311 results about "Word group" patented technology

The invention relates to the technical field of digital data processing, in particular to an intelligent triage and guide analysis method, device and system based on a large language model.The method comprises the steps that symptom information of a patient is collected in a text input or voice input mode, and the symptom information and patient identity information are associated; cleaning the collected symptom information and extracting a symptom keyword group; matching the extracted symptom keywords with data in a knowledge graph to determine a to-be-selected disease group; generating a corresponding recommended department table according to the to-be-selected disease group, and arranging the departments according to the priority; and correcting the arrangement sequence of the departments based on the historical treatment records of the patients. Through the steps, the symptom information of the patient can be efficiently collected and processed, and accurate and personalized medical suggestions can be provided. According to the method, the efficiency and the quality of medical services are greatly improved, and meanwhile, the medical experience of the patient is also improved.

The invention relates to a visual-language model cue word evolution generation method based on a genetic algorithm, which comprises the following steps of: randomly generating different cue words under a target task to construct an initial cue word set, preprocessing the randomly generated cue words, and reserving N groups of cue words as an initial population; and designing a multi-dimensional fitness evaluation function to evaluate the performance quality of each group of cue words in a vision-language task, and selecting high-quality cue word individuals based on an elitism strategy. Performing crossover and mutation operation on the selected high-quality cue word individuals by referring to a genetic algorithm to generate a new-generation cue word population; and finally, carrying out iterative optimization for multiple times until a preset termination condition is met, and outputting an optimal cue word set. By the adoption of the visual-language model cue word evolution generation method based on the genetic algorithm, high-quality and diversified cue words can be automatically generated, the performance of a visual-language model is remarkably improved, and meanwhile the visual-language model cue word evolution generation method has good interpretability and adaptability.

The invention relates to the technical field of speech recognition, in particular to a man-machine interaction method and system for speech recognition, and the method comprises the steps: obtaining the frequency spectrum information of a user speech segment, generating a speech spectrogram, constructing a speech library of a user, and carrying out the word segmentation processing, thereby obtaining a sequence of word units; dividing word groups by using a clustering algorithm, and calculating a segmentation coefficient and a stop coefficient of each word group according to a mapping function of an upper envelope line and a lower envelope line of the spectrogram so as to determine an optimal clustering result; real-time input voice segments are compared with reference word groups, and a user confirmation coefficient between the spectrogram of the real-time word groups and the spectrogram of the reference word groups is calculated; and judging whether the real-time input voice segment and the reference voice segment are the same user or not according to the user confirmation coefficient, and completing the human-computer interaction process of voice recognition. According to the method, the user voice library is constructed, and the spectrogram analysis and clustering algorithm is utilized, so that efficient voice recognition and user confirmation are realized, and the user interaction experience is improved.

The invention discloses an intelligent volume adjusting method and system based on environment sound, and the method is applied to a wireless earphone, and comprises the steps: determining a target prompt word according to an initial prompt word registration form submitted by a user; environment sound sampling data collected by wireless earphones are divided into environment noise data and human voice data, and the wireless earphones comprise a left earphone worn on a left ear and a right earphone worn on a right ear; dividing the human voice data into a plurality of groups of character voice data in one-to-one correspondence with the plurality of groups of characters according to voice features in the human voice data; determining target character sound data corresponding to the phrase whose similarity with the target prompt word is greater than a preset threshold value when identifying that the phrase whose similarity with the target prompt word is greater than the preset threshold value exists in the plurality of groups of character sound data; determining the orientation of human voice data corresponding to the target human voice data; and reducing the volume of the left earphone or the right earphone according to the orientation. According to the invention, the use convenience of the wireless earphone is improved.

The invention relates to the technical field of natural language processing, in particular to a dynamic intention chain modeling and causal cleaning method and system under a multi-round dialogue scene. According to the method, through multi-round dialogue data collection and preprocessing, one-hot codes are allocated to each sub-word or word group, intention recognition and sequence modeling are carried out based on the codes, and the intention of the user can be accurately recognized; quick mapping for directly obtaining user intentions from voice input data by skipping text data conversion is established, so that the intention recognition efficiency is improved; according to the method, the causal relationship graph is constructed based on the user intention sequence, the Bayesian network is utilized to perform causal modeling, the causal relationship between intentions is derived, and the probability of reasoning the next intention through the previous intention is calculated, so that the next intention of the user and the interactive operation to be executed are accurately reasoned; and collecting user feedback data to calculate a satisfaction score, and correcting the priority ranking rule of the rule engine based on the score.

