24 results about "Problem determination" patented technology

The invention discloses a question and answer method and system combining a large language model and a knowledge graph, and relates to the field of question and answer, and the method comprises the steps: determining corresponding meta-knowledge based on a meta-knowledge base according to a retrieval question, and the meta-knowledge comprises knowledge description, query actions and question entities; the meta-knowledge base comprises a knowledge graph; the meta-knowledge and short-term memory are combined to obtain cue word information, then a large language model is adopted to execute a query action and complete current reasoning, and an obtained response result is evaluated to obtain a reward score; if the reward score does not meet the preset condition, generating reflection correction information according to the response result, respectively storing the reflection correction information and the cue word information into a long-term memory and a short-term memory to realize data updating, updating the meta-knowledge base based on the updated long-term memory, and then executing the next round of reasoning; and if the reward score meets a preset condition, marking the response result as a question and answer result. The knowledge graph-based question and answer accuracy can be improved.

The invention provides an intelligent question and answer processing method and device, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the steps of obtaining a target question text in response to a received question and answer request, and performing intention analysis on the target question text to obtain an intention analysis result; when it is determined that the target problem text meets a problem dismantling condition based on the intention analysis result, dismantling the target problem text based on the intention analysis result and the target problem text to obtain a plurality of sub-problems; for each sub-problem, determining a first execution plan corresponding to the sub-intention corresponding to the sub-problem, and determining a first execution result corresponding to the sub-problem based on the first execution plan; and based on the first execution result corresponding to each sub-question, performing finite state transition, and determining a reply text corresponding to the target question text. According to the invention, the accuracy and controllability of intelligent question and answer processing can be improved.

The invention discloses a question recommendation method and device, a storage medium and electronic equipment, and the method comprises the steps: determining a plurality of historical questions proposed by a user in a current session, and employing a pre-trained question prediction model according to each historical question, and determining a prediction question outputted by the question prediction model. Determining a first question matched with the predicted question from a plurality of first questions included in a pre-constructed question and answer database, and taking the first question as a to-be-selected question; and according to the to-be-selected questions, determining a target question, and recommending the target question to the user. The historical problem in the current session is captured, the prediction problem conforming to the current session context is determined based on the historical problem by adopting the large language model, the to-be-selected problem matched with the prediction problem is determined, and the target problem recommended to the user is obtained based on the to-be-selected problem, so that the accuracy of the target problem is improved, and the user experience is improved. And the target question recommended to the user better meets the user demand, so that the user experience is improved.

The invention discloses a question and answer task processing method and device, equipment, a storage medium and a program product, and relates to the technical field of intelligent question and answer, and the question and answer task processing method comprises the following steps: receiving a to-be-processed task question input by a user in a session; determining a task scene type according to the to-be-processed task problem, and extracting task parameters of the to-be-processed task problem; and according to the task parameters, processing the to-be-processed task problem through a target agent corresponding to the task scene type to obtain a processing reply result. According to the method, multi-agent-based question and answer task processing is realized, the problem that an existing question and answer task processing method is low in processing efficiency in a complex task scene is solved, and the efficiency and accuracy of question and answer task processing are improved.

The embodiment of the invention discloses a business question and answer processing method, system and device and a storage medium. According to the technical scheme provided by the embodiment of the invention, the target problem vector value of the target service problem is determined by receiving the target service problem, the pre-constructed question and answer database and the function knowledge base are searched based on the target problem vector value, and the question and answer database configures reply data corresponding to different problem vectors in advance; the function knowledge base configures business functions corresponding to different problem vectors in advance; determining first reply data matched with the target question vector value from a question and answer database, and / or determining target function information matched with the target question vector value from a function knowledge base, executing a specified service based on the target function information, and determining second reply data; and replying the service problem based on the first reply data and / or the second reply data. By adopting the technical means, the service processing function of the intelligent dialogue assistant can be expanded, the service processing effect is improved, and the service question and answer experience of the user is improved.

