9 results about "Reference memory" patented technology

The invention provides a tool-based task processing method and device and electronic equipment, and relates to the technical field of artificial intelligence. The method comprises the following steps: determining a plurality of candidate tools by utilizing similarity between task description and function description of a preset tool; calculating the applicability score of the candidate tool in the current state of the intelligent agent by using the key parameters of the candidate tool and the memory data of the intelligent agent; calculating target scores of the candidate tools according to the applicability scores and the similarity of the candidate tools and historical tool data of the candidate tools; determining a to-be-called tool from the candidate tools according to the target scores of the candidate tools and the collaboration among the candidate tools; retrieving reference memory data from the memory data based on the task description; and calling the to-be-called tool in combination with the reference memory data to execute the to-be-processed task. According to the method, multiple factors can be comprehensively considered, the tool selection range is precisely narrowed, the tool selection accuracy is ensured, and then the task execution accuracy can be improved.

The invention provides a task execution method based on an intelligent agent, and relates to the technical field of artificial intelligence. The method comprises the steps that an execution plan is generated based on task description of a to-be-processed task, the execution plan comprises a plurality of sub-steps with an execution sequence, and each sub-step has a corresponding sub-step description; aiming at each target step, determining a tool to be called from a preset tool library by utilizing target step description corresponding to the target step, and retrieving reference memory data from the memory data; calling the to-be-called tool in combination with the reference memory data to obtain a tool calling result; and if the tool calling result is invalid, acquiring calling diagnosis data of the tool to be called, updating the execution plan into a new execution plan by utilizing an invalid type in the calling diagnosis data, and executing the task to be processed according to the new execution plan. When the tool calling result is invalid, the execution plan can be flexibly adjusted according to the specific invalid type, normal execution of the task is ensured, and then the success rate of task execution can be increased.

The invention discloses a few-sample industrial processing anomaly detection method based on a pre-training model CLIP, and aims to solve detection pain points of scarcity of abnormal samples, high labeling cost and insufficient generalization in an industrial scene. The method comprises the following steps: data preprocessing: collecting an industrial image, dividing the industrial image into a support set only containing normal samples and a query set containing normal and abnormal samples, and combining data enhancement and local module clustering decomposition; cross-modal feature adaptation is carried out, text semantic anchor points are constructed through combination prompt integration, a residual adapter is inserted to optimize vision-text feature alignment, and multi-scale features are aggregated by adopting a harmonic average method; few-sample reference learning is carried out, a normal mode reference memory bank is constructed based on a prototype network, and feature learning is reinforced in combination with feature registration and alternate learning; and abnormal judgment: realizing abnormal recognition through cosine similarity calculation and a dynamic threshold value, and outputting an image-level confidence coefficient and a pixel-level segmentation image.

This invention provides an information processing method, information processing system, information processing device, and program that enable the stable generation of responses from a large-scale language model by determining the information of the memory region to be referenced by the large-scale language model based on priority control rules, in cases where inconsistencies may occur in information between multiple memory regions. [Solution] An information processing method is provided for an information processing system that controls a large-scale language model having multiple memory areas, comprising: a contradiction detection step that detects whether or not there is a contradiction in the information stored in each of the multiple memory areas; a reference target determination step that, if the contradiction detection step detects a contradiction, determines a reference memory area from the multiple memory areas based on a priority control rule; and an interaction control step that controls the reference memory area determined by the reference target determination step as a reference target in the large-scale language model.

The invention provides a process control method and device, equipment and a storage medium, and the process control method in the application comprises the following steps: in response to a process control request, obtaining process memory data of a background running process and reference memory data of the background running process; determining memory deviation data of the background running process according to the process memory data and the reference memory data; if the memory deviation data is greater than a preset memory deviation threshold, determining memory evaluation data of the background running process based on the process memory data and historical memory data; and performing memory control processing on the background running process by utilizing the memory evaluation data to obtain a memory control result. According to the technical scheme, effective memory control can be intelligently carried out on the background running process with memory occupation abnormity or memory leakage, so that the memory pressure of the terminal is reduced, and the running fluency of the foreground application is improved.

The present application discloses a memory, a memory system, and a method for operating memory, which belongs to the memory techniques field. The method for operating memory comprises determining a storage state of a reference memory cell, determining a discharge duration of a sensing node corresponding to a target memory cell based on the storage state of the reference memory cell, and reading the target memory cell based on the discharge duration of the sensing node corresponding to the target memory cell to obtain read results. The target memory cell and the reference memory cell are located in the same string and are adjacent, and the programming order of the reference memory cell is after that of the target memory cell. The present application may reduce the influence on reading memory cells by interlayer interference and improve the accuracy of reading memory cells.

The application provides a tool-based task processing method and device and electronic equipment, and relates to the technical field of artificial intelligence. The method comprises the following steps: determining a plurality of candidate tools by using the similarity between a task description and a function description of a preset tool; calculating the applicability score of the candidate tools in the current state of an agent by using the key parameters of the candidate tools and the memory data of the agent; calculating the target score of the candidate tools by using the applicability score of the candidate tools, the similarity and the historical tool data of the candidate tools; determining a tool to be called from the candidate tools according to the target score of the candidate tools and the cooperativity between the candidate tools; retrieving reference memory data from the memory data based on the task description; and calling the tool to be called in combination with the reference memory data to execute a task to be processed. The application can comprehensively consider multiple factors, accurately narrow the selection range of the tool, ensure the accuracy of tool selection, and thus improve the accuracy of task execution.

This invention provides a task execution method based on an intelligent agent, relating to the field of artificial intelligence technology. The method includes: generating an execution plan based on a task description of the task to be processed; the execution plan includes multiple sub-steps with an execution order, and each sub-step has a corresponding sub-step description; for each target step, using the target step description corresponding to the target step, determining the tool to be invoked from a preset tool library and retrieving reference memory data from memory data; invoking the tool to be invoked based on the reference memory data, obtaining the tool invocation result; if the tool invocation result is invalid, obtaining the invocation diagnostic data of the tool to be invoked, using the invalidity type therein, updating the execution plan to a new execution plan, and executing the task to be processed according to the new execution plan. The tool invocation result is verified; if invalid, the execution plan can be flexibly adjusted according to the specific invalidity type to ensure the normal execution of the task, thereby improving the success rate of task execution.

The present disclosure discloses a memory, a memory system, and a method for operating memory, which belongs to the memory techniques field. The method for operating memory comprises determining a storage state of a reference memory cell, determining a discharge duration of a sensing node corresponding to a target memory cell based on the storage state of the reference memory cell, and reading the target memory cell based on the discharge duration of the sensing node corresponding to the target memory cell to obtain read results. The target memory cell and the reference memory cell are located in the same string and are adjacent, and the programming order of the reference memory cell is after that of the target memory cell. The present disclosure may reduce the influence on reading memory cells by interlayer interference and improve the accuracy of reading memory cells.