219 results about "Keyword search" patented technology

The invention belongs to the technical field of artificial intelligence, and provides a method and a system of a rule and regulation intelligent question and answer AI assistant embedded in a production and fusion platform, which are characterized in that a structured knowledge base is constructed, and natural language interactive intelligent questions and answers with strong business association are generated in combination with a large model; the method can help employees in the production and fusion platform to efficiently obtain company files such as rules and regulations, and improves the working efficiency. Meanwhile, the intelligent question answering and file tracing functions are provided, and source files are traced through keyword search; and the accuracy and the convenience of the employees to obtain the information can be improved. And thirdly, by constructing a structured knowledge base covering business specifications, process guidance, group document sending and rules and regulations, scattered unstructured files (such as PDF and Word documents) are converted into searchable metadata and associated tags, and the problem that traditional manual retrieval is time-consuming and labor-consuming is solved.

The invention discloses a mixed search method and device, equipment and a storage medium, and the mixed search method comprises the steps: extracting a keyword of a query statement when the query statement is received, searching a target document database according to the keyword to obtain a first search result, and meanwhile, utilizing a vectorization search algorithm to obtain a second search result; according to the method, vectorization indexing is carried out according to the query statement and the target vector database to obtain a second search result, and then the first search result and the second search result are merged and sorted to obtain a search result set, so that the high efficiency of vectorization indexing and the flexibility of keyword search are utilized; and the result of the vectorization index and the result of the keyword search are sorted and fused, and the obtained search result set is more accurate, so that the mixed search method disclosed by the invention realizes a more accurate, efficient and flexible search technology.

The invention discloses a sewage treatment question and answer method and device based on a large model, a medium and a product, and relates to the field of language model construction.The method comprises the steps that existing data related to sewage treatment are obtained; preprocessing the existing data to obtain text data; segmenting the text data to obtain text blocks; storing the text blocks in a text database, encoding the text blocks to generate semantic vectors, and storing the generated semantic vectors in a vector database; a keyword search method and a vector similarity search method are adopted, based on the sewage treatment problem, retrieval results related to the sewage treatment problem are obtained from the text database and the vector database; the retrieval results are reordered, and answer document fragments are obtained; forming prompts based on the sewage treatment questions and the answer document fragments; and inputting the prompt into the large language model to generate a sewage treatment question and answer text. According to the invention, accurate answers corresponding to sewage treatment questions can be provided, so that the risk of sewage treatment is reduced.

The invention relates to the technical field of information security, in particular to a forward security policy hidden attribute-based keyword search method, which is used for access control and search of sensitive information and comprises the following steps: acquiring a public parameter and a master key; attribute processing is performed on an attribute set submitted by a data user, a user private key is constructed, and a puncture key is output; the method comprises the following steps: randomly selecting a symmetric key, performing symmetric encryption on a plaintext through the symmetric key to obtain an initial ciphertext, sequentially performing strategy hidden encryption, keyword encryption and label binding on the plaintext to obtain a corresponding output representation, and integrating the initial ciphertext and the output representation to obtain a complete ciphertext; when the constraint condition is met, the puncture key is updated; establishing a keyword set according to the data user demand content, generating a trap door, and initiating a search request; matching the trap door with the complete ciphertext according to the search request to obtain a matching result, and decrypting the initial ciphertext by integrating the updated puncture key and the user private key to obtain a corresponding plaintext; and the forward safety is effectively improved.

The invention relates to the field of artificial intelligence, in particular to an enterprise information generation and retrieval method based on AI and a knowledge graph, which can accurately position core elements required by a user by receiving a target retrieval statement input by the user and respectively extracting various types of entities from the target retrieval statement, avoids fuzziness of traditional keyword retrieval, and improves user experience. According to the method, attribute similarity scores, relation similarity comprehensive scores and semantic similarity comprehensive scores of all enterprises are obtained through analysis, it is ensured that retrieval results are consistent with the basic face of user requirements, dynamic weight rules are constructed, relevancy scores of all the enterprises and user target retrieval statements are analyzed, and sorting results of all enterprise information are obtained and returned to users. And accurate, flexible and intelligent enterprise retrieval experience is realized.

The present invention relates to the technical field of natural language processing, and specifically to a visual patent search method based on a pre-trained language model. In a patent keyword search scenario, the present invention extracts keywords and represents word vectors from patent texts based on the pre-trained language model, reduces the dimensionality of patent features returned by the search, and visually displays the search results in the form of a scatter plot. Compared with search results displayed in a list form, the method is more intuitive and provides richer search information such as the degree of similarity between patents and patent clustering.

