21results about How to "Achieve retrieval" patented technology

The invention relates to the field of knowledge maps and intelligent questioning and answering, in particular to a domain intelligent questioning and answering system and method based on a knowledge map library and a text vector library. Firstly, a user stores unstructured texts and structured knowledge which are collected and arranged in a certain domain into the text vector library and a knowledge map respectively; the system adopts a customized knowledge retrieval algorithm to perform parallel retrieval on the text vector library and the knowledge graph so as to identify and extract related knowledge points. And based on the retrieved knowledge points, the system generates a question-answer reply of a natural language by using a large language model, so that a knowledge-driven question-answer process is realized. The domain questions and answers based on the knowledge graph library and the text vector library improve the accuracy and integrity of system answers, the illusion of a large language model is avoided, the answers of the system are traceable, and the credibility of the system is realized.

The invention belongs to but is not limited to the technical field of privacy protection, and discloses a certificateless linkable ring signcryption method and system based on an SM2 algorithm, the adopted SM2 algorithm is a public key encryption algorithm based on an elliptic curve, the secret key length is shorter, the safety is higher, and the operation efficiency is remarkably improved in the encryption and decryption process. A certificateless public key cryptosystem is used, dependence on a traditional PKI system is not needed, and complexity and cost of certificate management are reduced. According to the invention, a linkable function is creatively added into a ring signcryption scheme and is applied to a remote medical information system. On the premise of ensuring the privacy of the patient, a doctor can retrieve the medical record of the patient through the signature tag generated by the patient, so that the illness state of the patient can be better known without knowing the specific identity of the patient. Compared with an existing scheme, the scheme is more suitable for remote medical seeing of the patient, and the practicability is higher.

The embodiment of the invention provides a data processing method and device based on a natural language model and electronic equipment, and belongs to the technical field of financial science and technology. The method comprises the following steps: acquiring financial data information and to-be-answered question information; performing knowledge representation on the financial data information, and creating a first data structure and a second data structure; creating an insurance data set according to the first data structure and the second data structure; training a preset natural language model through the insurance data set to obtain an automatic question and answer language model; in response to a user retrieval instruction, performing text analysis on the to-be-answered question information to obtain an analysis result; performing answer retrieval on the analysis result based on an automatic question and answer language model and an insurance data set to obtain a retrieval set; and when the retrieval set is empty or the preset answer statement does not exist in the retrieval set, converting the user retrieval instruction into a manual service conversion instruction. According to the embodiment of the invention, the problem processing efficiency and the service quality can be improved.

The invention provides a space retrieval method and device supporting mass point cloud data, equipment and a medium, and relates to the technical field of point cloud processing, and the method comprises the steps: carrying out the three-dimensional division of a space occupied by to-be-processed point cloud data, and obtaining a multi-layer space grid set; constructing a unique grid index code of the space grid according to the corresponding azimuth information of the space grid in the space grid to which the space grid belongs in the upper-layer space grid set; establishing a mapping relation between the point cloud data and the grid index codes; rearranging the point cloud data based on the mapping relation and storing the point cloud data in a target storage area; and receiving a retrieval request, determining the index code of the to-be-rendered grid, and retrieving the to-be-rendered point cloud data from the target storage area according to the index code of the to-be-rendered grid, thereby realizing retrieval and real-time rendering of the to-be-rendered point cloud data. According to the method, quick retrieval and real-time rendering of the point cloud data with unlimited data volume can be supported, and the retrieval and rendering efficiency of the point cloud data is greatly improved.

The invention discloses an efficient video data distributed retrieval method and system, and the method comprises the steps: converting video data into a feature vector sequence through an image feature extraction technology; then, prefix features of the sample sub-feature sequences are constructed and extracted through data indexes, and spatial indexes are constructed on all sub-feature dimensions respectively; finally, through query processing, candidate sets are queried and filtered on all the sub-indexes based on the lower bound distance, and accurate video retrieval is completed through the intersection of the candidate sets and the follow-up processing process. By applying the multivariate time series data distributed similarity query method provided by the invention, distributed storage and efficient query of large-scale video data can be realized, and query contents can be quickly identified and positioned in a massive video database for given video paragraphs or semantic descriptions. The video data distributed index structure provided by the invention can effectively support video retrieval with unequal durations, has relatively high spatial ductility, and can play an important role in the fields of big data, data mining, databases and the like.

