concerning time of the users, which comprises the following steps: 1) the personalized improvement is conducted to the current webpage ordering based on the concerning time, so that the ordering result meets the psychology of the users; 2) a custom browser is used to collect the sample information of the text concerning time; 3) the custom browser collects the sample information of the picture concerning time; 4) the collected concerning time samples are corrected; 5) the concerning time of the unknown web pages is predicted based on the text and picture similarity; 6) personalized web pages and pictures are generated based on the concerning time by integrating with the traditional searching technology to order. The method effectively integrates the liking of the users into the searching process, so that the final ranking result is closer to the ideal ranking expected by the users, so that the webpage text and image search engines offer better personalized service to the users.

The invention relates to a method and a device for automatically updating a user interest model. The method particularly includes the steps: filtering push messages according to a current user interest model, and displaying the push messages to a user; acquiring feedback data after the user browses the push messages, and automatically updating the user interest model after analyzing the feedback data. According to the method and the device for automatically updating the user interest model, messages not interesting the user are filtered by the user interest model, the user interest model is automatically updated according to feedback of the user, so that better personalized service is provided for the user, and search efficiency is improved.

The invention discloses an individualized webpage recommending method based on the detection of the facial expression and the sight distribution of a user, comprising the following steps of: (1) detecting a focusing point of the sight of the user on a screen when the user reads a webpage; (2) detecting the facial expression of the user when the user reads the webpage, and estimating the reading concentration degree of the user at each moment; (3) estimating the reading interest of the user in each autonomous word according to the webpage read by the user; (4) predicting the reading interest of the user on a webpage which is not read by the user; and (5) generating an individualized webpage recommending result by utilizing reading interest of the user and combining with the traditional searching technology. The invention combines the reading concentration degree of the user with the searching and sequencing process of the webpage by effectively utilizing the facial expression and the sight distribution of the user when the user browses the webpage, thereby enabling the final individualized webpage recommending result to be more approximate to an expected result of the user.

The invention relates to a user net surfing time control method, which includes steps mentioned below in a user login process. Firstly, according to an account used by a login user, an AAA server (3) finds a corresponding allowed net surfing time segment from the corresponding relationship between the user account which is prearranged in the AAA server and one or a plurality of allowed net surfing time segment. The AAA server refuses the login of any user out of the allowed net surfing time segment or allows the login of a privileged user in the allowed net surfing time segment and notifies a network access server (2) to force the user out of the line when the allowed net surfing time segment is over. Compared with the prior art, the control method can specify the net surfing management more effectively and provide various users with better personalized service.

The invention discloses a method for searching and sequencing personalized web pages based on user retention time analysis. The method comprises the following steps of: firstly, obtaining document-level user retention time through a custom web browser; accordingly, predicting concept word-level user retention time; then, according to the predicted concept word-level user retention time, further predicting personalized reading interests of a user to each web page in any web page searching result; and finally, according to the personalized reading interests of the user, generating a personalized web page searching result facing to the user. In the method disclosed by the invention, by using an artificial intelligent related technology and methods for searching web pages, processing texts and the like, reading interests of users to different concepts can be estimated; therefore, personal reading habits and requirements are considered in the process for searching and sequencing the web pages; and the sequencing of the web page searching results is closer to the user personalized prediction result, therefore, better network search and browser support are provided for users.

The invention discloses a webpage text individualized searching method based on eyeball tracking, which comprises the following steps: 1) sample information of webpage text concerned time of a user is obtained by the use of an eyeball tracking device; 2) a user concerned time sample obtained is corrected; 3) an appropriate text similarity algorithm is dynamically selected by the application of a decision tree for an unknown webpage text; 4) the user concerned time of the unknown webpage text is predicted based on the text similarity; and 5) individualized webpage text searching results are generated by the use of the user concerned time and by the combination of traditional searching technology. The webpage text individualized searching method based on eyeball tracking effectively obtains individual reading interest of the user through the eyeball tracking device and combines the favorite of the user with the webpage text searching process, thus rendering the final webpage text searching ranking results to be closer to the ideal ranking expected by the user.