The invention discloses a content query method and device, electronic equipment and a computer readable medium. The method comprises the steps that to-be-queried content is acquired; in business data of at least one target business accessed to the search platform, business data matched with the to-be-queried content is searched based on a keyword search mode and a semantic search mode, and a first search result corresponding to the keyword search mode and a second search result corresponding to the semantic search mode are obtained; fusing the first search result and the second search result to obtain a fusion result; and obtaining a target query result corresponding to the to-be-queried content based on the fusion result. Therefore, access operations of different services can be realized through the search platform, so that the different services can use the search platform to realize a search function, and each access service can obtain the same search experience; in addition, the query result of the to-be-queried content is obtained in combination with keyword search and semantic search modes, and the search accuracy of the query result can be improved.

The invention discloses a hybrid encryption method supporting access control and controllable data search, and relates to the field of secure data sharing. According to the method, a CP-ABE (Ciphertext Policy Attribute Based Encryption) technology and a symmetric searchable Encryption (SSE) technology are creatively combined, and a data authorization access function and a data controllable search function are integrated. As for data authorization access, CP-ABE is dominated, fine-grained access control is achieved by embedding attribute information, and it is ensured that only authorized users conforming to a preset strategy can decrypt data. For data controllable search, SSE is dominated, a data storage service provider is allowed to execute a search task based on keywords on the premise of not decrypting data, and expansion of fuzzy keyword search is supported in combination with a trusted execution environment technology. According to the method, the problems that user access is not limited and data sharing is easy to leak to an untrusted party are effectively solved. Through strict user right control, unauthorized access is prevented. And meanwhile, the targeted search of the shared data is realized, and bidirectional requirements are met.

The invention provides an electronic signature service method and system compatible with multiple CA certificates, independent and unified standard functions, interfaces and processes such as certificates, seals, configuration rules and dragged seal signing are formed in a platform system, and API interfaces such as PDF seal picture synthesis and keyword search are carried out by utilizing a JAVA component and an itext component. A virtual complete signing process can be completed before no task is accessed to a CA service provider, and a previewed PDF file is formed; and according to subsequent docking of different CA digital certificates, APIs of different CA digital certificate service providers are accessed to complete configuration, rule explanation, signature authorization verification and the like in links of certificate management, seal management, rule configuration, seal dragging signature and the like, such as signature of seal positions of all parties, automatic signature and the like. According to the invention, various CA digital certificates and different API services and personalized requirements of providers can be flexibly corresponded, and various signing scenes and process specifications of existing users can be met to the greatest extent.

The invention discloses a network technology service consultation intelligent matching system based on artificial intelligence, and relates to the technical field of artificial intelligence, and the system comprises the steps: collecting historical network technical problems and corresponding solutions through a data collection module, and extracting main and auxiliary keywords; the search popularity calculation module calculates the search popularity of a keyword combination and introduces parameters such as search times, user feedback scores and time attenuation factors to construct a formula, the database storage module stores questions and schemes after sorting the questions and the schemes according to the popularity, and when a user inputs the questions, the user question matching module extracts keywords and sends the keywords to the user question matching module; the method comprises the following steps: determining a combination with relatively high search popularity according to a main keyword, taking the combination as alternative data, converting the keyword into a digital vector to calculate similarity, and displaying a solution with the similarity higher than a threshold value to a user according to the size of the similarity, so that the system can efficiently and accurately provide a solution for a network technical problem for the user; and the network technology service consultation quality and efficiency are improved.

The invention relates to the field of data analysis, in particular to a database information acquisition and analysis method for pharmacological analysis of heat stroke, which comprises the following steps: determining a data state according to data diversity and data stability of rat input data, and determining a data processing mode according to the data state; in analog data supplementation, determining a supplementation mode according to a comparison result of the effective standard index proportion and a preset effective standard index proportion; in the keyword analysis, a use state is determined according to the matching frequency and the spacing distance of the effective keywords, and a corresponding search mode is determined according to the use state; in the effective keyword search process, determining a page distribution state according to the page similarity and the information relevancy of the target website, and determining an acquisition adjustment mode as track simulation adjustment or search simulation adjustment according to the page distribution state; the searching and matching efficiency of database information acquisition and analysis in pharmacological analysis related to heat stroke is improved.

The invention relates to a multi-attribute tag and score data asset recommendation method, and belongs to the technical field of data asset recommendation. According to the method, the current situation that concerned data asset information is passively obtained through single keyword retrieval is changed, multi-dimensional attribute decomposition is carried out according to the characteristics of data assets, the recommendation process is designed through the relevance between the data assets, the relevance between the users and the relevance between the users, and the recommendation efficiency is improved. The relatively accurate data asset recommendation content is formed, the interested data assets are actively recommended to the user, and the accuracy of the recommendation result is improved.

