CN111341457B - Medical diagnosis information visualization method and device based on big data retrieval - Google Patents
Medical diagnosis information visualization method and device based on big data retrieval Download PDFInfo
- Publication number
- CN111341457B CN111341457B CN202010116976.0A CN202010116976A CN111341457B CN 111341457 B CN111341457 B CN 111341457B CN 202010116976 A CN202010116976 A CN 202010116976A CN 111341457 B CN111341457 B CN 111341457B
- Authority
- CN
- China
- Prior art keywords
- medical diagnosis
- information
- displayed
- index
- background server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 124
- 238000007794 visualization technique Methods 0.000 title claims abstract description 11
- 230000000007 visual effect Effects 0.000 claims abstract description 97
- 238000009877 rendering Methods 0.000 claims abstract description 63
- 238000012545 processing Methods 0.000 claims abstract description 50
- 238000000034 method Methods 0.000 claims abstract description 48
- 238000000605 extraction Methods 0.000 claims abstract description 39
- 238000004458 analytical method Methods 0.000 claims description 77
- 239000013598 vector Substances 0.000 claims description 46
- 238000004422 calculation algorithm Methods 0.000 claims description 36
- 238000004364 calculation method Methods 0.000 claims description 21
- 238000012216 screening Methods 0.000 claims description 14
- 238000012163 sequencing technique Methods 0.000 claims description 13
- 238000009825 accumulation Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 9
- 238000012800 visualization Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 238000003058 natural language processing Methods 0.000 description 27
- 239000011159 matrix material Substances 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 238000012935 Averaging Methods 0.000 description 2
- 206010020772 Hypertension Diseases 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000012634 fragment Substances 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 208000017667 Chronic Disease Diseases 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a medical diagnosis information visualization method and device based on big data retrieval, wherein the method comprises the following steps: the user terminal receives the inquiry text information input by the user, and the inquiry text information is uploaded to a background server based on an HTTPS protocol; the background server performs retrieval keyword extraction processing based on the received inquiry text information to obtain retrieval keywords; index searching is carried out on the medical diagnosis database by utilizing the search keywords, and medical diagnosis information searched by the index is ranked according to the relevance; performing visual feature determination on the sequenced medical diagnosis information on a background server to obtain determined visual features; performing rendering treatment to be displayed on the medical diagnosis information according to the determined visual characteristics to obtain rendering results to be displayed; and the background server loads the rendering result to be displayed to the user terminal for visual display. In the embodiment of the invention, the retrieval and visual display of the medical diagnosis information are realized.
Description
Technical Field
The invention relates to the technical field of medical big data visualization, in particular to a medical diagnosis information visualization method and device based on big data retrieval.
Background
In recent years, along with the continuous improvement of the living standard of people, people pay more and more attention to physical health, but the people have various chronic diseases such as hypertension, diabetes, hypertension and the like or general common diseases such as cold, fever and the like along with the trend of aging of domestic population; with the development of the Internet, online intelligent inquiry can be realized under the general condition, the traditional online intelligent inquiry is answered by online doctors, most of the online intelligent inquiry cannot be answered in real time, and how to quickly match medical diagnosis information according to the inquiry information input by a user through big data retrieval matching is realized and visualization is performed, so that online intelligent inquiry is realized quickly, and the use experience of the user is improved.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a medical diagnosis information visualization method and device based on big data retrieval, which can realize quick matching of medical diagnosis information and visualization through big data retrieval matching according to the inquiry information input by a user, thereby quickly realizing online intelligent inquiry and improving the use experience of the user.
In order to solve the technical problems, an embodiment of the present invention provides a medical diagnosis information visualization method based on big data retrieval, the method including:
the method comprises the steps that a user terminal receives inquiry text information input by a user and uploads the inquiry text information to a background server based on an HTTPS protocol;
The background server performs retrieval keyword extraction processing based on the received inquiry text information to obtain retrieval keywords;
index searching is carried out on the medical diagnosis database by utilizing the search keywords, and medical diagnosis information searched by the index is ranked according to the relevance;
Performing visual characteristic determination on the sequenced medical diagnosis information on the background server to obtain determined visual characteristics, wherein the visual characteristics comprise screen size, screen resolution and user expected display resolution of a user terminal for displaying the medical diagnosis information;
performing rendering treatment to be displayed on the medical diagnosis information according to the determined visual characteristics to obtain rendering results to be displayed;
And the background server loads the rendering result to be displayed to the user terminal for visual display.
Optionally, the background server performs a search keyword extraction process based on the received inquiry text information, to obtain a search keyword, including:
performing initial keyword extraction processing on the inquiry text information based on a keyword extraction algorithm to obtain initial keywords;
Carrying out semantic analysis processing on the inquiry text information based on an NLP analysis model to obtain a semantic analysis tag;
and screening and matching the initial keywords with the semantic analysis labels to obtain search keywords.