The embodiment of the invention discloses a physical examination report standardized storage method and device, electronic equipment and a medium. A specific embodiment of the method comprises the following steps: carrying out image enhancement processing on an obtained user physical examination report image set, and then carrying out physical examination item classification processing to obtain a first physical examination item report image set and a second physical examination item report image set; generating an image detection text information set; performing image text recognition on the user physical examination text region image set to obtain a physical examination report text recognition information set; performing text calibration on the physical examination report text identification information set to obtain a physical examination report text calibration information set; generating a report standardized prompt word group set; performing content extraction on the physical examination report text calibration information set to obtain a report extraction information set; and matching and storing the report extraction information set to a user physical examination report storage system. According to the embodiment, the extraction accuracy and effect of the physical examination report information can be improved, the extraction time is shortened, and waste of storage resources is reduced.

Gender bias assessment techniques that are available currently only consider two genders viz male and female and is not inclusive of lesbian, gay, bisexual, transgender and queer (LGBTQ) genders. Present disclosure provides method and system for assessing gender fairness of large language models (LLM). The system first receive context aware prompt comprising context and prompt and then converts names present in the context using name anonymization technique. The system then convert many-to-many pronouns present in no-name-context into many to one pronouns which are then used to create counterfactual context for each gender pronoun group. Thereafter, system queries LLM with counterfactual prompt created using counterfactual context to obtain counterfactual response which is then used to create embedding data frame. Further, system trains Gaussian Mixture Model using embedding data frame which is then utilized to calculate cluster distances. Finally, system assess gender bias based on cluster distances and predefined distance threshold.

The invention belongs to the technical field of data mining, and particularly relates to a social media data mining method based on user behavior analysis. The method comprises the following steps: collecting user multi-source behavior data in real time, analyzing unstructured data through natural language processing, extracting key phrases and mapping the key phrases to structured fields; after abnormal data is removed through data cleaning, a behavior sequence is constructed in a time window, a time perception embedded vector is introduced to generate time sequence feature representation, and meanwhile, BERT is utilized to extract behavior content semantic vectors, and features such as behavior types and strength are fused to generate uniform content representation vectors; and finally, fusing the two types of features through a BiGRU-Attention network, and predicting a future behavior probability value of the user to drive personalized recommendation. According to the method, the problems of insufficient behavior semantic motivation capture, difficulty in data isomerism processing, weak dynamic modeling capability and the like in the prior art are solved, and the social media data mining precision is improved.

The invention relates to the technical field of legal consultation services, in particular to an intelligent question and answer matching method based on machine learning, which comprises the following steps of: acquiring legal consultation text recognition subject behavior objects and articles, analyzing and carding statement logic in sections, generating a semantic hierarchical table, extracting key phrases and integrating semantic units, and constructing a semantic network to generate a mapping table. Comparing question answer semantic logic to generate a matching corresponding set, reviewing offset revised text to generate a revised set, and rechecking consistency arrangement to generate an intelligent matching result set. According to the method, legal text logic relations are analyzed and processed through semantic layering, question and answer matching precision is optimized, keyword extraction and semantic network construction are combined, semantic consistency recognition and matching flexibility is enhanced, semantic offset and logic inconsistency are corrected, result connection coherence is ensured, mismatching is reduced compared with the prior art, question and answer accuracy is improved, and the method is suitable for popularization and application. Legal consultation is more intelligent and accurate, and a reliable matching result is provided.