The invention discloses a standard query, retrieval and question and answer method and system, which is based on a standard text analysis module of a rule and is used for quickly and accurately carrying out structured processing on a standard text and adding a logic link. Through the combination of different text retrieval modes, the search range is expanded, and the accuracy of the search result is improved. According to the method, the characteristics of the standard industry are combined in a thinking chain mode, the cue words meeting the use habits of the standard industry are constructed, a large model tool is combined with the standard industry, answers are given, or an explanation, summary or related information list is generated according to the complexity of the questions input by the user, and the use experience of the user is improved.

The application relates to the computer technical field, in particular to a sensitive word storage and retrieval method and system, electronic equipment and storage medium, the method comprises the following steps: storing the sensitive word to be stored to a target sharding service through a target mapping table, wherein the target mapping table comprises a mapping relationship between the target sharding service and the first character of the sensitive word to be stored, the target sharding service is one of a plurality of sharding services in memory, and the target sharding service is a sharding service polled currently; based on the target mapping table and the first character of the word to be retrieved, the sharding service to be retrieved corresponding to the first character of the word to be retrieved is determined; and based on the word to be retrieved and the data stored in the sharding service to be retrieved, the sensitive word retrieval is carried out; the method can preferably improve the storage efficiency and retrieval efficiency of the sensitive word, and the cost is low.

The invention provides a dialogue multimedia content generation method and system, and the method comprises the steps: carrying out the semantic understanding and intention analysis of a standard text through a pre-trained large language model, so as to judge whether an input instruction is a retrieval instruction or an editing instruction; if the input instruction is a retrieval instruction, inputting the text unit into a preset video retrieval model, so that the video retrieval model feeds back a target video matched with the text unit; and if the input instruction is an editing instruction, performing similarity matching on the standard text to obtain an editing mode, and sequentially performing editing processing of video matting, video reconciling, video segmentation, video restoration, audio generation, mouth shape generation and the like on a to-be-edited video pre-selected by a user by adopting the editing mode to obtain multimedia generation content. Therefore, the multimedia content editing becomes intelligent, the threshold of multimedia editing can be greatly reduced, and more convenient and efficient editing experience is provided for users.

The application discloses a large-scale image-oriented encrypted retrieval method and relates to the technical field of image retrieval. Q The application discloses a large-scale image-oriented encrypted retrieval method and relates to the technical field of image retrieval. Q The application discloses a large-scale image-oriented encrypted retrieval method and relates to the technical field of image retrieval. Q The application discloses a large-scale image-oriented encrypted retrieval method and relates to the technical field of image retrieval. Q The application discloses a large-scale image-oriented encrypted retrieval method and relates to the technical field of image retrieval. The application can realize image content-based search, and the encryption algorithm is simple to design, which is beneficial to reducing search overhead while being encrypted.

This application provides a data processing method, apparatus, and electronic device based on a natural language model, belonging to the field of financial technology. The method includes: acquiring financial data information and information about questions to be answered; representing the financial data information using knowledge representation to create a first data structure and a second data structure; creating an insurance dataset based on the first and second data structures; training a preset natural language model using the insurance dataset to obtain an automatic question-answering language model; responding to a user's search instruction by performing text analysis on the information about questions to be answered to obtain analysis results; retrieving answers based on the automatic question-answering language model and the insurance dataset to obtain a search set; and converting the user's search instruction into a request to transfer the user to human assistance when the search set is empty or does not contain a preset answer statement. This application can improve the efficiency and quality of problem handling and service.

The present invention discloses a fast policy retrieval method based on attribute Bloom filter. The data owner generates the parameters required for platform operation and generates the available private key of the data user by using the subject attributes. The data owner formulates the access control policy and converts the policy into a linear secret sharing matrix to realize the construction of the policy and publish it to the blockchain. Before knowing the message to be encrypted, the data owner performs a large number of pre-calculations based on the public parameters. When the message to be encrypted is known, the ciphertext is quickly generated. During policy retrieval, the attribute matching function is reconstructed by using the attribute Bloom filter, and the specific position of the subject attribute is quickly located by using the hash function. If the attribute mapping function can be successfully constructed, it proves that the attribute of the data user meets the access policy formulated by the data owner, otherwise it indicates that there is no permission to access. Finally, the address of the object resource is decrypted, and the pressure of the chain retrieval is dispersed through multiple clients, the system retrieval time is improved, and data sharing is completed.