Optionally, the performing semantic analysis processing on the query text information based on the NLP analysis model to obtain a semantic analysis tag includes:
performing text feature vector list construction processing based on the inquiry text information to obtain a text feature vector list;
Inputting the text feature vector list into the NLP analysis model, and presetting a weight value of each text feature vector in the text feature vector list by using an N-Gram statistical language algorithm in the NLP analysis model;
And analyzing and processing the character feature vectors with preset weights through the NLP model, and outputting semantic analysis labels.
Optionally, the indexing searching on the medical diagnosis database by using the search keyword includes:
Clustering with the index key words in the medical diagnosis database by using the search key words as centers to obtain a clustering result;
performing Euclidean distance calculation based on the clustering result, and obtaining a final index keyword based on the Euclidean distance calculation result;
And constructing a keyword retrieval formula by utilizing the final index keywords, and carrying out index retrieval on the medical diagnosis database based on the constructed keyword retrieval formula.
Optionally, the sorting the medical diagnosis information retrieved by the index according to the relevance includes:
Acquiring index keyword information corresponding to each piece of medical diagnosis information;
Assigning a corresponding weight to the index key information based on the Euclidean distance calculation result;
and giving corresponding weights to the index key information for accumulation processing, and sequencing according to the accumulation result.
Optionally, the adding the corresponding weight by using the index keyword information includes:
And accumulating according to the corresponding weight value given by the index key words in each piece of medical diagnosis information.
Optionally, the determining the visual characteristic of the sequenced medical diagnosis information on the background server to obtain the determined visual characteristic includes:
the background server obtains the display characteristics of the user terminal based on the HTTPS protocol;
determining visual features of the ordered medical diagnosis information in the background server based on the display features, and obtaining determined visual features;
The display characteristics comprise the screen size of the user terminal for display and the display resolution set by the user;
The visual features include a screen size, a screen resolution, a user desired display resolution of a user terminal for displaying the medical diagnostic information.
Optionally, the rendering processing to be displayed is performed on the medical diagnosis information according to the determined visual characteristics, so as to obtain a rendering result to be displayed, including:
Mapping the data elements in the medical diagnosis information according to the determined visual characteristics to obtain a document frame to be displayed;
and carrying out rendering treatment to be displayed on the document frame to be displayed to obtain rendering results to be displayed.
Optionally, the background server loads the rendering result to be displayed to the user terminal for visual display, and the method includes:
and the background server loads the rendering results to be displayed to the user terminal according to the display sequence for visual display.
In addition, the embodiment of the invention also provides a medical diagnosis information visualization device based on big data retrieval, which comprises:
An input module: the method comprises the steps that a user terminal receives inquiry text information input by a user, and the inquiry text information is uploaded to a background server based on an HTTPS protocol;
Keyword extraction module: the background server is used for extracting the search keywords based on the received inquiry text information to obtain the search keywords;
index retrieval module: the index key words are used for index searching on the medical diagnosis database, and the medical diagnosis information searched by the index is ranked according to the relevance;
The visual characteristic determining module: the method comprises the steps that visual characteristics of ordered medical diagnosis information are determined on the background server, and the determined visual characteristics are obtained, wherein the visual characteristics comprise the screen size, the screen resolution and the user expected display resolution of a user terminal for displaying the medical diagnosis information;
And a rendering module to be displayed: the method comprises the steps of performing rendering processing to be displayed on medical diagnosis information according to determined visual characteristics to obtain rendering results to be displayed;
loading a visualization module: and the background server is used for loading the rendering result to be displayed to the user terminal for visual display.
In the embodiment of the invention, the inquiry text information input by a user is received and uploaded to a background server, the keyword is extracted, then index retrieval is carried out by using the extracted keyword, then sequencing is carried out, the sequencing result is rendered to be displayed according to the determined visual characteristics, and then the rendering result to be displayed is loaded to a user terminal for visual display; according to the method, the medical diagnosis information can be quickly matched and visualized through big data retrieval matching according to the inquiry information input by the user, so that online intelligent inquiry is quickly realized, and the use experience of the user is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings which are required in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a medical diagnostic information visualization method based on big data retrieval in an embodiment of the present invention;
Fig. 2 is a schematic structural diagram of a medical diagnosis information visualizing apparatus based on big data retrieval in the layout fee embodiment.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Examples
Referring to fig. 1, fig. 1 is a flow chart of a medical diagnosis information visualization method based on big data retrieval in an embodiment of the invention.
As shown in fig. 1, a medical diagnosis information visualization method based on big data retrieval, the method comprising:
S11: the method comprises the steps that a user terminal receives inquiry text information input by a user and uploads the inquiry text information to a background server based on an HTTPS protocol;
In the implementation process of the invention, a corresponding APP or applet or a PC application program and the like which can be connected with a background server are installed on a user terminal, a corresponding operation interface on the user terminal is provided with a corresponding inquiry information for receiving user input, after the inquiry information is received, the user terminal converts the inquiry information into inquiry text information through a corresponding algorithm, firstly, redundancy is removed on the inquiry information, generally, redundancy is removed in a mode based on grammar rules, and then inquiry text information is integrated in the inquiry information after redundancy is removed according to the input time sequence; after the user terminal obtains the inquiry text information, uploading the inquiry text information to a background server through an HTTPS protocol in the background server; through the mode, the inquiry information input by the user is correspondingly processed, subsequent processing is facilitated, the processing speed of subsequent steps is increased, and the safety and the transmission speed of text transmission are ensured through the HTTPS protocol.