The invention relates to an interaction method and device, electronic equipment and a storage medium, and the method comprises the steps: receiving a first reference image, and displaying the identification information of the received first reference image in a guide language input region; the number of the first reference images is multiple; receiving a text cue word, and displaying the text cue word in the guide word input area; the text cue word comprises an object description word group, and the object description word group corresponds to the first reference image; the object description phrases are used for describing objects in the first reference image corresponding to the object description phrases; the identification information of the first reference image is interspersed in the text cue word; the number of characters between the position of the object description phrase in the text cue word and the position of the identification information of the first reference image corresponding to the object description phrase in the text cue word is less than a preset number of characters; a first video is generated based on the content in the guide language input area. The demand that a user hopes to generate a video based on a plurality of first reference images can be met.

A mobile computing device can be configured, with an improved user interface, to synchronously play audio (or video) and text associated thereto, such as text stored in a synchronization index. Using the synchronization index, the device can periodically compare the current track time with that time associated to a word or range of words, such as a line (or segment) in a plurality of lines of text (or segments of text). Improved navigability of content using an improved mobile computing device and user interface is provided, because a user of the device can scroll through the lines of text associated with the audio or video to find a target word or range of words. If the user selects a particular word or range of words, by making a gesture on the mobile computing device, the device can identify a start time for the selected text. The device can then play the audio or video at the identified start time of the selected text. The improved user interface is a practical application for navigating audio (or video) and text associated thereto on a mobile computing device, providing bimodal reading on mobile computing devices and ease of navigability.

The invention relates to a power document intelligent writing method and system based on an extraction and generation hybrid model, and the method comprises the following steps: S1, carrying out the preprocessing of key phrases or short sentences which are inputted by a user and need to generate a document, then carrying out the discrimination of sentences in documents of related official documents and reports through a BGA extraction type sub-module in a state grid power brilliance large model, and carrying out the recognition of the sentences in the documents of related official documents and reports; extracting sentences which are highly matched with key information input by a user and have a threshold value to form a candidate sentence set; s2, according to the candidate sentence set, obtaining related background knowledge from a power time sequence knowledge graph by using a state grid power brightness large model KG-PGN deep learning network; and S3, according to the candidate sentence set and the related background knowledge, completing automatic document generation through a Transform encoder in the state grid electric power bright large model, and checking generated vocabularies during decoding in combination with a cover tool provided by the bright large model to avoid repeated generation of the same vocabularies. According to the method, the automation and intelligence level of power document generation is greatly improved.

The invention discloses a semantic prompt automatic labeling method in a building construction scene, and relates to the technical field of intelligent construction, and the method comprises the steps: collecting a construction plan, on-site surveying and mapping data and real-time environment information, dividing a construction site into construction operation units, and extracting task features to generate a task priority coefficient Kt and a scene state vector Ei; calculating a semantic prompt priority index SPI based on Kt and Ei, sorting prompt words, and mapping the prompt words into feature vectors through BERT; extracting image global features by using a visual model, performing weighted fusion on the image global features and semantic prompt features, and outputting a detection region set; through comparative analysis of a semantic consistency coefficient Ssem and a threshold value Qsc, optimal prompt phrases are optimized and combined to generate a multi-granularity labeling structure; and calculating a semantic anomaly coefficient SAI by adopting cross-modal cosine similarity, comparing the semantic anomaly coefficient SAI with a threshold value Qsai to judge whether the annotation is abnormal or not, and realizing anomaly correction, history comparison and responsibility judgment by recording and tracking the whole process of the annotation link.

The embodiment of the invention discloses a data processing method and device based on a large language model. According to the method, a to-be-scored question group is obtained, the to-be-scored question group comprises questions, answers of answering parties and reference answers, and according to the to-be-scored question group and key words, a prompt template, a false question generation prompt template and an evaluation generation prompt template are extracted, respectively constructing a keyword extraction prompt statement, a pseudo question generation prompt statement and an evaluation generation prompt statement, respectively inputting the constructed statements into a large language model to obtain corresponding keyword groups, question groups and global evaluation, determining text similarity of answers of answering parties and reference answers, and determining the similarity of the answers of the answering parties and the reference answers; and inputting the keyword group, the question group, the global evaluation and the text similarity into a pre-trained comprehensive scoring model to obtain a score corresponding to the answer of the answering party. According to the method, the advantages of the large language model and the comprehensive scoring model are combined, the generalization generation capability of the large language model is exerted, and the vertical domain scene learning capability of the comprehensive scoring model is utilized.