This application provides a website retrieval method and apparatus that can improve the accuracy of search engine retrieval results and increase the efficiency of obtaining target websites. The method includes: determining at least one key subtext in the initial search text based on its part-of-speech tagging; performing semantic-based transformation processing on each key subtext according to its semantics to generate representative text corresponding to each key subtext and related to the identification information of the website to be retrieved; determining a first search text based on the position of each key subtext in the initial search text and the representative text corresponding to each key subtext; and retrieving the first search text using a search engine to obtain a first target website.

The application discloses a data intelligent retrieval and access method and system in the field of space science, and the method comprises the following steps: according to the text input by a user, adopting a word segmentation model and a word embedding model respectively, mapping the text to corresponding key words and embedding vectors, and forming double-path recall retrieval results of a data set based on key word matching and embedding vector similarity matching; based on a rearrangement model, reordering the two kinds of retrieval results of the data set to form a query result of the data set granularity; according to the text input by the user, a data sample and a selected data set, adopting a pre-constructed machine feature extraction model, extracting a vector representation of user retrieval information, and based on vector similarity matching, retrieving data files in the data set to form a query result of the data file granularity; based on a pre-established optimal affine transformation function and a metric space, quantitatively calculating the data similarity with respect to a retrieval sample in terms of distance to obtain a retrieval result.

The invention relates to the technical field of knowledge base matching, and provides a character array comparison method based on OCR (Optical Character Recognition) image recognition, which comprises the following steps of: 1, carrying out OCR recognition on a submitted error-reporting screenshot, and extracting the position and specific character information of a feature character string in the screenshot; 2, the feature character strings are cleaned, the character strings are filtered, and the character strings passing cleaning are stored in a character string array to be compared; 3, traversing each piece of knowledge in the knowledge base, acquiring the position and specific character information of a feature character string corresponding to each piece of knowledge by utilizing OCR (Optical Character Recognition), comparing a to-be-matched feature character array of the knowledge with a feature character array of a knowledge point by utilizing a matching algorithm, and judging whether the knowledge is a possible solution or not; and 4, displaying all possible solutions according to the weights calculated by the matching algorithm from high to low. According to the invention, the character arrays can be well compared.

The present invention discloses a method, device and storage medium for identifying the name of a drug to be identified. The method for identifying the name of a drug to be identified includes the following steps: obtaining a preliminary identified drug name plus specifications; preliminarily retrieving and extracting similar drug names plus specifications; normalizing word segmentation processing; processing the normalized word segmentation results by a set difference quantization algorithm to obtain name similarity; selecting a similar drug name with the highest name similarity as the drug with the same name as the drug to be identified, and outputting it as a recommended drug name. The present invention utilizes word segmentation technology and semantic similarity technology, combined with a quantization method of the symmetric difference of two sets, to obtain the similarity between the preliminary identified drug name plus specifications and the standard drug name plus specification name in the local drug catalog database, thereby achieving rapid identification of drug names and recommending the same drug, solving the problem of time-consuming and labor-intensive identification and recommendation of the same drug in the prior art.

This invention discloses a method and system for video diagnosis of power system faults based on spatiotemporal semantic fusion, relating to the fields of power system fault detection, computer vision, and multimodal information fusion. The method involves acquiring fault videos and dividing them into multiple video sub-segments. For each video sub-segment, a CLIP image encoder is used to extract spatial feature vectors from each frame, resulting in a corresponding spatial feature sequence. This spatial feature sequence, after being embedded with positional information, is input into a temporal Transformer encoder. A self-attention mechanism is used to calculate the internal temporal relationships, and these are aggregated to obtain a sub-segment feature vector representing the dynamic features of that video sub-segment. Text describing the power system fault is collected, and a CLIP text encoder is used to extract text feature vectors for each fault text. Cross-modal similarity matching is performed between the sub-segment feature vectors and the text feature vectors, and the matching result with the highest similarity score is used as the fault diagnosis result. This invention has significant advantages for the identification of complex dynamic fault events.