S12: the background server performs retrieval keyword extraction processing based on the received inquiry text information to obtain retrieval keywords;
In the implementation process of the invention, the background server performs search keyword extraction processing based on the received inquiry text information to obtain search keywords, and the method comprises the following steps: performing initial keyword extraction processing on the inquiry text information based on a keyword extraction algorithm to obtain initial keywords; carrying out semantic analysis processing on the inquiry text information based on an NLP analysis model to obtain a semantic analysis tag; and screening and matching the initial keywords with the semantic analysis labels to obtain search keywords.
Further, the performing semantic analysis processing on the inquiry text information based on the NLP analysis model to obtain a semantic analysis tag includes: performing text feature vector list construction processing based on the inquiry text information to obtain a text feature vector list; inputting the text feature vector list into the NLP analysis model, and presetting a weight value of each text feature vector in the text feature vector list by using an N-Gram statistical language algorithm in the NLP analysis model; and analyzing and processing the character feature vectors with preset weights through the NLP model, and outputting semantic analysis labels.
Specifically, the keyword extraction algorithm is used for extracting the keyword from the inquiry text information to obtain an initial keyword, the keyword extraction algorithm used for extracting the keyword can be any one of a TF-IDF keyword extraction algorithm, a semantic-based statistical language model, a TF-IWF document keyword automatic extraction algorithm, a separation model-based text keyword extraction algorithm, a semantic-based Chinese text keyword extraction (SKE) extraction algorithm and a naive Bayesian model-based Chinese keyword extraction algorithm, and in the embodiment of the invention, the TF-IDF keyword extraction algorithm is preferentially used, and TF-IDF (term frequency-inverse document frequency) is a common weighting technology used for information retrieval and data mining; TF means Term Frequency (Term Frequency), IDF means inverse text Frequency index (Inverse Document Frequency); TF-IDF is a statistical method for evaluating the importance of a word to one of a set of documents or a corpus; the importance of a word increases proportionally with the number of times it appears in the file, but at the same time decreases inversely with the frequency with which it appears in the corpus; various forms of TF-IDF weighting are often applied by search engines as a measure or rating of the degree of correlation between documents and user queries; in addition to TF-IDF, search engines on the internet use a ranking method based on link analysis to determine the order in which files appear in the search results; after the initial keywords are extracted, carrying out semantic analysis on the inquiry text information by using an NLP analysis model, so that a semantic analysis tag is obtained through analysis; screening and matching are carried out by utilizing the initial keyword and the semantic analysis tag, so that a retrieval keyword is obtained; wherein, screening matching is carried out through similarity calculation during screening matching; the specific algorithm is as follows:
wherein S i,Sj is a set of initial keywords and a set of semantic analysis tags that are relatively close, t jh,tik is an initial keyword and a semantic analysis tag in the set S i,Sj, wup (t ik,tjh) is wup similarity between the initial keyword and the semantic analysis tag, max h(wup(tik,tjh)) is a maximum value of wup similarity between t jh and all the semantic analysis tags in S j, max k(wup(tjh,tik)) is a maximum value of wup similarity between t ik and all the initial keywords in S i, and size (S) represents the number of the set.
The method is used for constructing a position feature vector list by corresponding inquiry text information, and can accurately segment words and adjust the sequence after segmentation by combining a word bag model (BOF) in the field of natural language processing with N-Gram features. The bag of words model (BOF) is a standard target classification framework consisting of feature extraction, feature clustering, feature encoding, feature convergence and classifier classification 4 parts. The N-Gram feature is an algorithm based on a statistical language model, also called a first order Markov chain, and is to perform sliding window operation with the size of N on the content in the text according to bytes, so as to form a byte fragment sequence with the length of N. Each byte segment is called a gram, statistics is carried out on the occurrence frequency of all the grams, and filtering is carried out according to a preset threshold value to form a key gram list, namely a vector feature space of the text; each gram in the list is a feature vector dimension; firstly, carrying out rough segmentation processing on input criminal name field information; then performing Bi-gram cutting treatment; and finally, filtering to obtain a feature vector list.