The invention discloses a key value cache sharing method and device for a large language model, equipment and a product. The method comprises the steps that request content input to the large language model by a first user is acquired; determining a first segmented word group corresponding to a first part of a shared key value cache of the large language model in the request content, wherein the shared key value cache of the large language model does not have a matched key value; determining an attention score between every two segmented words in the first segmented word group to obtain an attention matrix, determining at least one second segmented word group based on the attention matrix and the first segmented word group, and adding a corresponding key value to a shared key value cache; wherein the attention score between the segmented words in the second segmented word group is greater than the attention score between the segmented words in the second segmented word group and the segmented words outside the second segmented word group. Continuous updating of the shared key value cache is realized, and the hit rate and the utilization rate of the cache key value are remarkably improved.

The invention belongs to the technical field of artificial intelligence, and particularly relates to an emergency perception method containing semantic extraction, which comprises the following steps of: S1, constructing a historical word library about emergencies, and forming an association weight between a vocabulary group and a user through historical data training; s2, constructing an entity variant word expansion model based on a double-layer model to realize generation of a variant word bank, wherein the double-layer model comprises a proper noun expansion layer and a historical word bank expansion layer; s3, collecting text data on a network, performing classification processing on the text data based on a text classification rule, and preliminarily extracting entity words; s4, inputting the extracted entity words into the variant word expansion model to obtain a corresponding variant word group, and completing identification and extraction of the entity words; and S5, carrying out situation analysis based on the knowledge graph, and predicting the occurrence and development situation of the emergencies. According to the method, the variant word bank suitable for the whole network is mined on the basis of the incidence relation of different users to different similar words, and the reliability of vocabulary expansion is improved.

The application discloses a character input method and device, electronic equipment and a storage medium, and belongs to the technical field of electronic equipment. The method comprises the following steps: receiving a first input for inputting a word group pinyin in an input method keyboard; in response to the first input, displaying at least one word group unit corresponding to the word group pinyin, each word group unit comprising at least one candidate word; in response to a second input for selecting a target word group unit from the at least one word group unit, displaying the target word group unit in a text input area corresponding to the input method keyboard.

The invention relates to the technical field of semantic processing, in particular to a government affair service hotline platform data government and analysis method based on big data. The method comprises the following steps: firstly, acquiring communication phrases of historical call data, and screening emphasized phrases and possible appeal phrases from the communication phrases; further matching the emphasis phrases of different calls based on the similarity between the emphasis phrases in any two pieces of historical call data; further according to the consistency of the use differences among all the matched emphasized phrases, obtaining an objective consistency coefficient and classifying all the historical call data; and finally, in any kind of historical call data, according to the similarity between the possible appeal phrases, in combination with the distribution of the possible appeal phrases, screening out the appeal phrases and recording the appeal phrases as demand tags, thereby effectively solving the technical problems of inaccurate classification of user demand tags and large data mining deviation in the prior art.

The invention discloses a hard tag text adversarial attack sample generation method, which belongs to the technical field of text adversarial sample generation, and comprises the following steps: determining a text adversarial sample target; binary phrases are constructed for the original samples, and initial confrontation samples are generated by preferentially replacing the binary phrases; replacing unnecessary synonyms with original words; searching synonym iteration replacement optimization confrontation samples by determining transition replacement words; according to the hard tag text adversarial attack sample generation method, in an adversarial sample initialization stage, firstly, a high-frequency binary phrase is replaced to improve the quality of a generated initial adversarial sample; in the confrontation sample optimization stage, a relatively simple and effective mode is adopted to carry out iterative optimization, a generative method is not adopted any more, consumption of too much query times is avoided, the quality and efficiency of generating the confrontation sample are improved, the quality of the confrontation sample is remarkably improved in an attack scene closer to reality, and meanwhile, the query cost is reduced. And the query cost is reduced while the generation quality of the adversarial sample is improved.

