11 results about "Social software" patented technology

This application provides a method, apparatus, device, medium, and program product for information processing, relating to the field of social software technology. The method displays a decision panel in response to a first trigger operation on a first message in a group chat interface. The decision panel includes a decision-making item obtained based on the first message and the initiator identifier of the decision-making item. In response to a second trigger operation on a second message in the group chat interface, the second message is added to the decision panel for display, serving as the user's decision opinion on the decision-making item. Therefore, when conducting decision-making discussions, users do not need to frequently browse group chat messages; they can simply view the decision-making item and opinion in the decision panel, improving decision-making efficiency and enhancing the user experience.

The invention provides a social software dynamic relationship prediction method and system based on a time sequence knowledge graph. The method comprises the following steps: S1, collecting data in real time; s2, processing time sequence knowledge graph data in the time sequence knowledge graph data set by using a multi-relation time sequence graph attention network, and establishing a fine-grained model; s3, combining the fine-grained model with a GRU network to construct a time evolution path, and outputting user dynamic representation; s4, obtaining static semantic embedding of each user, and taking the static semantic embedding as semantic core representation of the user in a full time span; s5, obtaining a final user representation containing space-time semantic collaborative optimization; s6, judging whether the relation is abnormal or not through a preset abnormal threshold value, and obtaining a prediction result; according to the technical scheme, the problems that in the prior art, social recommendation cannot give consideration to time-space dynamic characteristics and semantic association of user interaction at the same time, and the accuracy of relation prediction in a dynamic scene is insufficient are effectively solved, and a new solution is provided for a social software recommendation system.

An intelligent meeting scheduling method and system based on social media conversations, for identifying meeting requirements in users'daily conversations and relevant participants and recommending suitable meeting times, includes: receiving and storing text messages including message content from a social software platform; scanning the message content to identify meeting-related terms and extract names and department names, and comparing them with organizational structure data to establish a participant list; accessing electronic calendar data of each participant in the participant list to read scheduled event information within a specified date and time range; calculating common available time slots for each participant within the specified date and time range, calculating suitability scores based on time slot scoring rules, and selecting time slots with the highest scores as suggested options; and receiving selection signals for the suggested options from participants and sending a resource reservation request to a conference room management system.

The present application relates to the technical field of data mining, and especially relates to a traffic safety public opinion analysis method based on an SQ-LDA topic model. The present application comprises the following steps: S1, obtaining traffic safety social software public opinion data; S2, preprocessing the traffic safety social software public opinion data; S3, extracting feature topics by using the SQ-LDA topic model; and S4, visualizing traffic safety social software public opinion hotspots. The sample quality negative sampling method in the SQ-LDA topic model of the present application calculates sample information quantity according to a gradient, so as to distinguish high and low quality negative samples, filter out low quality negative samples, maximize positive sample probability, minimize high quality negative sample probability, and further effectively mine and analyze traffic safety social software public opinion data. The present application sets a keyword frequency probability threshold value under a topic, and when the frequency probability of a keyword exceeds the set frequency probability threshold value, the keyword public opinion early warning under the topic will be triggered, thereby providing necessary technical support for social public opinion early warning.

According to the computer device disclosed by the invention, contact person information can be automatically copied after the display screen is touched due to an accident and the data interface is damaged, and the contact person information is transcribed into the second computer through voice or social software, so that the problem that a user needs to repair the touch display screen of the computer device firstly and then transcribe the contact person information is avoided.

The invention provides an intelligent assistant system for assisting social software dialogues and a method thereof. According to the system, a text message of a community software platform is received through a dialogue recording module, the content of the message is divided into a plurality of semantic units by a content processing module by applying a natural language processing technology, and the semantic units are converted into a newly added knowledge graph. The system is provided with a knowledge graph database for storing a preloaded knowledge graph and a newly added knowledge graph, a knowledge retrieval module queries the preloaded knowledge graph according to a semantic unit to obtain a related knowledge graph, and a reference data module generates a reference data message with relevance according to the related knowledge graph. According to the method and the device, the user can be assisted to obtain related reference information in the community conversation, and the reference information can comprise at least one of related information prompt, suggested reply content or historical related information, so that the communication efficiency is improved.

This invention relates to a time-weighted difference-aware response generation method and system based on auto-step learning. The method includes the following steps: Step A: Collect natural, open-domain dialogues from social media software, and use a retrieval system to search for relevant background knowledge of the dialogue in an encyclopedia, and label real responses and real knowledge to construct a training dataset. DE Step B: Using the training dataset DE Step C involves training a time-weighted difference-aware deep learning network model M based on a self-synchronizing learning strategy. This model selects necessary background knowledge and generates responses based on the selected background knowledge. Step C involves inputting the dialogue context and background knowledge base into the trained deep learning network model M to generate corresponding responses. This method and system help improve the accuracy of generated responses.

This invention relates to the technical field of teaching scheduling management, and discloses a method and system for visualized intelligent scheduling of student learning courses based on big data. The system includes a student preset timetable management module, a student customized timetable management module, and a student timetable comprehensive creation module. It dynamically creates personalized blank timetables for student groups based on table text processing, enabling students to rationally and scientifically arrange their course order according to their personal learning plans. Based on the blank timetable text information and contact information of target students, and combined with a course management platform and social software, it autonomously and efficiently performs the task of creating and collecting timetable text information for the target student group at specific times. Simultaneously, it combines data analysis to comprehensively analyze the existence of timetable customization results for the student group, achieving reliable timetable creation based on both preset and customized timetables, thus improving the scientific nature and personalization of scheduling management.

The invention relates to the technical field of teaching course arrangement management, and discloses a visual intelligent course arrangement method and system for student learning courses based on big data, and the system comprises a student preset course schedule management module, a student customized course schedule management module, and a student course schedule comprehensive making module. A personalized blank course schedule oriented to student group objects is dynamically established based on table text processing, so that course arrangement students can reasonably and scientifically arrange a personal course sequence based on a personal learning plan; based on target course arrangement student blank course schedule text information and target course arrangement student contact information, in combination with a course management platform and social software, autonomously and efficiently executing course schedule text information formulation and collection homework of a target student group at a specific time point; and meanwhile, whether the class schedule customization result of the student group exists or not is integrally analyzed in combination with data analysis, so that the class schedule is comprehensively and reliably formulated based on the preset class schedule and the customized class schedule, and the scientificity and individuation of class arrangement management are improved.

The invention provides a content recommendation method, device and equipment, a computer program product and a computer readable storage medium. The embodiment of the invention can be applied to content recommendation scenes of social software, video software, shopping software and the like. The method comprises the following steps: respectively carrying out feature extraction on at least two pieces of description information of to-be-recommended content in at least two modes to obtain content description features in each mode; performing common feature mapping on the content description features in each mode to obtain common description features in each mode; carrying out feature mapping on the content description features in each mode to obtain feature description features in each mode; and when a content recommendation request is received, determining target recommendation content of the content recommendation request from the to-be-recommended content based on the common description feature and the characteristic description feature of the to-be-recommended content in each mode and the object feature corresponding to the content recommendation request. According to the invention, the accuracy of content recommendation can be improved.