The NLP analysis model architecture adopts an input, mapping (hiding) and output architecture, wherein X (1) to X (n) represent feature vectors of each word in a text, a paragraph can be represented by an average value after embedding and accumulating all words, and finally, a label of an output layer is obtained through nonlinear transformation of a hidden layer again; the model inputs a word sequence (a text or a sentence) and outputs probabilities that the word sequence belongs to different categories; the hidden layer is obtained by summing and averaging the input layers and multiplying the input layers by a weight matrix A; the output layer is obtained by multiplying the hidden layer by a weight matrix B; in order to improve the operation time and the running time, the model uses a hierarchical Softmax skill, and the label is encoded on the basis of the Hartmann encoding, so that the number of model prediction targets can be greatly reduced.
Specifically, the output layer is formed by multiplying the hidden layer by the weight matrix B as follows:
Wherein y n represents true label, x n represents feature vector list (N-Gram feature of document N after normalization), and A and B represent weight matrix respectively; n=1, 2,3, …, N being a positive integer.
Firstly, constructing text feature vectors of inquiry text information, inputting the constructed text feature vector list into an NLP analysis model, and carrying out weight presetting on each text feature vector in the text feature vector list by using an N-Gram statistical language algorithm in the NLP analysis model; and analyzing and processing the character feature vectors with preset weights through an NLP model, and outputting semantic analysis labels.
S13: index searching is carried out on the medical diagnosis database by utilizing the search keywords, and medical diagnosis information searched by the index is ranked according to the relevance;
in the implementation process of the invention, the index searching on the medical diagnosis database by using the search keyword comprises the following steps: clustering with the index key words in the medical diagnosis database by using the search key words as centers to obtain a clustering result; performing Euclidean distance calculation based on the clustering result, and obtaining a final index keyword based on the Euclidean distance calculation result; and constructing a keyword retrieval formula by utilizing the final index keywords, and carrying out index retrieval on the medical diagnosis database based on the constructed keyword retrieval formula.
Further, the sorting the medical diagnosis information retrieved by the index according to the relevance includes: acquiring index keyword information corresponding to each piece of medical diagnosis information; assigning a corresponding weight to the index key information based on the Euclidean distance calculation result; and giving corresponding weights to the index key information for accumulation processing, and sequencing according to the accumulation result.
Further, the adding the corresponding weight to the index key information includes: and accumulating according to the corresponding weight value given by the index key words in each piece of medical diagnosis information.
Specifically, clustering is performed by using the search key as a center and index keys in the medical diagnosis database, and k-means clustering is used in the embodiment of the invention, so that a clustering result with the search key as a center is obtained; then, calculating Euclidean distance by utilizing keywords in the clustering result, and determining a final index keyword according to the Euclidean distance obtained by calculation; and constructing a search formula applicable to the medical diagnosis database through the final index key words, and then carrying out index search on the medical diagnosis database by utilizing the search formula.
Firstly, obtaining multi-corresponding index keyword information in each piece of medical diagnosis information, calculating Euclidean distances among all index keywords, and giving corresponding weight to each index keyword through the Euclidean distances among the index keywords; finally, giving corresponding weight to the index key information corresponding to the plurality of pieces of medical diagnosis information for accumulation, and then sequencing according to the accumulated result; and accumulating according to the corresponding weight given by the index key words in each piece of medical diagnosis information.
S14: performing visual characteristic determination on the sequenced medical diagnosis information on the background server to obtain determined visual characteristics, wherein the visual characteristics comprise screen size, screen resolution and user expected display resolution of a user terminal for displaying the medical diagnosis information;
In the implementation process of the invention, the visual characteristic determination is performed on the sequenced medical diagnosis information on the background server to obtain the determined visual characteristic, which comprises the following steps: the background server obtains the display characteristics of the user terminal based on the HTTPS protocol; determining visual features of the ordered medical diagnosis information in the background server based on the display features, and obtaining determined visual features; the display characteristics comprise the screen size of the user terminal for display and the display resolution set by the user; the visual features include a screen size, a screen resolution, a user desired display resolution of a user terminal for displaying the medical diagnostic information.
Specifically, the display characteristics of the user terminal are obtained in the background server by utilizing an HTTPS protocol, wherein the display characteristics comprise the screen size of the user terminal for display and the display resolution set by a user; determining visual features of the sequenced medical diagnosis information in a background server according to the display features, and obtaining the determined visual features; in particular, the visual characteristics include a screen size, a screen resolution, a user desired display resolution of the user terminal for displaying the medical diagnosis information.
S15: performing rendering treatment to be displayed on the medical diagnosis information according to the determined visual characteristics to obtain rendering results to be displayed;
In the implementation process of the invention, the rendering processing to be displayed is carried out on the medical diagnosis information according to the determined visual characteristics to obtain the rendering result to be displayed, which comprises the following steps: mapping the data elements in the medical diagnosis information according to the determined visual characteristics to obtain a document frame to be displayed; and carrying out rendering treatment to be displayed on the document frame to be displayed to obtain rendering results to be displayed.
Specifically, mapping all data elements in the medical diagnosis information to be displayed according to the determined visual characteristics, so as to map the data elements to the corresponding document frames to obtain the document frames to be displayed; and finally, rendering the document frame to be displayed to obtain a rendering result to be displayed.
