33 results about "Preference behavior" patented technology

Video surveillance data is received from multiple disparate, unaffiliated locations at which various items are offered for sale. Based on the content of the video surveillance data, consumer preference behavior is characterized with respect to at least some of the items. The data is consolidated and can be made available for analysis.

The invention discloses a service-place recommendation method based on LBS (Location Based Services) data. The method includes: acquiring the LBS data, which correspond to all users in preset time, from a predetermined database, and carrying out clustering analysis on the acquired LBS data to respectively obtain at least one type of behavior trajectory data, which correspond to all the users, by analysis; analyzing the behavior trajectory data of all the users to obtain similarity between all the users by analysis; clustering all the users on the basis of the similarity between all the users to obtain different user groups; and analyzing LBS data of all users in the same user group to obtain preference behavior trajectories of all the users in the user group by analysis, and sending recommendation instructions for service places on the behavior trajectories of the users in the user group to predetermined terminals on the basis of the preference behavior trajectories which are of all the users and obtained by analysis. According to the method, more accurate recommendation can be provided for the users, and precision of LBS data application can be improved at the same time.

The invention discloses a driver risk preference behavior diagnosis system. The driver risk preference behavior diagnosis system comprises a scene module, a driving simulator and a diagnosis module, wherein the scene module is used for setting multiple design scenes of a specified task object in a driving task normal form; the driving simulator is used for carrying out simulation driving according to the specified task object; the diagnosis module is used for measuring the decision result, the behavior feature index and vehicle dynamics parameters of a driver under the driving task normal form and evaluating the internal risk preference of the driver according to the measurement result to generate a diagnosis report. The diagnosis system is based on the simulation driving task normal form of a virtual reality technology, the driving simulator serves as an evaluation platform, the internal risk preference of the driver is diagnosed by measuring the driver decision behavior and the vehicle dynamics indexes under the standard driving task normal format, the diagnosis reliability is improved, and the road traffic safety is better ensured.

The invention discloses a multi-task television program recommendation method integrating user click behaviors as well as user interests and preferences, which improves the television program recommendation effect through integrating user clicking and multi-task learning of user interests and preferences in television program recommendation. The multi-task television program recommendation methodcomprises the steps of: establishing a clicking model of television programs by a user from historical clicking program data of the user based on an attention network fusion neural network factorization algorithm; establishing an interest and preference model of the user for the programs from the user interest and preference data based on the attention network fusion neural network factorization algorithm; and finally, comprehensively considering the click behaviors of the user and the preference behaviors of the user during recommendation, so that the recommended television programs can better meet the requirements of the user, and the satisfaction degree of the user is improved.

The invention relates to an automatic tracking method of temperature place preference behaviors in laboratory mice. The method at least includes the steps: a laboratory mice temperature stimulation passage is divided into different temperature zones, each temperature zone is provided with a heating plate and a heating plate temperature sensor, each temperature zone is provided with temperature zone boundary left and right sensor bars, the heating plates are electrically connected with a processing unit through a heating control circuit, the processing unit is respectively connected with the heating plate temperature sensors, the boundary right sensor bars and the boundary left sensor bars through signal wires, the processing unit sets certain temperature spots for the different temperature zones through a human-machine interface, the processing unit controls heating through the heating control circuit, the temperatures of the corresponding temperature zones are controlled in the required temperature field accordingly, the temperature zone boundary of the different temperature zones is used for distinguishing a passing direction of the laboratory mouse through the boundary right sensor bars and the boundary left sensor bars, and the durations of the laboratory mouse being in the temperature zones at different times are provided according to recorded durations, and temperature preference behaviors of the laboratory mice are further understood.

The invention discloses a study method of Tet2 sequence preference, and the study method is characterized in that the Tet2 sequence preference is studied by amplified signal differences. According to the invention, small changes of Tet2 action site flanking sequences are performed with signal amplification based on the isothermal amplification technique, differences of main oxidation product contents are detected, so as to realize the study on sequence preference behaviors of Tet2 in the active demethylation process. The study method has the following characteristics: high-throughput detection, capable of achieving simultaneous detection of multiple samples; low detection cost, independent of expensive and complex large-scale instruments; good biocompatibility, unable to cause damage to protein or DNA samples; and simple operation, capable of achieving the transformation of protein behavior differences into amplified signal differences.