The invention provides a mixed retrieval method, system and device based on multi-algorithm fusion and a storage medium, and the method comprises the steps: obtaining various types of document data, preprocessing the document data, and obtaining plain text data; segmenting the plain text data into a plurality of pieces of block node data, and generating a plurality of derivative problems for each piece of block node data by using a large language model; carrying out vectorization coding on the block node data and the derivation problem, and storing the block node data and the derivation problem in a vector database; receiving a user query question, and generating a plurality of related preset questions for the query question by using the large language model; converting the query question and the preset question into a vector form, executing keyword retrieval and vector retrieval, and obtaining corresponding candidate results in a vector database; and carrying out weighted fusion on the candidate results through a weighted reciprocal rearrangement algorithm to obtain most relevant retrieval data. According to the method, the efficiency of information retrieval and the correlation of results can be improved, and the retrieval requirement of a user in a complex semantic scene is met.

The invention belongs to but is not limited to the technical field of artificial intelligence, and particularly relates to a multi-strategy RAG process optimization method and system for large model questioning and answering, and the method comprises the steps: carrying out the classification processing of a document of a user, and selecting semantic blocks or customizing the sizes of the blocks; receiving a text input by a user; the retrieval is divided into two parts, one part is semantic vector retrieval, and the other part is keyword retrieval; the system further screens and filters candidate text paragraphs in combination with structured meta-information on the basis of vector retrieval; after the preliminary vector retrieval, a bge-ryanker-v2-m3 model is introduced to carry out secondary sorting on the results; the model firstly receives input Prompt and converts the Prompt into vector representation; the vector is processed through a multi-layer Transform network so as to extract and model semantic features in the text; a corresponding output result is generated in combination with specific task requirements defined by Prompt; and outputting an answer generated by the large model for the user question.

The invention discloses an efficient attribute-based searchable encryption method with dual privacy protection, which adopts an inner product predicate encryption mechanism, and effectively ensures the privacy security of user attributes and access strategies by introducing orthogonal attribute design. A blind factor is introduced in a user attribute private key distribution stage, so that a cloud server is effectively prevented from acquiring sensitive attribute information of a patient in a keyword search and attribute matching process. The overall access policy is divided into a plurality of sub-policies, and the limitation that only an AND gate structure is supported traditionally is broken through, so that the fine-grained access control requirements for different application scenes are met. And in combination with a keyword-attribute matching algorithm, tight binding of data and indexes is realized, and the trap door and the transformed private key are integrated, so that the matching efficiency of the cloud server is improved. An off-line / on-line encryption mechanism and an outsourcing decryption technology are introduced, a large amount of calculation operation is transferred to cloud processing, the calculation pressure of Internet of Things medical terminal equipment is effectively relieved, and the system operation efficiency is remarkably improved.

The invention belongs to but is not limited to the technical field of symmetric searchable encryption, and discloses an efficient wildcard keyword search method and system for encrypted data, the feature set # imgabs0 # of a keyword w is extracted by calling IndexSet (wi), the encryption algorithm # imgabs1 # in symmetric subset predicate encryption is called to encrypt # imgabs2 #, and the symmetric encryption algorithm SE.Enc (K, DB (wi)) is used to encrypt a document identifier containing the keyword wi. The two parts of ciphertexts are stored in an encryption database and outsourced to a cloud server; calling TrapSet (wq) for a keyword wq containing a wildcard character to generate a query set # imgabs3 #, calculating a decryption key tk for the query set # imgabs4 # through an S2PE algorithm, and finally sending the tk as a search trap door to a cloud server by a user; and for the obtained ciphertext identifier, the user obtains the corresponding identifier by using the key K. According to the method, false alarms of character sequences can be reduced or eliminated in searchable encryption of wildcard characters, leakage of feature matching modes is reduced, storage and query overhead in the search process is reduced, and search performance is improved.

The invention belongs to the technical field of artificial intelligence, and relates to a data generation method and device, computer equipment and a storage medium. Performing structured processing on the multi-dimensional information based on the intelligent agent to obtain target information; based on a keyword search tool, searching target resource content related to the target information from a recommendation resource library; generating a target input text based on the target information and the target resource content; performing scheme generation processing on the target input text and the target prompt text based on the target large language model to obtain a target return visit scheme; performing privacy verification on the target return visit scheme; and if the target return visit scheme passes the privacy verification, outputting the target return visit scheme. In addition, the invention also relates to a block chain technology, and the target return visit scheme can be stored in a block chain. The method can be applied to return visit business scenes in the medical science and technology field and the financial field, and the processing efficiency and flexibility of return visit scheme generation are effectively improved.