The invention discloses an education evaluation method and system based on visual identification data analysis, and relates to the technical field of education analysis, and the method comprises the steps: presetting the understanding difficulty for each mapping node, and taking the understanding difficulty as a teaching path reference; performing semantic analysis on the explanation scheme, extracting knowledge points and secondary and supplementary key phrases, and associating the knowledge points and the secondary and supplementary key phrases to corresponding mapping nodes to realize content structuring; acquiring real-time classroom voice information, extracting and analyzing characters to determine real-time keywords, positioning corresponding nodes in the mind map, sequentially connecting the nodes to form a real-time map node sequence line, and capturing an actual explanation path; calculating student initial state evaluation, combining node difficulty correction to obtain final evaluation, and accumulating all student evaluation as a teaching effect; taking a preset explanation order line teaching effect corresponding to the real-time order line as a standard, determining the relative positioning of actual evaluation, and achieving deviation quantification; according to the invention, through multi-modal fusion and a dynamic order line mechanism, the real-time performance and accuracy of evaluation are improved, and teaching improvement guidance is provided.

The present application provides an AI-based text processing method, apparatus, computer device, and storage medium. The method obtains a comment dataset of a target object within a first period, then determines a target comment dataset from the comment dataset according to a target comment tag, generates a prompt message based on the comment texts of the individual comment data in the target comment dataset, and inputs the prompt message into a preset AIGC engine to output a reference comment text corresponding to the target comment tag. The prompt message not only includes a prompt statement for instructing the AIGC engine to generate a reference comment text, but also includes a text to be processed, which consists of keywords and keyword phrases and is directly related to the user's core concerns. This intelligent prompt message generation method helps the AIGC engine better understand the user's intention and generate high-quality reference comment texts.

The application discloses a keyword extraction method, system, device and storage medium. The method comprises the following steps: obtaining a sensitive word group list, removing stop words and splicing words in each sensitive word group, and obtaining preprocessed text; based on the preprocessed text, a word vector is constructed, and a mapping relationship between a word group in the preprocessed text and the splicing words is established; an initial cluster center vector is selected in the word vector, a Hamming distance between a remaining word vector and the initial cluster center vector is calculated, the word vector is divided into clusters according to the Hamming distance, and a preliminarily divided keyword cluster is obtained; based on the word vector and the preliminarily divided keyword cluster, an adaptive clustering algorithm is adopted to obtain a similar word vector cluster; and the similar word vector cluster is spliced with the splicing words according to the mapping relationship, so that a keyword list is generated; and it is ensured that the obtained keywords can accurately reflect the characteristics of the text content.

The invention relates to the technical field of classical Chinese teaching, and discloses a classical Chinese dismantling teaching method and system based on artificial intelligence assistance, and the method comprises the following steps: S1, obtaining a classical Chinese text to be teaching, carrying out the structural processing of the classical Chinese text, and dismantling the classical Chinese text into a plurality of dismantling units of different levels; s2, on the basis of preset teaching cognition parameters, performing cognition difficulty and teaching value evaluation on each disassembly unit, and generating corresponding disassembly unit difficulty identifiers and teaching weight information; according to the classical Chinese dismantling teaching method based on artificial intelligence assistance, classical Chinese texts are dismantled into dismantling units of different levels such as a word level, a phrase level, a syntactic level and a semantic level, and a classical Chinese understanding process is subjected to structured processing, so that classical Chinese learning is converted from result guidance to process guidance, and the classical Chinese learning efficiency is improved. Students can conveniently and systematically master the language law of classical Chinese, so that the classical Chinese understanding ability is improved.

The invention relates to the technical field of artificial intelligence, is suitable for the financial field and the medical health field, and provides a verbal skill generation method and device, equipment and a storage medium, and the method comprises the steps: obtaining a user input text of which a topic deviates from a business topic, and extracting a target word group from the user input text; determining a first response template text from a plurality of preset response template texts associated with different business themes; generating a second response template text based on the target word group and the first response template text; analyzing the user input text and the second response template by using a preset language model to generate a plurality of target lexical elements for responding to the user input text, and obtaining probability data corresponding to each target lexical element; and based on the multiple target lexical elements and the probability data corresponding to each target lexical element, generating a target response verbal skill used for guiding the topic to return to the business theme. The method can help an artificial intelligence customer service to naturally guide the dialogue to return to the business theme.

