301 results about "Search terms" patented technology

A research assistant system described herein includes a research assistant tool and associated components and a graphical user interface to guide user input to research, discover, and evidence answers for complex research questions. The research assistant system may include the graphical user interface (“GUI” or “user interface”) for presentation on a user device associated with a user. The user interface may provide prompts and guidance for collaboration and exploration of research concepts iteratively. A concept may include a search term, entities, and / or propositions / statements.

The invention relates to the technical field of information retrieval, and discloses a retrieval method for aggregating multi-dimensional retrieval strategies. When retrieval is carried out, a retrieval word input by a user is obtained; based on the retrieval word, performing retrieval by using each retrieval strategy to obtain a retrieval result of each retrieval strategy; inputting the retrieval word into a semantic judgment model to obtain a retrieval strategy weight adjustment parameter; calculating according to the retrieval strategy weight adjustment parameters to obtain the final weight of each retrieval strategy; and according to the final weight of each retrieval strategy, sorting the retrieval results of each retrieval strategy to obtain a final retrieval result. According to the method, the weights of full-text retrieval, vectorization retrieval and graph database retrieval are dynamically adjusted according to semantic features of user retrieval words through retrieval strategy weight adjustment parameters accurately obtained by using a semantic judgment model, and it is ensured that optimal retrieval results can be obtained in different query scenes.

The invention provides a behavior scheme determination method based on a large model, and relates to the technical field of artificial intelligence, in particular to the technical fields of computer vision, deep learning, large models and the like. According to the specific implementation scheme, a hybrid expert model is called based on features of multi-modal data, the hybrid expert model comprises a plurality of first large models for processing different modal data, and the features represent search words for performing in-library search on the first large models; inputting the multi-modal data into a hybrid expert model, and performing information extraction on each modal data to obtain text data, the text data including behavior information; inputting the text data into a second large model to obtain behavior content, and selecting and calling the second large model based on the category of the behavior information; and determining a behavior scheme by using the behavior content. The invention further provides a behavior scheme determination device based on the large model, electronic equipment and a storage medium.

Disclosed herein are a system, method, and computer program product embodiments for retrieving and ranking knowledge resources relevant to a query from knowledge base(s). For example, a query for resources from knowledge base(s) may be received. Based on the query, a first set of candidate resources are obtained from the knowledge base(s) having a lexical similarity to the query search terms, and a second set of candidate resources are obtained from the knowledge base(s) having a semantical similarity to the search terms. For each of the first and second sets of candidate resources, a confidence level indicating the relevance of the candidate resource to the query is determined. The sets of candidate resources are ranked based on at least the confidence levels to generate a ranked list of candidate resources. A query response comprising at least a subset of the ranked list candidate resources is provided to a GUI.

Systems, methods, devices, and computer readable storage media described herein provide techniques for intelligently interpreting and / or responding to search queries. In an aspect, a search query comprising a search term is received. A generative artificial intelligence (AI) model is utilized to generate a question based on the search term. Data semantically similar to the question is identified. The generative AI model is used to determine an answer to the question based on the question and the identified data. In a further aspect, a question-answer pair comprising the question and answer is generated. In an alternative further aspect, the answer is caused to be presented in a graphic user interface corresponding to a search engine. In a further aspect, the answer is determined during an active session with the search engine. In a further aspect, the search term and the question-answer pair are stored in a key-value store.

The invention relates to the technical field of artificial intelligence, and provides a search method and device, electronic equipment and a readable storage medium. The method comprises the following steps: acquiring a search term for searching; matching the search terms through a preset database to obtain an initial matching result; obtaining a target search term according to the search term and the initial matching result, and performing semantic extension on the target search term to obtain at least one extended search term; searching by utilizing a target search term and at least one extended search term to obtain a first search result corresponding to the target search term and a second search result corresponding to the at least one extended search term; and determining a target search result corresponding to the search term according to the first search result and the second search result. Through initial semantic matching, semantic extension and comprehensive analysis, a more accurate and comprehensive search result meeting the search intention of the user can be provided for the user.

Embodiment of the disclosure relates to a method, apparatus, device, and storage medium for media item generation. The method provided herein includes: displaying a item search page comprising a search control, the item search page being configured to provide an item search result corresponding to received input information; receiving a search term inputted in the search control; providing, in the item search page, a generation entry in association with the search control; and based on a selection of the generation entry, displaying, in the item search page, a set of media items generated based on the search term. In this way, the embodiments of the disclosure may provide users with more diversified media items to meet user specific needs for media items.