The invention provides a vector retrieval device based on approximate nearest neighbor search. The vector retrieval device comprises a first storage, a second storage, a third storage, a fourth storage, a large clustering calculation LCM module, a quantitative lookup table calculation QPM module and a final quantitative similarity calculation and result calculation DCM module. The device can be connected with memories such as an HBM and a DDR instead of only adopting a BRAM on-chip memory of an FPGA to store all data, and can be applied to more and more complex scenes; according to the device, a more efficient parallel strategy of large clustering center calculation and quantitative lookup table calculation and a higher-speed Top-k calculation module are adopted, so that the speed is higher, and the power consumption is lower.

The invention discloses a power transformer technical standard differentiation comparison method based on a knowledge graph, and the method comprises the steps: determining the technical standard of a power transformer according to the collected related technical standard covering the power transformer, carrying out the textualization processing of the technical standard, and generating a text technical standard; according to a text technical standard, carrying out first preset hierarchy disassembly to generate predetermined format technical content of each hierarchy; performing second preset level disassembly on the power transformer equipment to generate preset format equipment content of each level; the content of the first technical requirement project level and the content of the second technical requirement project level of the knowledge graph technology are associated, and a power transformer technical key point system is constructed; and searching a plurality of technical requirements of the to-be-searched structure from the hierarchical technical key point system of the power transformer by utilizing a knowledge graph query language, and comparing the plurality of technical requirements to form a differentiated technical standard of the to-be-searched structure.

This invention discloses a method, medium, device, and product for interpreting and delivering evidence chains in soil inversion based on confirmatory ablation, relating to the field of soil information inversion technology. The method includes: dividing joint input features into a set of interpretation objects according to interpretation granularity, and constructing an ablation baseline for the interpretation objects; constructing an ablation input based on the ablation baseline; inputting the ablation input and joint feature vector into a trained soil inversion model, respectively, and calculating the evidence contribution of the interpretation objects based on the two prediction results; extracting Top-K evidence to form pixel-level evidence entries; dividing all pixels into regional units according to governance units, constructing a regional evidence ranking score, and extracting the Top-K evidence entries from the regional units to form a regional evidence summary; outputting the prediction results and regional evidence summaries according to preset field semantic specifications as an interpretation list and interpretation layer, and generating an index file. This invention solves the problem of the lack of a verifiable evidence interpretation mechanism in existing technologies.

The self-driven fish passing system comprises a power generation dredging device, a monitoring device and a flow state adjusting device, and the power generation dredging device comprises a rotating shaft structure, movable fan blades, a power generator, a high-pressure spray head, an overflow type bottom filter, a brush and a storage battery; the monitoring device comprises an infrared camera, a flow velocity detector, an environmental condition measuring instrument, a water temperature measuring instrument, an illumination detector, a turbidity measuring instrument, a controller, a computer, a PIT antenna and an electric box, and the flow state adjusting device comprises a movable lead angle and an overflow type bottom filter. The long-term monitoring effect on the fish passing effect of the fishway is improved, self-adjustment of the flow state flow in the fishway pond chamber is achieved, meanwhile, a water flow environment which facilitates efficient passing of fishes and reduces the physiological pressure of the fishes as much as possible can be created, the upstream efficiency is improved, a reasonable fishway pond chamber dredging method can be provided, and the fishway pond chamber dredging efficiency is improved. And the service life of the fishway is prolonged while the running effect of the fishway is ensured.

A scene sketch retrieval system based on a conditional graph autoencoder comprises the following modules: a conditional graph construction module, a weighted graph construction module, a graph embedding vector generation module, a weakly supervised semantic reconstruction module and a retrieval module; a scene sketch retrieval method based on a conditional graph autoencoder comprises the following operation steps: (1) constructing a conditional graph and generating conditional graph node features; (2) constructing a weighted graph and generating weighted graph node features; (3) generating a graph embedding vector; (4) calculating the distance between the graph embedding vector of the scene sketch to be retrieved and the graph embedding vectors of all natural images in a database, sorting them in ascending order according to the distance, and returning the natural images in sequence as retrieval results.