45 results about "Information behaviour" patented technology

Methods and apparatuses of determining a time for sending information, wherein a method includes obtaining n1 time periods during which an information receiving party most often opens information based on a result of statistics collected in advance for information related behavior of the information receiving party; and determining an information sending time for the information receiving party using the n1 time periods. The methods of present disclosure can predict a proper sending time for an information receiving party according to information related behavior of the information receiving party, which improves the probability that the information receiving party opens the information, and thereby promotes the effect of effectively reading the information.

The invention discloses an information generation method and device. The method comprises the steps: obtaining the behavior information of a user and the information of a target when determining to recommend the target to the user, and obtaining the behavior information of the user and the information of the target in each preset scene according to at least one of the current environment information, behavior information and target information of the user and the attribute information of each scene; determining a plurality of scenes as specified scenes, and generating and displaying recommendation information for recommending the target to the user through a generation template corresponding to the specified scene for each specified scene according to at least one of the environment information, the behavior information and the target information. As the recommendation information browsed by the user has the characteristics of user preferences and targets, compared with existing recommendation information, the recommendation information generated in the specification is more attractive to the user, and the user can be effectively assisted in making decisions.

The present invention provides a method and system for determining information similarity. Based on the time when information is consumed, the information consumed by each user is sorted to obtain the corresponding first information behavior sequence; the first information behavior sequence corresponding to all users is The sequence is integrated to obtain the second information behavior sequence; calculate the first similarity between each pair of information with a co-occurrence relationship in the second information behavior sequence; based on the second information behavior sequence, construct a topological map between information; use The graph convolution algorithm calculates the second similarity between each pair of nodes in the topological graph; based on the first similarity between each pair of information with a co-occurrence relationship, combined with the second similarity between each pair of nodes in the topological graph The second similarity is to determine the final similarity between each pair of information in the second information behavior sequence. Combine the two methods to calculate the final similarity between information, increase the amount of information covered by the method of calculating similarity, and then improve the accuracy of information recommendation.

Embodiments of the present invention provide a method and device for identifying batch accounts, at least for solving the technical problem of identifying batch accounts. The method includes: obtaining behavior record information of the account to be identified, which represents the registration and / or use behavior of the account; obtaining behavior record information of other accounts; based on the behavior record information of the account to be identified and the Behavior record information of other accounts, calculating the degree of similarity between the registration and / or usage behavior of the account to be identified and the other accounts; if the degree of similarity reaches a preset level, identify the account to be identified as a batch account.

The embodiment of the present application provides a method for updating a data flow type identification model and related equipment, the method includes: determining the first data flow type corresponding to the current data flow according to the packet information and the behavior recognition model of the current data flow; The relationship and the general characteristics of the current data flow determine the second data flow type corresponding to the current data flow, wherein the target correspondence is the correspondence between multiple general characteristics and multiple data flow types; if the first data flow corresponding to the current data flow If the type is different from the type of the second data stream corresponding to the current data stream, the correction data corresponding to the current data stream is obtained, wherein the correction data corresponding to the current data stream includes the message information of the current data stream and the second data corresponding to the current data stream Stream type, the correction data is used as training samples to update the behavior recognition model. This way of obtaining training samples for updating the action recognition model is more efficient.

A campus message push optimization method based on GIS system. First, according to the personal information of campus members, the decision tree classification algorithm is used to classify members into corresponding groups, and then based on the GIS system, the campus information behavior of campus members is counted, and the characteristics are classified and given. Each feature is given a certain weight, and then the redundant information in the campus push messages is removed through big data technology, and the classification results are classified according to the characteristics of campus members, and then an analysis model is constructed. Finally, different campus members are classified according to the weight and interest characteristics. Push different messages. The present invention can meet the push message requirements of different campus members.

The invention discloses a campus management system and method, comprising: an image acquisition device for acquiring image information of school personnel; a server comprising: an identity identification module storing a trained first artificial intelligence model for identifying the image information, Obtain the identity information of the school personnel; the behavior recognition module identifies the behavior data of the school personnel according to the image information and the identity information of the school personnel; the classification module stores the trained second artificial intelligence model, and uses the school personnel identity information and the school personnel The personnel behavior data classifies the school personnel; the output module outputs the corresponding management strategy according to the classification results. Through the combination of artificial intelligence technology, the real, reliable, real-time and efficient acquisition of the behavior data of school personnel is carried out; the situation of students in school is classified through artificial intelligence technology, and data support is provided for the improvement of teaching quality and campus security, so that the campus management strategy is aimed at School staff to formulate and implement reasonably and accurately.

The invention discloses a device and technology for reading life cycle information of OFD format files. The invention directly reads the binary flow content in the OFD format file through the decompression technology, and obtains the life cycle file in the OFD format file through step-by-step searching. The method of the present invention enables people not only to read the content of the OFD file itself, but also to effectively consult the life cycle information of the OFD format file through the device and technology; to directly read the binary stream content in the OFD format file through the decompression technology, and to Effectively omit the process and time of decompressing to a temporary directory, and improve the reading efficiency of OFD format files. Regardless of whether the file is in the application environment or after it leaves the application environment, you can quickly and efficiently see the main process information and behavior information of its life cycle in the original application system.