50 results about "Recommendation - action" patented technology

A computing system for video content creation executes a chat application to cause the processor to, in a chat conversation with a user in real-time, receive communication including a command from the user for interacting with a video content, use the large language model to analyze the command and generate a natural language response and a recommended action to implement on the video content based at least on the analyzed command, and implement the recommended action on the video content based at least on the analyzed command.

Apparatuses, systems and methods are disclosed for providing property improvement recommendations. The method comprises: (1) receiving, by one or more processors from a user, a first prompt associated with a property; (2) generating, by the one or more processors, a second prompt based upon the first prompt, data associated with the property and one or more property metrics associated with the property; (3) transmitting, by the one or more processors to a chatbot, the second prompt to generate a response, the response comprising a recommended action associated with the property; and / or (4) presenting, by the one or more processors, the response to the user.

The invention provides an intelligent collaborative recommendation method and device oriented to multi-modal immersive content, and relates to the technical field of immersive interaction.The method comprises the steps that multi-modal data are collected, and the attention weight of interaction between the multi-modal data and other modalities is calculated for each modality; and obtaining a corresponding fusion feature through the calculated attention weight and the representation weight after self-modal internal attention processing, and determining a recommended action by using a predefined multi-agent according to the obtained fusion feature. According to the method and the device, the problem that the recommended immersive content cannot meet the actual demand of the user due to the fact that multiple modal data for understanding the user state in the virtual environment and the interaction among the modal data are not comprehensively considered in the prior art is solved.

Techniques for action recommendation based on conversational log for real time assistance are described. Pre-generated intent clusters can be used to identify a relevant intent of a user in a given conversation between the user and a contact center agent. Based on the identified intent, certain recommended actions can be performed on the computing device of the contact center agent to facilitate the conversation between the user and the contact center agent. Feedback relating to the conversation and / or the recommended actions can be recorded and used to update the pre-generated intent clusters to improve the quality and relevance of the actions recommended for future conversations.

Techniques for access governance are disclosed, including: computing, based on attributes associated with users having one or more access permissions in common, an aggregate similarity score of the users; computing, based at least on the attributes, an individual similarity score between the users and a target user, where the target user has the one or more access permissions or the target user requests to have the one or more access permissions; determining, based at least on the individual similarity score and the aggregate similarity score, a recommended action with respect to the one or more access permissions for the target user, where the recommended action includes one of (a) administrative review or (b) administrative approval of the one or more access permissions for the target user; and generating a notification of the recommended action with respect to the one or more access permissions for the target user.

A system may include a plurality of processing nodes in communication with a storage device configured to store a plurality of data. The processing nodes may receive a query on at least a portion of the data and may generate a query plan in natural language format. The processing nodes may generate a large language model (“LLM”) input based on the natural language format of the query plan and may execute an LLM on the LLM input. The processing nodes may generate, in response to execution of the LLM, a plurality of recommended actions to perform to improve the query plan. The processing nodes may receive input to execute at least one of the plurality of recommended actions and may alter the query plan in accordance with the at least one of the plurality of recommended actions. A method and computer-readable medium are also disclosed.

The invention relates to the technical field of car rental recommendation, in particular to a car rental recommendation method and system based on artificial intelligence, and aims to overcome the limitation of traditional rule recommendation on context understanding by fusing user historical car use records and current input requirements, constructing a multi-dimensional state vector and accurately representing user behavior habits and travel scenes. A reinforcement learning model is adopted to model a car renting behavior strategy based on a Markov decision process, a reward value is calculated in combination with real feedback such as clicking, renting conversion and scoring, a recommendation strategy is dynamically optimized through a strategy gradient algorithm, output recommendation actions cover vehicle type categories, price ranges and place screening, personalized matching of cars is achieved, and the car renting efficiency is improved. Recommendation generalization is avoided, and recommendation accuracy and user satisfaction are improved. The model has continuous learning ability, adapts to changes of different car renting scenes, and improves the intelligent level and practical value of the recommendation system.

Methods and systems provide for intelligent content recommendation within a communication session. In one embodiment, the system receives a list of content recommendation actions, each content recommendation action being associated with one or more trigger phrases constituting conditions for the content recommendation action to be performed, each trigger phrase being associated with a party the trigger phrase is to be uttered by. The system connects to a communication session with a plurality of participants, and receives a number of utterances associated with the participants in real time. For each utterance, the system determines whether a prediction of relatedness is present between the utterance and one or more trigger phrases associated with a content recommendation action. Upon determining that a prediction of relatedness is present, the system performs the associated content recommendation action by transmitting, to one or more client devices, one or more pieces of content to be recommended.