Methods, systems, and devices are disclosed for adjusting an image such that its vector representation more closely aligns with the vector representation of one or more intended search terms, and less closely aligns with the vector representation of one or more non-intended search terms. The method includes accessing an image and the intended and non-intended search terms. The image is iteratively adjusted using a machine learning system operating using a loss function that rewards adjustments resulting in an increase in the similarity score of the intended search terms, and penalizes adjustments resulting in an increase in the similarity score of the non-intended search terms. The loss function also penalizes increases in the perceptual loss between the input image and the adjusted image. The adjusted image may be uploaded to a sharing platform to improve the accuracy of search and organization of the adjusted image.

The embodiment of the invention provides an entity search result display method and device, an entity search result generation method and device, equipment and a medium. The entity search result display method comprises the steps that in response to a search operation of a current user for a target search term, a first search result corresponding to the target search term is obtained from a server, and the target search term is a search term for an entity object; the first search result is displayed in a result display area of a search result page, the first search result comprises at least one sub-search result, different sub-search results correspond to different target search requirements, and the target search requirements are search requirements of a current user. Different sub-search results are displayed in different sub-display areas of the result display area according to the demand intensity of the corresponding target search demand. According to the embodiment of the invention, by adopting the technical scheme, the accuracy and practicability of the displayed search result can be improved.

The embodiment of the invention provides an interface interaction method, device and equipment and a computer readable storage medium. The method comprises the following steps: presenting an information flow viewing interface; and in the viewing interface, presenting content items associated with the map, the content items including a plurality of content cards displayed on the map, the plurality of content cards corresponding to a plurality of points of interest determined based on the preset search term, and the content cards displaying description information corresponding to the points of interest.

Systems and methods include receipt of search terms, determination of an embedding for each of the search terms, generation of a composite embedding based on the determined embeddings, determination of similarities between the composite embedding and second composite embeddings associated with each of a plurality of hierarchical group codes, determination of a hierarchical group code of the plurality of hierarchical group codes based on the determined similarities, and generation of search results based on the search terms and the hierarchical group code.

Described are systems and processes for identifying relevant media content for users in response to natural language requests. The media content may be formed as a playlist of music. Requests may be sent to various models to obtain results, such as a large language model (LLM) and a local search model. Results may be selected from one or both models. The results may be used to fetch media content and provide user interfaces with a playlist with the media content to a user that submitted the request. User interfaces may include selectable search terms suggested for the user and animations during processing of the request.

Disclosed embodiments include computer-implemented methods and systems that can efficiently generate highly relevant recommended search terms to clinicians. A hybrid collaborative filtering model recommends search terms for a specific patient to the clinician. The model draws on information from patients' clinical encounters and the searches that were performed during the clinical encounters. To generate recommendations, the model uses search terms which are (1) frequently co-occurring with the ICD codes recorded for the patient and (2) highly relevant to the most recent search terms. One variation of the model uses only the most recent ICD codes assigned to the patient. Another variation uses all ICD codes. Comprehensive experiments of embodiments of the methods and systems have demonstrate high levels of performance.

The invention relates to a memory retrieval method, a memory generation method and related devices. The method comprises the following steps: acquiring an input search word, and translating the input search word into a search word of a target language; performing memory retrieval by using the input retrieval word and the retrieval word of the target language according to the memory index to obtain a retrieval result; wherein the memory index is established according to at least one of an original and a copy of the memory information; the copy is obtained by translating the original into a target language. The method can match and support multiple languages.

The invention discloses a search result generation method and device, equipment and a storage medium, which are used for improving the accuracy of abstract calculation. The method comprises the following steps: obtaining at least one webpage corresponding to a search term; generating a first text corresponding to the search term, wherein the first text is a text associated with the search term; for each webpage, extracting the abstract of the webpage from the text of the webpage according to the search word and the first text; and generating a search result of the search term according to the abstract of the webpage. According to the method, the first text is obtained on the basis of the search word, extension of the search word is achieved, the search word is more complete, the abstract is jointly determined on the basis of the search word and the first text, and the problem that the abstract effect is poor when the search word is incomplete or the search word has the question and answer intention is solved; the key words corresponding to the search terms in the abstract and the key words corresponding to the first text can be displayed emphatically, so that a user can intuitively know the search result.