The invention discloses a method for constructing TV user portraits. The method comprises the following steps: step 1, collecting data of TV terminal users through a data platform, and analyzing and classifying the data; step 2, pre-defining a TV user portrait tag; step 3, classifying data of type B, and constructing a first level tag of the TV user portraits of the data of type B; step 4, classifying data of type C, and constructing the first level tag of the TV user portraits of the data of type C; step 5, constructing second level tags of the TV user portraits of the data of type B and type C; step 6, merging and counting each type of first level tags and each type of second level tags of the TV user portraits; step 7, analyzing program type preference attribute data of the TV users, and constructing TV user portrait tags; and step 8, updating the pre-defined TV user portrait tags into the constructed TV user portrait tags. According to the method disclosed by the invention, the viewing behavior data of the TV users are analyzed to master the preference of the users so as to provide better personalized service for users.

The invention relates to an English text automatic abstracting method based on eye tracking. Existing methods can not generate a personalized text abstract aiming at different readers. The method comprises the following steps of: obtaining the concerning time of a user to all words in a text when reading an electronic text by utilizing an eyeball tracking device or a camera; predicating the user interest in all sentences based on test similarity; and generating a personalized automatic abstracting result by utilizing the combination of user interest and text automatic abstracting algorithm. The method can effectively combine the user interest in an English text automatic abstracting process so as to lead the final test automatic abstracting result to be more similar to the abstract content expected by the user, thereby causing automatic abstracting software to provide better personalized service to the user.

The invention discloses a network video ordering method based on user concerned time, which utilizes the user concerned time to carry out an individualized improvement against the searching results obtained by a network video searching engine so as to render the search ordering results of network videos to better meet needs of the user. The network video ordering method based on the user concerned time comprises the following steps: 1) the concerned time of the user for every network video in the network video searching results is obtained by the use of a user-defined web page browser; 2) every user concerned time obtained is corrected; 3) the user concerned time of every key frame in unknown network videos is predicted based on image similarity; 4) the user concerned time of unknown network videos is calculated through the user concerned time of every key frame of the video; and 5) the network videos obtained by the network video searching engine are respectively reordered by the use of the user concerned time obtained or predicted. The network video ordering method based on the user concerned time effectively combines the favorite of the user with the network video searching process, thus rendering the final network video ordering results to be closer to the ideal ordering expected by the user.

The invention discloses a method of correcting the positional accuracy of a target space for an artificial limb. The method comprises the steps of initially locating a series of targets by using a method of realizing carrying out space positioning to a random target by virtue of the artificial limb with multi-degree of freedom so as to obtain an integration of a series of target point positions, and leaving the integrations a training input sample set of an artificial neural network; precisely measuring an integration of the practical three-dimensional coordinate values of a series of targets, leaving the integration of the practical three-dimensional coordinate values as the training input sample set of the artificial neural network, building the artificial neural network, and enabling an output value of the artificial neural network to be close to a real value close to a target after the fully training. The actual output of the artificial neural network is close to the true value when the training input sample integration and parameters close to the training input sample integration are input into a network, so that a precision correcting model for carrying out space positioning on a random target by an upper limb artificial limb with multi-degree of freedom or a robot can be formed to effectively correct the positioning precision of the target by the artificial neural network.

The invention discloses a webpage image individualized searching method based on eyeball tracking, which comprises the following steps: 1) sample information of webpage image concerned time of a user is obtained by the use of an eyeball tracking device; 2) a user concerned time sample obtained is corrected; 3) an appropriate image similarity algorithm is dynamically selected by the application of a decision tree for an unknown webpage image; 4) the user concerned time of the unknown webpage image is predicted based on the image similarity; and 5) individualized webpage image searching results are generated by the use of the user concerned time and by the combination of traditional searching technology. The webpage image individualized searching method based on eyeball tracking effectively obtains individual reading interest of the user through the eyeball tracking device and combines the favorite of the user with the webpage image searching process, thus rendering the final webpage image searching ranking results to be closer to the ideal ranking expected by the user.