S16: and the background server loads the rendering result to be displayed to the user terminal for visual display.
In the implementation process of the invention, the background server loads the rendering result to be displayed to the user terminal for visual display, and the method comprises the following steps: and the background server loads the rendering results to be displayed to the user terminal according to the display sequence for visual display.
In the embodiment of the invention, the inquiry text information input by a user is received and uploaded to a background server, the keyword is extracted, then index retrieval is carried out by using the extracted keyword, then sequencing is carried out, the sequencing result is rendered to be displayed according to the determined visual characteristics, and then the rendering result to be displayed is loaded to a user terminal for visual display; according to the method, the medical diagnosis information can be quickly matched and visualized through big data retrieval matching according to the inquiry information input by the user, so that online intelligent inquiry is quickly realized, and the use experience of the user is improved.
Examples
Referring to fig. 2, fig. 2 is a schematic structural diagram of a medical diagnosis information visualizing apparatus based on big data retrieval in the layout fee embodiment.
As shown in fig. 2, a medical diagnosis information visualizing apparatus based on big data retrieval, the apparatus comprising:
The input module 21: the method comprises the steps that a user terminal receives inquiry text information input by a user, and the inquiry text information is uploaded to a background server based on an HTTPS protocol;
In the implementation process of the invention, a corresponding APP or applet or a PC application program and the like which can be connected with a background server are installed on a user terminal, a corresponding operation interface on the user terminal is provided with a corresponding inquiry information for receiving user input, after the inquiry information is received, the user terminal converts the inquiry information into inquiry text information through a corresponding algorithm, firstly, redundancy is removed on the inquiry information, generally, redundancy is removed in a mode based on grammar rules, and then inquiry text information is integrated in the inquiry information after redundancy is removed according to the input time sequence; after the user terminal obtains the inquiry text information, uploading the inquiry text information to a background server through an HTTPS protocol in the background server; through the mode, the inquiry information input by the user is correspondingly processed, subsequent processing is facilitated, the processing speed of subsequent steps is increased, and the safety and the transmission speed of text transmission are ensured through the HTTPS protocol.
Keyword extraction module 22: the background server is used for extracting the search keywords based on the received inquiry text information to obtain the search keywords;
In the implementation process of the invention, the background server performs search keyword extraction processing based on the received inquiry text information to obtain search keywords, and the method comprises the following steps: performing initial keyword extraction processing on the inquiry text information based on a keyword extraction algorithm to obtain initial keywords; carrying out semantic analysis processing on the inquiry text information based on an NLP analysis model to obtain a semantic analysis tag; and screening and matching the initial keywords with the semantic analysis labels to obtain search keywords.
Further, the performing semantic analysis processing on the inquiry text information based on the NLP analysis model to obtain a semantic analysis tag includes: performing text feature vector list construction processing based on the inquiry text information to obtain a text feature vector list; inputting the text feature vector list into the NLP analysis model, and presetting a weight value of each text feature vector in the text feature vector list by using an N-Gram statistical language algorithm in the NLP analysis model; and analyzing and processing the character feature vectors with preset weights through the NLP model, and outputting semantic analysis labels.
Specifically, the keyword extraction algorithm is used for extracting the keyword from the inquiry text information to obtain an initial keyword, the keyword extraction algorithm used for extracting the keyword can be any one of a TF-IDF keyword extraction algorithm, a semantic-based statistical language model, a TF-IWF document keyword automatic extraction algorithm, a separation model-based text keyword extraction algorithm, a semantic-based Chinese text keyword extraction (SKE) extraction algorithm and a naive Bayesian model-based Chinese keyword extraction algorithm, and in the embodiment of the invention, the TF-IDF keyword extraction algorithm is preferentially used, and TF-IDF (term frequency-inverse document frequency) is a common weighting technology used for information retrieval and data mining; TF means Term Frequency (Term Frequency), IDF means inverse text Frequency index (Inverse Document Frequency); TF-IDF is a statistical method for evaluating the importance of a word to one of a set of documents or a corpus; the importance of a word increases proportionally with the number of times it appears in the file, but at the same time decreases inversely with the frequency with which it appears in the corpus; various forms of TF-IDF weighting are often applied by search engines as a measure or rating of the degree of correlation between documents and user queries; in addition to TF-IDF, search engines on the internet use a ranking method based on link analysis to determine the order in which files appear in the search results; after the initial keywords are extracted, carrying out semantic analysis on the inquiry text information by using an NLP analysis model, so that a semantic analysis tag is obtained through analysis; screening and matching are carried out by utilizing the initial keyword and the semantic analysis tag, so that a retrieval keyword is obtained; wherein, screening matching is carried out through similarity calculation during screening matching; the specific algorithm is as follows:
wherein S i,Sj is a set of initial keywords and a set of semantic analysis tags that are relatively close, t jh,tik is an initial keyword and a semantic analysis tag in the set S i,Sj, wup (t ik,tjh) is wup similarity between the initial keyword and the semantic analysis tag, max h(wup(tik,tjh)) is a maximum value of wup similarity between t jh and all the semantic analysis tags in S j, max k(wup(tjh,tik)) is a maximum value of wup similarity between t ik and all the initial keywords in S i, and size (S) represents the number of the set.