The invention provides a search result recommendation method and equipment, which are used for improving the search performance of electronic equipment and improving the use experience of a user on a search function of the electronic equipment. According to the method, the electronic equipment detects and responds to a search instruction of a user, and a search word can be obtained; the electronic equipment can obtain at least one piece of equipment use information; based on the obtained search term and the equipment use information, the electronic equipment can provide a search result matched with the equipment use information of the electronic equipment, and the provided search result can be obtained after screening and / or sorting. Therefore, the search result provided by the electronic equipment can fit the use habit of the user or can be matched with the use state of the electronic equipment, so that the use experience of the user can be improved.

Visual search query intent extraction and search refinement is described. In one or more implementations, a visual search query system receives a search query for items listed on an online marketplace, the search query including an image. Using one or more machine learning models, the visual search query system analyzes the image to determine characteristics of an object in the image. Based on the characteristics of the object in the image, the visual search query system automatically generates one or more search terms and searches the online marketplace to locate items matching the one or more search terms. The visual search query system then displays visual indications of the located items matching the one or more search terms in a user interface of the online marketplace.

A multimodal search system is described. The system can receive image data captured by a camera of a user device. Additionally, the system can receive audio data associated with the image data. The audio data can be captured by a microphone of the user device. Moreover, the system can process the image data to generate visual features. Furthermore, the system can process the audio data to generate a plurality of words. The system can generate a plurality of search terms based on the plurality of words and the visual features. Subsequently, the system can determine one or more search results associated with the plurality of search terms and provide the one or more search results as an output.

An electronic device may comprise displays, at least one processor, and memories storing instructions. The instructions may, when executed by at least one processor, cause the electronic device to: display, on at least a portion of the display, a search window configured to receive a text input; enable the electronic device to receive a text input via the search window; identify whether the text includes a character string representing a function and / or instruction of the electronic device; and display a user interface, including a selectable object for changing the settings for a function of the electronic device corresponding to the character string, on at least a portion of the display in response to the identification of the character string.

The embodiment of the invention provides an article page generation method and device, a storage medium and a program product. In the embodiment of the invention, the user can search the search result item which is issued by the target platform and points to the first target article page based on the search word, and jump to the first target article page based on the search result item which points to the first target article page. Furthermore, the first target article comprises a plurality of display areas, the first area displays multi-modal article content which is related to the search terms and generated by an AI multi-modal generation model based on artificial intelligence, and a knowledge plaza page can be entered through entry information of the second area. And the user can continue to view any article page under any category of information through the knowledge square page. The user can view more related article pages through the searched article page, so that the page structure can provide more abundant related information which the user is interested in for the user, the information requirement of the user is met, and the flow of the user is attracted.

1. The name of the design product: input area and display area of information search graphical user interface of electronic device. 2. The use of the design product: an electronic device. 3. The design points of the design product: the partial graphical user interface of the electronic device. 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 information search. The partial graphical user interface protected by the design is used to input search instructions and display recommended search instructions and generated answer results. 7. The human-computer interaction mode of the graphical user interface: in response to the user inputting search keywords in the input bar of the design 1 front view, the graphical user interface changes from the design 1 front view to the design 1 change state view 1 to display the associated recommended search terms; in response to the user inputting search instructions in the input bar of the design 1 change state view 1, the graphical user interface changes from the design 1 change state view 1 to the design 1 change state view 2 to display the generated answer results for the instructions. In response to the user inputting search instructions in the input bar of the design 2 front view, the graphical user interface changes from the design 2 front view to the design 2 change state view to display the generated answer results for the instructions. In response to the user inputting search keywords in the input bar of the design 3 front view, the graphical user interface changes from the design 3 front view to the design 3 change state view 1 to display the associated recommended search terms; in response to the user inputting search instructions in the input bar of the design 3 change state view 1, the graphical user interface changes from the design 3 change state view 1 to the design 3 change state view 2 to display the generated answer results for the instructions. In response to the user inputting search instructions in the input bar of the design 4 front view, the graphical user interface changes from the design 4 front view to the design 4 change state view to display the generated answer results for the instructions. 8. Other circumstances that need to be explained: the part of the graphical user interface shown by the dashed line in each view of designs 1 to 4 does not constitute the part protected by the design.