The invention discloses a problem processing method and device based on a large model, equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the steps of generating a first decision scheme according to problem log data of a to-be-processed problem and current account data associated with the to-be-processed problem based on a pre-trained large model; according to the problem log data, matching the to-be-processed problem with each standard problem in a knowledge base to obtain a successfully matched target problem, and determining a second decision scheme according to the target problem; and generating a screening prompt text according to the first decision scheme and the second decision scheme, and inputting the screening prompt text into the large model to obtain an output target decision scheme. According to the technical scheme, intelligent decision making of the to-be-processed problem is achieved, and the accuracy and efficiency of abnormal positioning of the to-be-processed problem are improved.

The present disclosure provides a question determination method, device and equipment and storage medium, relates to the field of artificial intelligence, in particular to natural language processing and deep learning technology, and can be specifically used in the scene of inference engine, question and answer platform, reading comprehension, intelligent search and the like. The question determination method comprises: extracting a key element in a question, the category of the key element being at least one; based on the key element, obtaining a final determination rule matched with the question, the final determination rule comprising a to-be-processed element, the category of the to-be-processed element being consistent with the category of the key element; and based on the key element and the to-be-processed element, obtaining a determination answer of the question. The present disclosure can improve the question determination effect.

The invention provides a recommendation question determination method and device based on financial question and answer features, which can be used in the artificial intelligence field, the financial field or other fields, and the method comprises the following steps: carrying out word segmentation processing on stock questions by using a word segmentation system, determining a plurality of candidate words and word frequencies of the candidate words, and determining feature values corresponding to the candidate words; sorting the feature values, determining vector space dimensions, performing similarity calculation on each vector, and determining a similar problem set; performing entity recognition on financial preset knowledge points to obtain a domain knowledge graph, determining similarity between the knowledge points, and determining an effective question set according to a similarity calculation result between the knowledge points; and according to the questions input by the user, screening the similar question set and the effective question set to obtain a recommended effective question set. The problem of how to quickly recommend effective questions to the user in the prior art is solved, the provided questions and answers better conform to the expectation of the user, the recommendation efficiency and accuracy are improved, human resources are saved, and the user experience is improved.

The invention belongs to the technical field of data analysis, and provides a dynamic data acquisition and intelligent screening analysis method and system based on multi-dimensional feature fusion. The method comprises the steps of multi-dimensional working data collection, abnormal problem judgment, abnormal process matching, potential problem equipment determination, secondary data collection, abnormal multi-dimensional data screening and abnormal data analysis model analysis. According to the invention, the abnormal production identification sensitivity is improved through the abnormal judgment model; through the default frequency and the fault analysis frequency, the data volume during the abnormal traceability period is optimized, and the abnormal data analysis reliability is improved; through abnormal multi-dimensional data screening, the data structure is optimized, the proportion weight of abnormal potential data is improved, and the model calculation amount is reduced; and through the abnormal data analysis model, the early-stage manual labeling process is avoided, and the universality and flexibility of the model are improved.

The application provides a process automation and exception self-recovery system and method, wherein the system comprises: a rule engine configuration subsystem configured to configure a rule engine of a process platform; an exception problem determination subsystem configured to determine an exception problem in process approval according to characteristic information of historical process handling exception problems, and obtain an exception problem determination result; and an exception self-recovery subsystem configured to automatically handle the exception problem according to the exception problem determination result and an automatic handling rule configured in the rule engine. The process automation and exception self-recovery system and method of the application configure the rule engine, automatically identify and handle exception conditions in a process execution process, introduce a deep learning algorithm, combine characteristic information of historical process handling exception problems, fully consider possible problems in process approval, automatically calculate and determine exceptions in process approval by using the combination of the deep learning algorithm and the rule engine, and make process exception detection more comprehensive and intelligent.

To provide an information processing device, an information processing method, and an information processing program that can provide appropriate answers to questions. [Solution] The information processing device according to the present invention comprises a reception unit that receives questions from a user, a determination unit that determines which answer generation agent matches the question from among a plurality of answer generation agents, each of which has learned to provide answers based on different answer policies and is linked in a hierarchical structure for each predetermined event, and a generation unit that generates an answer to the question using the determined answer generation agent.