The invention discloses a device and a relevant method that integrates user identification information on televisions; the device comprises: A core circuit board, a radio frequency identification RFID reader, a MCU, a storage and a RFID tag; wherein, the MCU and the storage are arranged on the core circuit board; the RFID reader is used to identify RFID tag and read information in RFID; the MCU is respectively connected with the RFID reader and the storage through buses, and performs analysis on information that is received from the RFID reader, in order to extract user information before storing into the storage; the storage is used to store programs and relevant data; The RFID tag is used to receive radio frequency signal from the RFID reader, and return self-codes and self-storage information to the RFID reader. The invention aims at the defect in current televisions that cannot identify user personal information; a television is integrated with a set of device to identify user information; through information interaction between the radio frequency identify reader and the television, the television can identify different users' personal information, so as to provide the users with better and more individualized services.

The invention discloses a network video individualized searching method based on eyeball tracking, which comprises the following steps: 1) sample information of network video concerned time of a user is obtained by the use of an eyeball tracking device; 2) a user concerned time sample obtained is corrected; 3) an appropriate image similarity algorithm is dynamically selected by the application of a decision tree for an unknown network video; 4) the user concerned time of each key frame in the unknown network video is predicted based on the image similarity; 5) the user concerned time of the video is calculated by the concerned time of each key frame in the video for the unknown network video; and 6) individualized network video searching results are generated by the use of the user concerned time and by the combination of traditional searching technology. The network video individualized searching method based on eyeball tracking effectively obtains individual reading interest of the user through the eyeball tracking device and combines the favorite of the user with the network video searching process, thus rendering the final video searching ranking results to be closer to the ideal ranking expected by the user.

The invention relates to an intelligent path planning method and system applied to a passenger transport service place. The method comprises the following steps: acquiring a face image of a user entering the place in the passenger transport service place; performing identity recognition on the user according to the face image, and determining identity information of the user; inquiring communication information of a mobile terminal bound with the user according to the identity information of the user; acquiring ticket information of the user from the travel order of the user according to the identity information of the user; querying the position of the corresponding entrance according to the ticket information of the user; planning a route in the passenger transport service place by taking the current position of the user as a starting point and the position of the entrance as an end point; and pushing the planned route to a mobile terminal bound with the user. By adopting the methodand the system, the identity of the user is automatically identified after the user enters the passenger transport service place, the ticket information is automatically queried, and then the route tothe entrance is automatically queried and pushed to the user so that the user can quickly find his entrance.

A search method includes the steps: searching data in a search database according to inputted search keywords, and returning a search result; acquiring feedback information of a user on the search result; and judging whether the corresponding search result is a junk datum or not according to the feedback information, adding the feedback information and the corresponding search result into a junk database if the corresponding search result is the junk datum, and adding the feedback information and the corresponding search result into the search database if the corresponding search result is not the junk datum. By the aid of the method, search accuracy can be also improved without manual operation, so that workload of a background is reduced. Besides, the invention further provides a search system.

The embodiment of the invention discloses a user portrait determination method and device in the field of artificial intelligence, equipment and a storage medium, and the method comprises the steps: determining an audio resource played by a target user in a target time period, and taking the audio resource as a reference audio resource; obtaining an audio coding feature corresponding to the reference audio resource, wherein the audio coding feature is obtained by processing an audio sequence of the reference audio resource through an audio coder; and according to the audio coding feature corresponding to the reference audio resource, determining an interest feature of the target user as a target audio portrait of the target user. The method can be suitable for a network platform for providing audio resources for a user, can determine the audio portrait for reflecting the preference of the user for the audio resources, and is helpful for the network platform to provide better personalized services based on the audio portrait.