Embodiments of the invention provide an information searching method and apparatus. The method comprises the steps of: carrying out search according to keywords sent by a client, and obtaining a plurality of search results; for each search result, obtaining user preference data corresponding to current search results according to stored historical preference behavior information of a user to the current search results; carrying out sorting on the plurality of search results according to the user preference data corresponding to each search result; and returning a sorting result to the client, so that the client can display the sorting result. According to the scheme, different sorting results can be provided for different users, thereby providing effective information for access decisions of the users to the search results.

The invention discloses a fish temperature preference testing experiment device which comprises a main water tank and a low temperature water tank, wherein the low temperature water tank is connectedwith the main water tank through a water conveying pipeline; the main water tank is internally provided with at least one temperature chain; the temperature chains are vertically arranged; a pluralityof temperature sensors are mounted on the temperature chains; the main water tank is also internally provided with a camera system; a plurality of heating devices are arranged inside the main water tank from bottom to top. As low temperature water inside the main water tank is heated at different layers, and a water temperature layering effect is observed through the temperature chains, simulation similarity of a water temperature layering structure is ensured; swimming process of fish individuals or groups in a layered water body is monitored and recorded through a camera mounted inside a water trough, and together with temperature chain observation data, temperature preference behaviors of fishes in a layered environment can be observed and studied.

The invention relates to the field of telecommunication service support, and provides an algorithm for calculating user behavior preference on the basis of exponential regression and maximum likelihood estimation. The algorithm comprises the steps that distribution analysis on user position data and abnormal data removal are conducted; the linear relation between the user activity frequency and the user quality state attribute is fit through negative binomial regression, parameters to be estimated are solved through maximum likelihood estimation, whether parameter estimation passes an inspection or not is checked, and then a regression equation is obtained. Three-quarter quantile of the expense, the flow and call duration is solved, and a critical point of the base station activity frequency is determined through the regression equation, so that the high quality state is achieved while the activity frequency of screened users is guaranteed. According to the algorithm, the problem that a traditional preference extraction algorithm is inaccurate and prone to be disturbed is solved, the preference behavior of the user can be comprehensively taken into account, and the marketing success rate can be increased while marketing recommendation is conducted on the user.

The invention provides a content recommendation method and device based on artificial intelligence, electronic equipment and a computer readable storage medium. The method comprises the following steps: in response to a touch operation of a content presentation interface, obtaining a historical operation behavior of a user account logging in the content presentation interface; determining account attributes of the user account according to the historical operation behaviors; acquiring an account preference behavior conforming to the account attribute, and performing preference analysis processing according to the account preference behavior to obtain preference information of the user account on multiple contents in the content library; determining a content recommendation strategy according to the account attribute and the preference information, and screening out to-be-recommended content from a content library according to the content recommendation strategy; and updating a content presentation interface according to the screened content to be recommended. By means of the content recommendation method and device, accurate content recommendation can be achieved, and meanwhile the actual utilization rate of computing resources consumed when the electronic device conducts content recommendation is increased.

The invention discloses a test device and a research method for migration and habitat preference behaviors of aquatic animals. The test device comprises a water tank with a circulating waterway, a filter screen baffle, a drive water pump, a light-reflecting observation area, a video-recording observation area, a radio frequency identification system and a lighting system. The test device and the research method for the migration and habitat preference behaviors of the aquatic animals have the advantages that field ecological parameter simulation is firstly applied to construction of indoor aquatic animal behavioral research devices and behavioral researches, so that the research devices simulate field ecological parameters (water flow velocity, water depth, river bed materials, river geomorphology and light intensity) to the greatest degree, and research results are closer to real field conditions of the aquatic animals.

