9 results about "Business goals" patented technology

The present application relates to a kind of intelligent interview evaluation and feedback system based on multi-modal data fusion, specifically relates to data processing field, by meta-learning mechanism dynamic perception interview scene and generate initial fusion weight, subsequently utilize the complex interaction relationship between modalities modeled by graph neural network to carry out fine-grained correction to weight, so as to significantly improve the accuracy and scene adaptability of multi-modal evaluation, further introduce reinforcement learning, link evaluation decision and long-term performance of talents, continuously optimize weight generation strategy, ensure that evaluation standard and business goal are aligned, finally, through closed-loop iteration mechanism, make the whole scheme can be updated automatically according to new data and performance feedback, continuous evolution, with strong self-optimizing ability and long-term robustness, realize the fundamental change from static rule to dynamic intelligent decision.

The invention discloses an e-commerce advertisement putting strategy generation method and system based on quantum computing optimization, and particularly relates to the technical field of quantum computing, comprising parameter coding, quantum optimization, line evolution, strategy resolving, dynamic optimization and strategy verification and output. According to the method, a high-dimensional parallel search mechanism based on a parameterized quantum circuit is constructed by introducing a quantum calculation normal form, the problem of calculation complexity index increase of a classical computer in e-commerce advertisement multi-parameter combination optimization is effectively solved, and the multi-parameter combination optimization of e-commerce advertisements is realized by designing a classical and quantum mixed architecture and a dynamic feedback optimization mechanism. The real-time adaptive adjustment of the advertisement putting strategy is realized, the practicability and robustness of the system are remarkably improved, the precise alignment of the technical means and the commercial target is realized by deeply coupling the quantum optimization process with the specific e-commerce advertisement business index, and a quantifiable business improvement effect is provided.

This invention provides an artificial intelligence-based software refactoring method. The method includes: acquiring the current code data and user data of the software to be refactored; determining a target refactoring strategy based on the current code data and user data; generating refactoring code data corresponding to the target refactoring strategy based on a large language model; and refactoring the software based on the refactoring code data to obtain the target software. This invention analyzes code data and user data, considering both the code problems of the software to be refactored and user business expectations, to generate a target refactoring strategy that balances technical optimization and business needs. This avoids the problem of the separation between technical optimization and business goals in traditional methods, ensuring that the refactored code accurately matches the user's actual business scenario while optimizing technical indicators, reducing the cost of secondary modifications due to misunderstandings of requirements, and thus improving the accuracy and efficiency of software refactoring.

An implementation method, device and equipment for path searching along an original path as much as possible and a storage medium. In the application, the business goal of "searching along the original path as much as possible" is converted into a quantifiable priority index in the path searching algorithm. By judging the "deviation" degree of the candidate route from the original route in real time during the path searching process, and giving a lower priority to the route that deviates earlier, the search process is systematically guided to preferentially explore the route branch similar to the original path, and the optimal solution is efficiently found.

This invention relates to a dialogue goal optimization device, method, and program for optimizing goal achievement in user interactions. Based on user utterances and actions, it estimates user states, including emotions, resistance, comprehension, and signs of detachment, as well as goal progress indicating the degree of achievement of primary and sub-goals, and maps these to a state space. After restricting the set of candidate response strategies based on constraints such as compliance and cost applied to the dialogue, it selects a response strategy that maximizes the objective function. Furthermore, it performs a self-correction process that dynamically updates the parameters of the response strategy in response to signs of failure detected during the dialogue. This makes it possible to suppress user detachment while adhering to practical constraints and continuously improve the business goal achievement rate.

The invention provides a dialogue generation method and device driven by a large language model, equipment and a medium, and the method comprises the steps: receiving natural language input of a user; based on the natural language input and the context information, performing semantic analysis through a large language model to obtain intention and slot position information; managing and updating a current dialogue state based on the intention and the slot position information, the dialogue state being migrated according to a predefined state conversion logic; checking the filling condition of a necessary slot position corresponding to the current dialogue state; deciding the next action of the system based on the filling condition and the updated current dialogue state; and based on the next action, calling the large language model to generate a user-oriented natural language reply. By adopting the method, the controllability of the dialogue process, the natural fluency of interaction, the business goal achievement efficiency and the user interaction experience can be improved.

The present disclosure relates generally to an integrated machine learning platform. The machine learning platform can convert machine learning models with different schemas into machine learning models that share a common schema, organize the machine learning models into model groups based on certain criteria, and perform pre-deployment evaluation of the machine learning models. The machine learning models in a model group can be evaluated or used individually or as a group. The machine learning platform can be used to deploy a model group and a selector in a production environment, and the selector may learn to dynamically select the model(s) from the model group in the production environment in different contexts or for different input data, based on a score determined using certain scoring metrics, such as certain business goals.

The invention discloses a fund comprehensive scoring method based on adaptive learning. The fund comprehensive scoring method comprises the steps of data preparation and preprocessing; carrying out model training and initialization processing; carrying out distribution drift detection; a model training and updating mechanism; performing fund score prediction; and carrying out interpretability analysis. According to the method, a multi-dimensional feature system covering styles, earnings and risks is constructed, and comprehensive information input is provided for the model. XGBRanker is selected as a base model, Pairwise is used as a target function, and the relative sequence relation between samples can be learned. The method is highly consistent with a business target of screening out funds with good performance, and can better learn relative advantages and disadvantages between funds compared with a regression or linear scoring model. The fund is divided into ten groups for back testing according to the model score, and the annual yield of the high group is about 41% higher than that of the low group, which shows that the model has effective distinguishing ability.

This invention provides a method and system for training large-scale models in vertical domains, belonging to the field of artificial intelligence technology. Based on a general-purpose large language model, the method sequentially constructs an instruction fine-tuning dataset through data engineering, introduces domain-supervised samples for joint optimization after multi-task pre-training to obtain a base model, employs a two-stage hybrid fine-tuning strategy to activate and consolidate domain knowledge, and finally performs dual-dimensional alignment training of business goal alignment and common sense alignment. The common sense alignment constructs training sample sets and selects appropriate optimization algorithms for four anomaly patterns in the model response: illusion, factual error, security and privacy, and timeliness issues. This invention significantly reduces the training cost of large-scale models in vertical domains, enhances the model's deep understanding of specific domain knowledge and instruction compliance capabilities, and improves the stability and security of performance in engineering applications.