The present application discloses a text matching method, apparatus, device and storage medium, including: obtaining input text and resource data to be matched; performing word segmentation on the input text and resource data to be matched based on words in a system vocabulary to obtain a first keyword phrase corresponding to the input text and a second keyword phrase corresponding to the resource data to be matched; calculating the similarity between the first keyword phrase and the second keyword phrase, and determining the resource data corresponding to the input text from the resource data to be matched based on the similarity. The present application performs a word segmentation operation with a finer matching granularity on the input text and the resource data to be matched based on the system vocabulary to obtain the corresponding first keyword phrase and second keyword phrase, making the word segmentation result more accurate, and then determines the resource data in the resource data to be matched that matches the input text by calculating the similarity between the first keyword phrase and the second keyword phrase, thereby improving the text matching accuracy in lightweight scenarios.

It enables document proofreading tailored to individual tasks and documents. [Solution] The document proofreading device (document processing device 100) includes a dictionary generation unit 116 that creates a synonym acquisition prompt requesting a synonym group, which is a collection of documents containing one or more documents, with words grouped by synonym; an answer acquisition unit 118 that sends the synonym acquisition prompt to a language model server 210 and obtains the synonym group directly or indirectly from the language model server 210; and a document proofreading unit 117 that refers to the synonym group and creates a proofreading document acquisition prompt requesting a proofreading document that corrects variations in word notation in the documents included in the document collection. The answer acquisition unit 118 sends the proofreading document acquisition prompt to the language model server 210 and obtains the proofreading document directly or indirectly from the language model server 210.

The application relates to the computer technical field, and provides a keyword matching method, an electronic device cluster and a program product, and further provides a computer readable storage medium. The keyword matching method provided by the application is applied to an electronic device, and the method comprises the following steps: extracting all continuous words satisfying the length of index word groups from a to-be-matched text, and generating one or more to-be-retrieved word groups; performing secret processing on the one or more to-be-retrieved word groups, and generating one or more ciphertext retrieval word groups; matching the one or more ciphertext retrieval word groups with ciphertext index word groups; when there is a ciphertext retrieval word group matching a ciphertext index word group, obtaining one or more keyword lengths; extracting continuous words satisfying the one or more keyword lengths from the to-be-matched text, and generating one or more to-be-matched word groups; performing secret processing on the one or more to-be-matched word groups, and generating one or more ciphertext matching word groups; and matching the one or more ciphertext matching word groups with ciphertext keywords, and obtaining a matching result. According to the method of the first aspect, the data processing amount occupied by the matching operation can be effectively reduced, and the execution efficiency of the matching operation is improved.

The invention relates to a dialogue generation method and device, computer equipment, a storage medium and a program product, and the method comprises the steps: obtaining a plurality of target person feature words corresponding to the role description information of a digital person according to a preset person feature word library; combining the feature words set by each target person to obtain a plurality of feature word groups; matching the plurality of feature phrases with a preset dialogue scene library to determine a feature phrase set; under the condition that the current output dialogue is the first section dialogue, determining a first feature phrase; generating a current output dialogue based on the first feature phrase through a dialogue generation model; under the condition that the current output dialogue is any non-first-section dialogue, determining a second feature word group; and through the dialogue generation model, based on the second feature phrase and the output dialogue before the current output dialogue, the consistency of long-range dialogue role features is maintained.

This application discloses an input recommendation method, apparatus, electronic device, and storage medium. The method includes: acquiring an input pinyin string and determining the number of preset words matched by the pinyin string in a preset word library; if the number does not exceed a preset threshold, performing word grouping processing on the pinyin string based on the preset word library to obtain a candidate word set; inputting the pinyin string into a syllable segmentation network for syllable segmentation processing to obtain a predicted syllable sequence corresponding to the pinyin string, wherein the syllable segmentation network extracts features for syllable segmentation processing from the pinyin string based on a lightweight convolutional module; inputting the predicted syllable sequence into a word prediction network for word prediction to obtain a predicted word set; and outputting recommended words based on the candidate word set and the predicted word set. This application improves the accuracy and efficiency of input recommendation and is highly suitable for input method recommendation on low-resource devices (such as smartphones).