The invention provides an intelligent digital person recommendation method based on multi-modal emotion calculation and cross-domain behavior analysis, and relates to the technical field of digital person personalized recommendation, and the method comprises the steps: collecting cross-domain behavior data streams of a target user in real time, including behavior events from different application fields and timestamps of the behavior events; performing multi-modal analysis on the behavior event, extracting a corresponding emotion feature, and generating a corresponding emotion vector; on the basis of the timestamps of the behavior events and in combination with the corresponding emotion vectors, behavior vectors of the target user are generated, and the behavior vectors represent key interests and demand states of the target user in the current time window; and according to the behavior vector of the target user, carrying out matching to obtain a corresponding recommendation action, so that the digital person executes personalized recommendation. According to the method, through cross-domain data fusion and emotion calculation, the recommendation accuracy, timeliness and emotion adaptability are remarkably improved, and the core defects that in the prior art, data are one-sided and emotion is neglected are overcome.

A method for testing advertising, said method comprising the steps of: recruiting prospective survey respondents within a single online platform and collecting inputs from the respondents representing a prospective advertising audience regarding their advertising creative variant preferences and desirability as customers, combining the individual inputs from the survey respondents to compute at least one score for each pairing of audience and creative; and recommending actions based on the computed score, wherein the recommended actions include at least one of activating pairings with high preference scores and density of desirable customers; suppressing pairings with low preference scores or low density of desirable customers; or conducting another test after changing at least one of the audience or advertising creative variants, wherein the recommended actions are within the single on-line platform.

The invention provides an enterprise marketing intelligent recommendation method and system based on deep learning, and the method comprises the steps: constructing an interest heat map according to the historical behavior data of a user, and predicting the future interest trend of the user; obtaining a state space in combination with the interest heat map, the interest trend tag and an external environment signal; generating a candidate recommended action set for each user according to the state space; inputting the state space into a pre-trained strategy network based on reinforcement learning to evaluate the strategy value of each candidate action in the candidate recommendation action set in the current state, and selecting a recommendation action with the optimal long-term return; and real execution of the recommendation behavior is completed for the recommendation action of the optimal long-term return, and after the response of the user occurs, the feedback behavior of the user is collected so as to carry out system optimization. The method has good adaptability and popularization value in complex marketing tasks with sparse user behaviors or obvious interest drifting.

Artificial Intelligence driven system for managing deployment actions based on sentiment analysis includes performing operations including obtaining an assigned feature name for an application feature of a target application, selecting, using respective vector encodings of an application feature name that include the assigned feature name, and filtering a collection of feedback using a set of application feature names of an application feature to obtain a filtered set of feedback. The operations further include generating a sentiment request prompt requesting a sentiment score and comprising the filtered set of feedback and the set of application feature names, and processing, by a large language model (LLM), the filtered set of feedback with the set of application feature names to generate the sentiment score for the application feature. The operations further include selecting a recommended action based on the sentiment score and updating the target application according to the recommended action.

To provide an action promotion system capable of prompting a worker to take a recommendation action.SOLUTION: An action promotion system 10 comprises: a setting acceptance unit 44 which accepts the setting of a recommendation action recommended for a worker; a notification unit 45 which notifies the worker of the set recommendation action; a determination unit 46 which acquires at least one of information on the worker location and facility and equipment information on the facility or equipment used by the worker and determines whether the worker has taken the recommendation action on the basis of at least one acquired information; and a management unit 47 which gives a point to the worker when the determination unit determines that the worker has taken the recommendation action.SELECTED DRAWING: Figure 1

The present invention provides a temporal recommendation method and system based on deep reinforcement learning. The method includes: generating a user state st at time t according to the item set It of the user at time t and user information; taking the user state st as the input information of the trained Actor model to obtain a recommendation action at under the user state st; recommending the recommendation action at to the user and obtaining corresponding user feedback information rt; obtaining the user state st+1 and item set It+1 at time t+1 according to the user feedback information rt, and storing the corresponding recommendation action set (st, at, rt, st+1) at time t into the experience pool M to update the experience pool M; taking the user state st and the recommendation action at as the input information of the trained Critic model to obtain the Q function value under the user state st, and calculating the loss function value according to the Q function value and the user feedback information rt; updating the network parameters of the Actor model and the network parameters of the Critic model with the latest experience pool M as the training data according to the Q function value and the loss function value.

Techniques for recommending actions for resolution of errors associated with medical coding records are described. In an example, a plurality of edits corresponding to a medical coding record is identified, where the plurality of edits is indicative of resolutions to at least one error associated with the medical coding record. The plurality of edits is then analysed using a code editing model to rank the plurality of edits, where the code editing model is trained based on the statistical information indicative of relevance of the plurality of edits for resolution of errors associated with the medical coding record. The ranked plurality of edits is then provided along with a set of recommendation actions for resolution of the error associated with the medical coding record.