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 present invention discloses an industry entity recognition method, device, storage medium and electronic device, the method comprising: obtaining a target search term, recognizing the target search term, determining a primary font size recognition result in the target search term, extracting the last preset digits of the primary font size recognition result as a target entity, querying the target entity to determine company information associated with the target entity, the company information including business scope information, and when the business scope information includes the target entity, marking the target entity as an industry entity. The industry entity recognition method, device, storage medium and electronic device provided by the present invention can more accurately identify industry entity information in the search content, and effectively improve the recognition accuracy of entity categories.

The invention relates to an audio and video platform searching method, an audio and video platform and a computer program product. The method comprises the following steps: analyzing a retrieval condition input by a user, and extracting each retrieval word in the retrieval condition; determining a retrieval priority corresponding to each retrieval word; searching is conducted from the lowest searching priority according to the searching words corresponding to the searching priorities and a preset searching strategy, if a result is not searched, the searching priorities are sequentially improved according to the sequence of the searching priorities, and searching is conducted according to the searching words corresponding to the improved searching priorities and the preset searching strategy; if a result is retrieved, the retrieval result is fed back to the user, and retrieval is ended; and if the result is not retrieved and the retrieval priority reaches the highest level, the retrieval is ended. According to the video and audio platform searching method provided by the invention, the user experience is optimized and the operation cost of the user is reduced through a link of condition priority definition, hierarchical relaxation and semantic understanding.

The invention provides a web3.0-based distributed database recommendation algorithm implementation method, provides a keyword encoding method, and improves the speed of a recommendation algorithm in a manner of combining a Chinese dictionary with a Hash table. The method for calculating the matching degree between the keyword and the search term is provided, and after the matching degree is calculated, a file corresponding to the keyword with the highest matching degree is recommended to a user; a multi-search-term matching method is provided, and a file corresponding to a keyword with the highest matching degree is recommended to a user by calculating the comprehensive matching degree among multiple search terms; the invention provides a data searching method of a node database, which supports dynamic addition and deletion of nodes. According to the keyword searching method, dynamic keyword adding is supported in the searching process, and when the keywords are dynamically added, the keywords can be dynamically matched with the added keywords; according to the method, the keywords are quickly matched in the form of the data table, so that the search speed of the keywords is increased; according to the method, dynamic login and logout of the target database are supported, and the availability of the database is ensured; the invention provides a method for simultaneously acquiring a file list corresponding to a keyword online by a plurality of servers.

Structured data comprising primary data is transformed into object-based data comprising the primary data and at least one search function. The object-based data when loaded into memory provides the search function as executable instructions for an object instance. When an application calls the object instance with search terms as input, the search terms are located within the primary data (which is loaded into memory) by the search function, and the object instance returns corresponding field values from the primary data associated with the search terms to the application.

The present application relates to the technical field of computer information retrieval, and particularly relates to a digital publishing platform supplementary character retrieval method and system, the present application provides a kind of digital publishing platform supplementary character retrieval method and system, retrieve function is called out by user end, supplementary character feature is matched with supplementary character database, corresponding glyph is extracted according to matching data, after obtaining search term, the search term data uploaded to central server is processed by indexing word division data in supplementary character database and preset algorithm based on supplementary character, key word full-text retrieval is carried out by word division, and the search result is displayed in user end, solve the supplementary character of prior art and can only be expressed by screenshot form, picture is difficult to form effective index, cannot be directly added to full-text retrieval engine, leading to related digital publishing application cannot be based on supplementary character to realize key word retrieval, pinyin, initial letter retrieval and other problems.

The present invention relates to a method for converting expression retrieval into Elasticsearch search statements, wherein the retrieval expression used in the expression retrieval consists of a search term and a logical operator, the retrieval expression is submitted to a retrieval system, the retrieval system parses the retrieval expression into a retrieval command that can be recognized and executed by the search engine, and then submits it to the open source search engine Elasticsearch to obtain the desired retrieval results, the method specifically includes two links: designing an expression and designing a conversion algorithm, in the designing expression link, the fields used are listed, and the priorities of simple retrieval expression symbols, retrieval expression combiners and retrieval expression symbols are defined respectively; in the designing conversion algorithm link, the retrieval expression is converted into a suffix expression operation and the retrieval expression suffix expression is calculated to obtain the converted Elasticsearch search statement. The method of the present invention improves the expression parsing capability of the retrieval system, can support expressions of varying complexity, and cooperates with the formulation and success of retrieval strategies.