The invention relates to the technical field of communication, in particular to an IMS call problem determination method and device, equipment and a computer readable storage medium. Under the condition that a calling terminal calls a called terminal, the method is executed by the called terminal, and the method comprises the following steps: determining whether the called terminal is in an idle state or not; under the condition that the called terminal is in the idle state, executing a problem checking operation; wherein the problem checking operation comprises the step of judging whether the called terminal successfully demodulates a paging wireless network identifier in a calling process; under the condition of successful demodulation, judging whether paging sent by a network side is matched with the called terminal or not; and if the call establishment fails and a preset condition is satisfied, a network side fault is prompted, and the preset condition comprises that all paging wireless network identifiers of the called terminal in a preset time period are successfully demodulated and the paging pagging at each time is not matched with the called terminal.

The invention provides a process automation and abnormity self-healing system and method, and the system comprises a rule engine configuration subsystem which is used for configuring a rule engine of a process platform; the abnormal problem judgment subsystem is used for carrying out abnormal problem judgment in process approval according to the characteristic information of the historical process processing abnormal problems, and obtaining an abnormal problem judgment result; and the exception self-healing subsystem is used for automatically processing the exception problem according to the exception problem judgment result and the automatic processing rule configured in the rule engine. According to the process automation and exception self-healing system and method, the rule engine is configured, and exceptions in the process of process execution are automatically recognized and processed; a deep learning algorithm is introduced, and problems possibly occurring in process approval are fully considered in combination with feature information of historical process processing exception problems; the deep learning algorithm and the rule engine are combined to automatically calculate and judge the abnormality in the process approval, and the process abnormality detection is more comprehensive and intelligent.

The invention relates to a computer-implemented method for solving a problem, the problem being a decision problem or optimization problem, in which method at least one subproblem of the problem is identified. An occupancy is determined for at least one variable of the problem by solving the at least one subproblem using a quantum computer. A solution to the problem is generated using the determined occupancy of the at least one variable of the problem.

The invention provides a question and answer pair correlation evaluation method, electronic equipment and a storage medium, the method comprises the following steps: obtaining a to-be-evaluated question and answer pair, the to-be-evaluated question and answer pair comprising a to-be-evaluated question and a to-be-evaluated answer corresponding to the to-be-evaluated question, the to-be-evaluated answer is generated according to the answer of the question answering system to the to-be-evaluated question; based on the to-be-evaluated answers, a plurality of variant questions are generated, and the variant questions are questions corresponding to the to-be-evaluated answers and different from the to-be-evaluated questions; and determining the correlation of the question-answer pair to be evaluated based on each variant question and the question to be evaluated. The questions and answers can be accurately and efficiently evaluated, so that a foundation is laid for providing a questions and answers system with good questions and answers use experience for a user.

To provide a learning assistance system that makes it possible to temporarily stop presentation of a problem that lacks necessary to learn.SOLUTION: A learning assistance system 10 comprises: a problem storage unit 12 in which a plurality of problems for a learner 4 to acquire knowledge and answers respective corresponding to the plurality of problems are registered; a presented problem determination unit 14 which determines a presentation interval so as to heighten learning effects of the learner 4 when determining the date of presentation of each of the plurality of problems; a presentation dormancy setting unit 19 which sets dormancy for pausing presentation of a problem the necessity of which for the learner 4 to learn is low, and a presentation unit 18 which presents each problem to the learner 4 on the basis of the presentation interval determined by the presentation interval determination unit 14 while pausing presentation of a problem of low necessity to learn that is set to be paused by the presentation dormancy setting unit 19.SELECTED DRAWING: Figure 1

The invention discloses a guidance problem determination method and a related device, which are applied to scenes such as artificial intelligence. The method comprises the steps that M following questions are generated according to previous answers of a preset language model, and M is a positive integer and is larger than or equal to 2; for each of the following questions, encoding the following questions into a first encoding feature; a second coding feature of each target question in N target questions of a preset language model is obtained, N is a positive integer, and N is larger than or equal to 2; the target question is generated by preset input content of a preset language model, and the target question is matched with a question logic strategy of the preset language model; according to the similarity between the M first coding features and the N second coding features, a plurality of guide questions matched with a preset language model and a question logic strategy are determined from the M following questions and the N target questions, and each guide question is a question skilled in answering by the preset language model and is a question conforming to the question logic of the preset language model; and the accuracy, selectivity and reference of the guiding problem are improved.