The method is used for constructing a position feature vector list by corresponding inquiry text information, and can accurately segment words and adjust the sequence after segmentation by combining a word bag model (BOF) in the field of natural language processing with N-Gram features. The bag of words model (BOF) is a standard target classification framework consisting of feature extraction, feature clustering, feature encoding, feature convergence and classifier classification 4 parts. The N-Gram feature is an algorithm based on a statistical language model, also called a first order Markov chain, and is to perform sliding window operation with the size of N on the content in the text according to bytes, so as to form a byte fragment sequence with the length of N. Each byte segment is called a gram, statistics is carried out on the occurrence frequency of all the grams, and filtering is carried out according to a preset threshold value to form a key gram list, namely a vector feature space of the text; each gram in the list is a feature vector dimension; firstly, carrying out rough segmentation processing on input criminal name field information; then performing Bi-gram cutting treatment; and finally, filtering to obtain a feature vector list.
The NLP analysis model architecture adopts an input, mapping (hiding) and output architecture, wherein X (1) to X (n) represent feature vectors of each word in a text, a paragraph can be represented by an average value after embedding and accumulating all words, and finally, a label of an output layer is obtained through nonlinear transformation of a hidden layer again; the model inputs a word sequence (a text or a sentence) and outputs probabilities that the word sequence belongs to different categories; the hidden layer is obtained by summing and averaging the input layers and multiplying the input layers by a weight matrix A; the output layer is obtained by multiplying the hidden layer by a weight matrix B; in order to improve the operation time and the running time, the model uses a hierarchical Softmax skill, and the label is encoded on the basis of the Hartmann encoding, so that the number of model prediction targets can be greatly reduced.
Specifically, the output layer is formed by multiplying the hidden layer by the weight matrix B as follows:
Wherein y n represents true label, x n represents feature vector list (N-Gram feature of document N after normalization), and A and B represent weight matrix respectively; n=1, 2,3, …, N being a positive integer.
Firstly, constructing text feature vectors of inquiry text information, inputting the constructed text feature vector list into an NLP analysis model, and carrying out weight presetting on each text feature vector in the text feature vector list by using an N-Gram statistical language algorithm in the NLP analysis model; and analyzing and processing the character feature vectors with preset weights through an NLP model, and outputting semantic analysis labels.
Index retrieval module 23: the index key words are used for index searching on the medical diagnosis database, and the medical diagnosis information searched by the index is ranked according to the relevance;
in the implementation process of the invention, the index searching on the medical diagnosis database by using the search keyword comprises the following steps: clustering with the index key words in the medical diagnosis database by using the search key words as centers to obtain a clustering result; performing Euclidean distance calculation based on the clustering result, and obtaining a final index keyword based on the Euclidean distance calculation result; and constructing a keyword retrieval formula by utilizing the final index keywords, and carrying out index retrieval on the medical diagnosis database based on the constructed keyword retrieval formula.
Further, the sorting the medical diagnosis information retrieved by the index according to the relevance includes: acquiring index keyword information corresponding to each piece of medical diagnosis information; assigning a corresponding weight to the index key information based on the Euclidean distance calculation result; and giving corresponding weights to the index key information for accumulation processing, and sequencing according to the accumulation result.
Further, the adding the corresponding weight to the index key information includes: and accumulating according to the corresponding weight value given by the index key words in each piece of medical diagnosis information.
Specifically, clustering is performed by using the search key as a center and index keys in the medical diagnosis database, and k-means clustering is used in the embodiment of the invention, so that a clustering result with the search key as a center is obtained; then, calculating Euclidean distance by utilizing keywords in the clustering result, and determining a final index keyword according to the Euclidean distance obtained by calculation; and constructing a search formula applicable to the medical diagnosis database through the final index key words, and then carrying out index search on the medical diagnosis database by utilizing the search formula.
Firstly, obtaining multi-corresponding index keyword information in each piece of medical diagnosis information, calculating Euclidean distances among all index keywords, and giving corresponding weight to each index keyword through the Euclidean distances among the index keywords; finally, giving corresponding weight to the index key information corresponding to the plurality of pieces of medical diagnosis information for accumulation, and then sequencing according to the accumulated result; and accumulating according to the corresponding weight given by the index key words in each piece of medical diagnosis information.