Processor-based systems and / or methods of operation may generate queries and suggest legacy narrative content (e.g., video content, script content) for a narrative under development. An artificial neural network (ANN, e.g., autoencoder) is trained on pairs of video and text vectors to capture attributes or nuances beyond those typical of keyword searching. Query vector representations generated using an instance of the ANN may be matched against candidate vector representations, for instance generated using an instance of the ANN from legacy narratives. Such may query for missing video and / or text for a narrative under development. Matches may be returned, including scores or ranks. Feature vectors may be shared without jeopardizing source narrative content. Legacy source narrative content may remain secure behind a controlling entity's network security wall.

The invention relates to the technical field of data asset management, and discloses a data asset intelligent retrieval and visualization display platform, which comprises a data asset intelligent retrieval and visualization system, and the data asset intelligent retrieval and visualization system comprises a central processing unit. The input end of the central processing unit is electrically connected with the output end of a data analysis and mining module; according to the intelligent retrieval and visual display platform for the data assets, a user can quickly position required data resources in manners of keyword search, label screening and the like, the data retrieval efficiency is greatly improved, meanwhile, an intelligent retrieval algorithm can provide personalized search results according to the search history and preference of the user, and the user experience is improved. According to the method and the system, the retrieval accuracy is further improved, the platform performs classified management on the data assets, and a corresponding label is marked on each data set, so that a user is helped to better understand the meaning and the purpose of the data, and a more accurate matching result can be provided during retrieval.

A system is provided.SOLUTION: A system comprising: an information reception unit that receives a request input by a user; an analysis unit that analyzes the request and extracts a keyword related to the request; a search unit that searches for a store corresponding to an electronic payment based on the extracted keyword; a recommendation unit that recommends an optimal store based on the search result; and an information transmission unit that transmits the recommended store information to a user terminal.SELECTED DRAWING: Figure 1

A system is provided.SOLUTION: A system, comprising: means for receiving authentication information input by a user and generating an authentication token; means for receiving a keyword searched by the user and providing a search result; means for obtaining and providing detailed information corresponding to a selected recipe; means for suggesting substitute ingredient information for an ingredient included in the recipe; and means for receiving an image and a comment posted by the user and displaying the image and the comment in a community.SELECTED DRAWING: Figure 1

1. Name of the Design Product: Graphical User Interface for Keyword Search Recommendation Display of Electronic Devices. 2. Use of the Design Product: For an electronic device. 3. Design Key Points of the Design Product: Lies in the content of the graphical user interface on the screen. 4. Picture or Photograph Most Indicating the Design Key Points: Front View. 5. Use of the Graphical User Interface: In the application interface, based on the user's interactive operations, pop up the recommended information of the input keywords. The front view shows the page display before entering keywords. The user enters text in the input box, and the interface enters the changing state diagram, where the recommended information of the keywords is displayed in the search dropdown box.

A display device comprises a voice recognition unit performing voice recognition, a conversation-derived term extraction unit extracting conversation-derived terms from conversation information derived from the voice recognition, a search keyword storage storing the conversation-derived terms and search keyword in an associated manner, a search keyword extraction unit extracting search keywords from the search keyword storage using the conversation-derived terms, a material storage unit storing each page of a plurality of presentation materials, a search term of each page, and a score of the search term in an associated manner, a relevant page information extraction unit extracting a page of presentation material associated with the search keyword, a selection term extraction unit extracting the search keywords, and a selection term display unit causing the selection terms to be displayed on a display unit.

The invention relates to the technical field of AI voice rates, and discloses an AI voice rate adjusting method of an AI platform, which comprises the following steps: acquiring a voice signal input by a user, and extracting keywords; searching and determining a reply text of the voice content according to the keyword; performing speech speed analysis on the speech signal to obtain the speech speed of the speech signal as an initial speech speed, and meanwhile, obtaining the speech speed of AI speech aiming at the reply text as a target speech speed; comparing the initial speech speed with a target speech speed, and when the difference value between the initial speech speed and the target speech speed is smaller than a set threshold value, performing AI speech broadcast on the reply text by adopting the target speech speed; and when the difference value between the initial speech speed and the target speech speed is greater than or equal to a set threshold value, adjusting the target speech speed according to the initial speech speed. According to the method, the voice speed of AI voice reply is adjusted, the AI voice can adapt to the voice speed requirement in real time no matter the habit of the user is rapidly expressed or the preference of the user is slowly narrated, and the satisfaction degree and dependency degree of the user on voice service are enhanced.