The invention discloses a wireless network resource distribution method and system based on user preference of user terminal resources, and belongs to the technical field of wireless communications. Flow generated by terminals within each cell range is sensed at a network core node, actual access points are recorded, user preference application and content are analyzed and extracted, the user concentrated request time and duration time are observed, a user preference behavior library is built, the user preference content is pre-cached in the corresponding access point in advance, and the user preference content keeps synchronous update with a remote server; the specific service requested by users and IMEI numbers of the user terminals are detected at the access points, bandwidth is calculated and ensured according to the service requested by the users, then the types of the terminals are obtained by the utilization of the IMEI numbers, the actual processing capacity of the terminals is determined, the highest bandwidth needed by operation of the terminals is evaluated, relevant information of the access points is obtained from the network core node, a modulation coding strategy and emission power are adjusted, and the total bandwidth capable of being distributed by the access points is calculated. By the method, the users can obtain the needed content rapidly, the bandwidth is distributed in an individuation mode according to the characteristic of the user service request, and the utilization rate of the bandwidth is improved.

The invention relates to the technical field of artificial intelligence, and provides a course recommendation method and device based on artificial intelligence, an electronic device and a medium. The method comprises the following steps of generating a user information matrix in an information field and a user course matrix in a course field, then calculating the similarity between any two users in the information field through the user information matrix, and constructing a first user field set according to the similarity so as to construct a second user field set of the course field according to the user course matrix and the first user field set; migrating the information reading preference behavior of the user to the course learning preference behavior in the course field by using the migration learning thought, and finally carrying out mutual course recommendation for the two similar second users in the second user field set, so that the cold start problem in a course recommendation model is effectively solved, the courses can be recommended to multiple users in a personalized manner at a time, and the mutual recommendation of the courses of the two similar users is achieved.

The invention discloses a fresh agricultural product recommendation method based on multi-granularity fuzzy data. The method comprises the steps of obtaining feature parameters of a user and a product; constructing a feature model based on the feature parameters so as to determine user preference parameters; and inputting the user preference parameters into a multi-granularity fuzzy data recommendation model to obtain a recommendation result, and feeding back the recommendation result to the user. According to the scheme provided by the invention, the user satisfaction is considered based on the similarity between the user preference product and the recommended product. Therefore, in the recommendation process, products meeting the preference behaviors of the user can be recommended, and the optimal recommendation can be generated for the user on the basis. Compared with a current fresh agricultural product e-commerce platform, the method has great practical significance, the conversion rate can be increased, higher benefits can be brought, the user experience can be improved, the user viscosity can be enhanced, and therefore the method has outstanding emphasis in the increasinglyintense market of current fresh agricultural product e-commerce competition.

The invention provides a personalized recommendation algorithm based on crowd sensing, and the algorithm comprises the steps of collecting a large amount of data of the technological process of environmental protection equipment from a multi-source multi-mode data fusion result based on the thought of crowd sensing, and carrying out the feature analysis on the obtained data; during the recommendation process, introducing a Behavior-Intensive Neural Networking framework, wherein the Behavior-Intensive Neural Neural Networking framework comprises two parts, namely, an environmental protection equipment vector generation part and a differentiated behavior learning part; generating a standardized vector for each piece of environmental protection equipment by using a Neural Item Embedded model;and then exploring the interaction sequence of the customer by using a Discovery Behaviors Learning model to obtain the priori knowledge, so as to recommend the environmental protection equipment tothe target customer; and designing two learning modes to explore the user behaviors, namely the session-based behavior learning and the preference behavior learning, and learning the previous behaviors and historical preferences of the customers respectively; and finally, based on the vectorized environmental protection equipment, recommending the first k possible preferred environmental protection equipment to the target customer through the combination of the two learning behaviors.

The invention discloses a cross-correlation collaborative filtering method fusing weak trace behavior preferences of a user. According to the method, weak trace behaviors such as clicking and articlebrowsing time are collected, a scoring matrix and a weak trace behavior matrix of the user are constructed, an arithmetic scoring mean value of the user is assigned to represent weak trace behavior preferences of the user, and a scoring enhancement matrix fused with the weak trace behavior preferences of the user is obtained; the correlation between the user behavior preferences and articles can be described more accurately; furthermore, an improved cross correlation coefficient calculation method is provided, a hot penalty coefficient is fused to construct a user-user preference similarity matrix, the preference similarity of the user to the articles is predicted, and recommendation sorting of the articles with similar preferences is optimized. According to the method, the problem of datasparseness in a traditional collaborative filtering method is solved, and the influence of factors such as different user scoring scales and non-preference behaviors caused by popular factors on userpreference similarity calculation is reduced, so that the accuracy of similar preference recommendation results and sorting is effectively improved.