The invention discloses an answer generation method and a related device, and relates to the technical field of data processing, and the method comprises the steps: obtaining a question input by a user; determining a question proposing intention of the user based on a question input by the user to obtain a target intention; a question-answer pair retrieval method is adopted, candidate questions consistent with the target intention are searched from a knowledge base, the candidate question with the maximum matching degree with the question input by the user is determined, a target question is obtained, and an answer to the target question is obtained; a knowledge graph retrieval method is adopted to search candidate answers consistent with the target intention, the candidate answer with the maximum matching degree with the question input by the user is determined, and a target answer is obtained; inputting the question input by the user into a large language model to obtain a large language model answer; and obtaining the answer of the question input by the user based on the answer of the target question, the target answer and the big language model answer. The answer generation accuracy can be improved.

The invention discloses a cross-domain problem processing method and device based on a large language model, equipment and a medium. The method comprises the steps that a target problem of a target domain is received; performing similarity matching on the target problem and a source problem of at least one source field in an example pool, wherein the example pool stores source problems classified according to industries or technical fields, corresponding thinking chains and source data source fields on which thinking chain reasoning depends; based on the matching result, obtaining or generating a thinking chain associated with the target question; identifying a source data source field on which the obtained or generated thinking chain associated with the target question depends, and determining a corresponding target data source field for the target question based on the semantic similarity; constructing an enhancement instruction based on the obtained or generated thinking chain, the source data source field and the target data source field; and inputting the enhancement instruction into the large language model to generate an answer to the target question. According to the method, the big language model can generate answers which are logically coherent and reliable in data support.

This invention discloses a multi-agent collaborative reasoning system and method. The system includes: a dynamic policy coordination module for analyzing the original problem input by the user and determining initial policy parameters; a multi-round reasoning module for sending the original problem and initial policy parameters to a pool of agents, obtaining reasoning data from each agent, performing multiple rounds of interaction until round control conditions are met, and determining collaborative reasoning data based on the latest reasoning data; obtaining updated reasoning data from each agent during each round of interaction; a parameter optimization module for calculating trajectory scores on the reasoning data from the previous round for each agent, determining the current interaction mode and current interaction parameters, and updating the trajectory score weights; and a communication optimization module for processing the reasoning data from each agent and sending it to other agents. This invention enables multi-agent collaboration that organically integrates efficient interaction, deep reasoning evaluation, and optimal result selection.

The invention discloses a training method of a multi-round question and answer model, a multi-round question and answer method and a related device. The multi-round question and answer model training method comprises the following steps: respectively taking at least one round of question in multi-round question and answer training data as a current round of question, and determining an attribute relationship between the current round of question and a historical round of question; a prompt instruction with the prompt type matched with the attribute relation is obtained and serves as a current prompt instruction corresponding to the current round of questions, and the prompt instruction is used for instructing the large model to conduct answer prediction; performing answer prediction on the current round of questions based on the current prompt instruction by using the large model to obtain predicted answers corresponding to the current round of questions; and based on the predicted answer and the reference answer corresponding to the at least one round of question, adjusting parameters of the large model to obtain a multi-round question and answer model. According to the scheme, the multi-round question and answer model obtained through training can adapt to user questions with diversified attributes in the multi-round question and answer process, and the accuracy of answer prediction is improved.

The application provides a project problem determination method and device, electronic equipment and storage medium. The method comprises the following steps: designing a test case based on the requirement of a target project, and determining the total number of problems of the target project; determining the problem omission rate of the target project up to the current release number of the target project based on the total number of problems; determining the problem omission number of the target project based on the problem omission rate of the target project and the total number of discovered problems of the target project; detecting whether the problem omission number of the target project meets a preset problem omission number threshold value; if yes, allowing the target project in the current release number to be used; and if no, continuously determining the problem omission number of the target project in the next release. The problem omission number of the project is dynamically predicted according to the effectiveness of the project problem solution. The predicted problem omission number can be used to evaluate the project quality, thereby improving the maturity of the project.