Automated content recommendation is used in conferencing. In one embodiment, a system receives a list of content recommendation actions. The system receives a number of utterances associated with the participants in real time. For each utterance, the system determines whether a prediction of relatedness is present between the utterance and one or more trigger phrases associated with a content recommendation action. Upon determining that a prediction of relatedness is present, the system performs the associated content recommendation action by transmitting, to one or more client devices, one or more pieces of content to be recommended.

Methods and systems for responding to an operational event are provided. Aspects include receiving a notification of the operational event, obtaining a first set of recommendation actions for responding to the operational event, and providing the first set of recommendation actions to a user responding to the operational event. Aspects also include capturing a first response action performed during responding to the operational event, obtaining, based at least in part on the first response action, a second set of recommendation actions for responding to the operational event, displaying the second set of recommendation actions based to the user responding to the operational event, capturing a second response action performed during responding to the operational event, and generating a final outcome report of the operational event including the first response action, the second response action, and an automatically captured timestamp of the first response action and the second response action.

The application discloses a kind of personalized explainable recommendation system based on deep reinforcement learning, it includes state modeling module by fusing user historical behavior sequence data, commodity feature data, environmental variable data, obtain comprehensive state vector;Reinforcement learning decision module is based on comprehensive state vector Markov decision framework is constructed, and the optimal recommended action and corresponding output probability are obtained by using proximal policy optimization algorithm to train reinforcement learning strategy network model;Explainability analysis module is by SHAP method to the output probability of optimal recommended action carries out feature contribution degree attribution analysis, obtains the feature contribution value corresponding to each feature, obtains the feature contribution weight corresponding to each feature after normalization processing.The application can provide quantifiable, traceable feature contribution explanation for each recommendation decision.

The invention discloses a recommendation system based on unstructured local business data, and the system comprises a multi-mode semantic coding module which is used for receiving text comments, picture tags and social statements and outputting a unified semantic vector; the spatial semantic fusion mechanism is used for embedding the geographic position, the business district label and the time period into the semantic vector based on the spatial position code; the semantic graph construction and graph neural network module is used for forming a heterogeneous semantic graph by taking stores, commodities, users, comment themes, picture tags, time periods and geographic grids as nodes and establishing edges through co-occurrence and causal dependence, and outputting node-level, sub-graph-level and graph-level embedding vectors; the causal reasoning and anti-fact analysis module is used for estimating a causal effect and generating a causal weight by taking the recommended action as an intervention variable and the operating index as a result variable; and the interpretable recommendation generator is used for outputting the tetrad based on the embedded vector and the causal weight. The invention aims to improve the business intelligent analysis and recommendation capability.

The invention discloses a multi-path element chain type thinking reasoning search method for generative agent recommendation, and belongs to the field of artificial intelligence and recommendation systems. The method comprises the following steps: acquiring a user demand text, a candidate object set and searchable evidence information, constructing a session state including an environment information state, a user preference belief state and an auditable language trajectory state, and constructing an action space of a reasoning action, a retrieval / tool action and a recommendation submission action; under budget constraints of token, end-to-end time delay, tool calling times, node expansion times and the like, fusing heuristic search and Monte Carlo tree search to generate a plurality of candidate recommendation paths; the candidate paths are scored according to a target function of comprehensive preference alignment revenue and resource cost / risk penalty, a target recommendation path is determined, a Top-K recommendation result is output, meanwhile, a corresponding evidence reference index and an interpretable reasoning path are output, and recommendation robust alignment, cost controllable and auditable output are achieved.

A computing system for video content creation executes a chat application to cause the processor to, in a chat conversation with a user in real-time, receive communication including a command from the user for interacting with a video content, use the large language model to analyze the command and generate a natural language response and a recommended action to implement on the video content based at least on the analyzed command, and implement the recommended action on the video content based at least on the analyzed command.

The application provides an enterprise marketing intelligent recommendation method and system based on deep learning, which comprises the following steps: constructing an interest heat map according to historical behavior data of a user, and predicting the future interest trend of the user; combining the interest heat map, the interest trend label and external environment signals to obtain a state space; generating a candidate recommendation action set for each user according to the state space; inputting the state space into a pre-trained reinforcement learning-based policy network to evaluate the policy value of each candidate action in the candidate recommendation action set under the current state, and selecting a recommendation action with the optimal long-term return; and completing the real execution of the recommendation action of the optimal long-term return, and collecting user feedback behavior after the user response occurs, so as to optimize the system. The application also has good adaptability and popularization value in complex marketing tasks with sparse user behavior or obvious interest drift.