A system generates a topic graph based on the SERP data for high-ranking keywords in a search engine. Clustering may be based on (for example) degrees of intersection between links in search results of keywords from the SERP data, or keyword embeddings on the SERP data. The topic graph loosely clusters the keywords, such that the keywords have at least a threshold degree of similarity to their clusters, but not necessarily to all the other keywords in the cluster. As a consequence of the loose clustering, a given topic contains keywords that represent different aspects of the same concept, such that a content viewer would likely be interested in a piece of content that addresses the different aspects, and a search engine would be more likely to highly rank the content within its search results for one of the keywords. The system may also provide a user interface permitting a user to browse and filter the topics in the topic graph according to search criteria, as well as to see the topics ordered according to topic ROI estimates computed by the system.

To enable the valuation of patents. [Solution] An information processing system comprising: a keyword extraction unit that extracts keywords from the claims of a patent to be verified; a search unit that searches for information about a business or product that matches the extracted keywords; an infringement determination unit that estimates the degree to which the searched information about the business or product satisfies the constituent elements of the claim; and a valuation unit that evaluates the value of the patent according to the degree.

The present invention discloses a community life convenience evaluation method based on network map service, which is applicable to the community life convenience evaluation at the city level, including: using a keyword search interface to obtain the commercial community and life service facility data of the study area; assigning weights according to the number of life service facilities, and establishing a life convenience evaluation system; using a buffer zone analysis method to screen potential accessible facilities, and obtaining the walking time between the community and the life service facilities through a path planning interface; based on the opportunity accumulation method, introducing a Gaussian decay function to calculate the community life convenience. The present invention makes full use of the characteristics of large data volume, high precision, and fast update of network map services, and incorporates the distance between the community and the public service facilities into the community life convenience evaluation through the Gaussian decay function, thereby improving the accuracy of the evaluation method.

1. The name of the present design product: the area of search bar of the graphical user interface of the key word search of the electronic device. 2. The use of the present design product: for an electronic device. 3. The design points of the present design product: in the claimed part of the graphical user interface. 4. The picture or photo that best shows the design points: design 1 front view. 5. Design 1 is designated as the basic design. 6. The use of the graphical user interface: the graphical user interface is used for key word search, and multiple types of fields are selected in the talent search input box for search screening. 7. The human-computer interaction mode of the graphical user interface: the graphical user interface can be interacted by clicking, pressing or sliding the graphical user interface. 8. The change state description of the graphical user interface: design 1 front view is a key word search interface, and position related information can be searched here. When the search box is empty, click the search box to display the drop-down menu of search history. When the mouse is selected and stopped on any historical search data, the search condition of the data is displayed, design 1 front view becomes design 1 change state figure 1; click any historical search button in design 1 change state figure 1 to search, enter design 1 change state figure 2; click any term below to enter design 1 change state figure 3; the label can be one or more, if the content exceeds the size of the search box after selecting multiple labels, it is omitted, such as design 1 change state figure 4; mouse over any label in design 1 change state figure 4, a red × appears on the label, such as design 1 change state figure 5. Design 2 front view is a key word search interface, and position related information can be searched here. When the search box is empty, click the search box to display the drop-down menu of search history. When the search box input content, the drop-down menu displays the search type label and the matching content related to the search content below the label, design 2 front view becomes design 2 change state figure 1; click any search type label button in design 2 change state figure 1, the current input content of the search box is searched as the type corresponding to the label, enter design 2 change state figure 2; click any term below to enter design 2 change state figure 3; the label can be one or more, if the content exceeds the size of the search box after selecting multiple labels, it is omitted, such as design 2 change state figure 4; mouse over any label in design 2 change state figure 4, a red × appears on the label, such as design 2 change state figure 5. 9. Other matters requiring explanation Other matters requiring explanation: The design of the present design product is partially protected by the design office. The part covered by the gray shadow is not claimed, and the rest is claimed.

Intelligent Storage and Retrieval (ISAR) systems and methods are described, which combine keyword search methods with vector search methods. ISAR also includes additional sub-systems and methods such as ngram searching, entity counts, hyponym filtering, and selective synonym expansion. ISAR pinpoints the exact passages that are relevant to a given query and returns the facts that are precisely relevant to a given query. Some embodiments send the relevant facts themselves in lieu of sending any text chunks. Moreover, ISAR is extremely cost effective. It is extremely fast as well.