Visual characteristics determination module 24: the method comprises the steps that visual characteristics of ordered medical diagnosis information are determined on the background server, and the determined visual characteristics are obtained, wherein the visual characteristics comprise the screen size, the screen resolution and the user expected display resolution of a user terminal for displaying the medical diagnosis information;
In the implementation process of the invention, the visual characteristic determination is performed on the sequenced medical diagnosis information on the background server to obtain the determined visual characteristic, which comprises the following steps: the background server obtains the display characteristics of the user terminal based on the HTTPS protocol; determining visual features of the ordered medical diagnosis information in the background server based on the display features, and obtaining determined visual features; the display characteristics comprise the screen size of the user terminal for display and the display resolution set by the user; the visual features include a screen size, a screen resolution, a user desired display resolution of a user terminal for displaying the medical diagnostic information.
Specifically, the display characteristics of the user terminal are obtained in the background server by utilizing an HTTPS protocol, wherein the display characteristics comprise the screen size of the user terminal for display and the display resolution set by a user; determining visual features of the sequenced medical diagnosis information in a background server according to the display features, and obtaining the determined visual features; in particular, the visual characteristics include a screen size, a screen resolution, a user desired display resolution of the user terminal for displaying the medical diagnosis information.
The rendering module to be displayed 25: the method comprises the steps of performing rendering processing to be displayed on medical diagnosis information according to determined visual characteristics to obtain rendering results to be displayed;
In the implementation process of the invention, the rendering processing to be displayed is carried out on the medical diagnosis information according to the determined visual characteristics to obtain the rendering result to be displayed, which comprises the following steps: mapping the data elements in the medical diagnosis information according to the determined visual characteristics to obtain a document frame to be displayed; and carrying out rendering treatment to be displayed on the document frame to be displayed to obtain rendering results to be displayed.
Specifically, mapping all data elements in the medical diagnosis information to be displayed according to the determined visual characteristics, so as to map the data elements to the corresponding document frames to obtain the document frames to be displayed; and finally, rendering the document frame to be displayed to obtain a rendering result to be displayed.
The load visualization module 26: and the background server is used for loading the rendering result to be displayed to the user terminal for visual display.
In the implementation process of the invention, the background server loads the rendering result to be displayed to the user terminal for visual display, and the method comprises the following steps: and the background server loads the rendering results to be displayed to the user terminal according to the display sequence for visual display.
In the embodiment of the invention, the inquiry text information input by a user is received and uploaded to a background server, the keyword is extracted, then index retrieval is carried out by using the extracted keyword, then sequencing is carried out, the sequencing result is rendered to be displayed according to the determined visual characteristics, and then the rendering result to be displayed is loaded to a user terminal for visual display; according to the method, the medical diagnosis information can be quickly matched and visualized through big data retrieval matching according to the inquiry information input by the user, so that online intelligent inquiry is quickly realized, and the use experience of the user is improved.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program to instruct related hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like.
In addition, the above description is provided for a method and a device for visualizing medical diagnosis information based on big data retrieval according to the embodiments of the present invention, and specific examples should be adopted herein to illustrate the principles and embodiments of the present invention, where the above description of the embodiments is only for helping to understand the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (3)
1. A medical diagnostic information visualization method based on big data retrieval, the method comprising:
The method comprises the steps that a user terminal receives inquiry text information input by a user and uploads the inquiry text information to a background server based on an HTTPS protocol; the method comprises the steps that a corresponding APP or applet or a PC application program which is connected with a background server is installed on a user terminal, inquiry information input by a user is received on a corresponding operation interface on the user terminal, after the inquiry information is received, the user terminal converts the inquiry information into inquiry text information through a corresponding algorithm, redundancy removal is conducted based on a grammar rule mode, and the inquiry text information is formed by integrating the inquiry information after redundancy removal according to an input time sequence;
The background server performs retrieval keyword extraction processing based on the received inquiry text information to obtain retrieval keywords;
index searching is carried out on the medical diagnosis database by utilizing the search keywords, and medical diagnosis information searched by the index is ranked according to the relevance;
Performing visual characteristic determination on the sequenced medical diagnosis information on the background server to obtain determined visual characteristics, wherein the visual characteristics comprise screen size, screen resolution and user expected display resolution of a user terminal for displaying the medical diagnosis information;
performing rendering treatment to be displayed on the medical diagnosis information according to the determined visual characteristics to obtain rendering results to be displayed;
the background server loads the rendering result to be displayed to the user terminal for visual display;
The step of determining visual characteristics of the sequenced medical diagnosis information on the background server to obtain the determined visual characteristics comprises the following steps:
the background server obtains the display characteristics of the user terminal based on the HTTPS protocol;
determining visual features of the ordered medical diagnosis information in the background server based on the display features, and obtaining determined visual features;
The display characteristics comprise the screen size of the user terminal for display and the display resolution set by the user;