A system and a method are disclosed for recommending a set of actions to be performed to improve a target performance metric of a client application. An action recommendation system receives the target performance metric from a user associated with the client application. The action recommendation system determines features of the client application describing characteristics and performance history of the client application. The features of the client application and the target performance metric is provided as input to a machine learning model that outputs sets of target features that are likely to result in improvement for the target performance metric. The action recommendation system ranks the sets of target features and selects one of the sets based on the ranking. The action recommendation system determines a set of recommended actions based on the selected set of target features and presents the set of recommended actions to the user.

The present invention provides an intelligent collaborative recommendation method and device for multi-modal immersive content, which relates to the field of immersive interaction technologies. The method includes: collecting multi-modal data and calculating the attention weights of the interaction between itself and other modalities for each modality, obtaining the corresponding fusion features by weighting the representation after internal attention processing of its own modality with the calculated attention weights, and determining the recommendation actions using pre-defined multi-agents according to the obtained fusion features. The present invention solves the problem that the prior art does not comprehensively consider multiple modal data for understanding the user state in a virtual environment and their interaction effects, resulting in the recommended immersive content not meeting the actual needs of users.

Techniques for generating actionable links to Artificial Intelligence (AI)-generated content are disclosed. A system generates a prompt to a generative AI model to generate content, including a recommended action based on a set of analyzed data. The prompt further includes instructions to identify a resource used to generate the recommended action. The generative AI model identifies resources used to generate the recommended action based on a set of resources included in the prompt or based on fine-tuning the generative AI model with a dataset that includes system tools available in a system. A system analyzes content output from the generative AI model to identify a recommended action. The system matches the functionality of a resource used to generate the recommendation with the recommended action. The system generates software code to link the AI-generated content to the resource with functionality to perform the recommended action.

Stress detection systems and methods, and non-transitory computer readable media, include building a library including previously identified stressful sentences and stressful phrases; receiving, by a trained neural network model, the library; receiving, by the trained neural network model, a text interaction between a customer and an agent; calculating, by the trained neural network model, a cosine similarity score between each stressful sentence or stressful phrase in the library and each sentence in the text interaction; determining, by the trained neural network model, a probability that the text interaction is stressful based on the calculated cosine similarity score; determining that a percentage of stressful interactions for the agent in a time interval is greater than a threshold percentage; providing a manager with recommended actions to decrease stress on the agent; receiving, from the manager, a selection of one or more recommended actions; and implementing the one or more recommended actions.

The embodiment of the invention provides a resource recommendation processing method and device.The resource recommendation processing method comprises the steps that in the process that an access user accesses a resource service, recommendation decision data is generated according to access data of the access user and user data, and inputting the recommendation decision data into a large language model to perform recommendation action decision to obtain a recommendation action, further calling an agent corresponding to the recommendation action in the multiple agents to perform resource recommendation processing to obtain resource recommendation data, and displaying the resource recommendation data to the access user. Therefore, resource recommendation is carried out on the access user in the resource access process of the access user through cooperation of the large language model and the multiple agents.

An automated system is provided for facilitating resolution of an incident on a digital processing system. The automated system has a data storage unit with information on previous incidents, a user interface and a resolution facilitation server. The server receives incident information from a monitoring system, including status information for at least one operating parameter of the digital processing system. The server is configured to apply a machine learning model to determine a first recommended action using the incident information and the previous incident information, present the first recommended action to the user, and receive a recommendation response. The server is also configured to establish a recommendation score based at least in part on the recommendation response and to update the machine learning model using the incident information, the first action recommendation, and / or the first recommendation score.

The invention discloses a recommendation method and electronic equipment, and the electronic equipment responds to the current interaction operation of a user, and determines the behavior characteristics of the user based on a knowledge graph; the behavior characteristics are used for representing behavior preferences of the user in the current interaction scene; generating a current recommendation result based on the decision model and the behavior characteristics; the decision model comprises an action value evaluation function which is used for evaluating the expected value of each recommended action under the behavior characteristics; and based on feedback operation information of the user on the current recommendation result, updating the decision-making model and the knowledge graph to obtain an updated decision-making model and an updated knowledge graph, and performing recommendation for the next interaction operation of the user based on the updated knowledge graph and the updated decision-making model.

The invention relates to a data processing method and device, computer equipment and a readable storage medium. The method comprises the following steps: acquiring business behavior data of a target object, and determining business behavior characteristics of the target object; selecting a corresponding pre-configuration rule set and a pre-configuration model according to an event type corresponding to the business behavior data; respectively inputting the business behavior characteristics into a pre-configuration rule set and a pre-configuration model to obtain a rule output result and a model output result; and generating a recommended action instruction according to the rule output result and the model output result, and executing the recommended action instruction. By adopting the method, the accuracy of the recommended action can be improved.