the visual features include a screen size, a screen resolution, a user desired display resolution of a user terminal for displaying the medical diagnosis information;
The rendering processing to be displayed is carried out on the medical diagnosis information according to the determined visual characteristics, and a rendering result to be displayed is obtained, and the rendering processing comprises the following steps:
Mapping the data elements in the medical diagnosis information according to the determined visual characteristics to obtain a document frame to be displayed;
performing rendering treatment to be displayed on the document frame to be displayed to obtain rendering results to be displayed;
The index searching on the medical diagnosis database by using the search keyword comprises the following steps:
Clustering with the index key words in the medical diagnosis database by using the search key words as centers to obtain a clustering result;
performing Euclidean distance calculation based on the clustering result, and obtaining a final index keyword based on the Euclidean distance calculation result;
constructing a keyword search formula by utilizing the final index keywords, and carrying out index search on the medical diagnosis database based on the constructed keyword search formula;
the sorting the medical diagnosis information retrieved by the index according to the relevance comprises the following steps:
Acquiring index keyword information corresponding to each piece of medical diagnosis information;
Assigning a corresponding weight to the index key information based on the Euclidean distance calculation result;
Giving corresponding weights to the index key information for accumulation processing, and sequencing according to the accumulation result;
The step of adding the corresponding weight by using the index key information comprises the following steps:
Accumulating according to the corresponding weight given by the index key words in each piece of medical diagnosis information;
The background server loads the rendering result to be displayed to the user terminal for visual display, and the method comprises the following steps:
The background server loads the rendering results to be displayed to the user terminal according to the display sequence to perform visual display;
The background server performs search keyword extraction processing based on the received inquiry text information to obtain search keywords, and the method comprises the following steps:
performing initial keyword extraction processing on the inquiry text information based on a keyword extraction algorithm to obtain initial keywords;
Carrying out semantic analysis processing on the inquiry text information based on an NLP analysis model to obtain a semantic analysis tag;
screening and matching the initial keywords with the semantic analysis tags to obtain search keywords;
Wherein, screening matching is carried out through similarity calculation during screening matching; the specific algorithm is as follows:
；
Wherein, To compare a set of similar initial keywords to a set of semantic analysis tags,/>Respectively is a collectionIn (1) initial keywords and semantic analysis tags,/>For/>, between the initial keyword and the semantic analysis tagSimilarity,/>Is/>And/>/>, Of all semantic analysis tags in (a)Maximum value of similarity,/>Is/>And/>/>, Of all initial keywords in (1)The maximum value of the degree of similarity is,Representing the number of sets.
2. The medical diagnosis information visualization method according to claim 1, wherein the performing semantic analysis processing on the inquiry text information based on the NLP analysis model to obtain a semantic analysis tag includes:
performing text feature vector list construction processing based on the inquiry text information to obtain a text feature vector list;
Inputting the text feature vector list into the NLP analysis model, and presetting a weight value of each text feature vector in the text feature vector list by using an N-Gram statistical language algorithm in the NLP analysis model;
and analyzing and processing the character feature vectors with preset weights through the NLP analysis model, and outputting semantic analysis labels.
3. A medical diagnostic information visualizing apparatus based on big data retrieval, the apparatus comprising:
An input module: the method comprises the steps that a user terminal receives inquiry text information input by a user, and the inquiry text information is uploaded to a background server based on an HTTPS protocol; the method comprises the steps that a corresponding APP or applet or a PC application program which is connected with a background server is installed on a user terminal, inquiry information input by a user is received on a corresponding operation interface on the user terminal, after the inquiry information is received, the user terminal converts the inquiry information into inquiry text information through a corresponding algorithm, redundancy removal is conducted based on a grammar rule mode, and the inquiry text information is formed by integrating the inquiry information after redundancy removal according to an input time sequence;
Keyword extraction module: the background server is used for extracting the search keywords based on the received inquiry text information to obtain the search keywords;
index retrieval module: the index key words are used for index searching on the medical diagnosis database, and the medical diagnosis information searched by the index is ranked according to the relevance;
The visual characteristic determining module: the method comprises the steps that visual characteristics of ordered medical diagnosis information are determined on the background server, and the determined visual characteristics are obtained, wherein the visual characteristics comprise the screen size, the screen resolution and the user expected display resolution of a user terminal for displaying the medical diagnosis information;
And a rendering module to be displayed: the method comprises the steps of performing rendering processing to be displayed on medical diagnosis information according to determined visual characteristics to obtain rendering results to be displayed;
Loading a visualization module: the background server is used for loading the rendering result to be displayed to the user terminal for visual display;
The step of determining visual characteristics of the sequenced medical diagnosis information on the background server to obtain the determined visual characteristics comprises the following steps:
the background server obtains the display characteristics of the user terminal based on the HTTPS protocol;
determining visual features of the ordered medical diagnosis information in the background server based on the display features, and obtaining determined visual features;
The display characteristics comprise the screen size of the user terminal for display and the display resolution set by the user;
the visual features include a screen size, a screen resolution, a user desired display resolution of a user terminal for displaying the medical diagnosis information;
The rendering processing to be displayed is carried out on the medical diagnosis information according to the determined visual characteristics, and a rendering result to be displayed is obtained, and the rendering processing comprises the following steps:
Mapping the data elements in the medical diagnosis information according to the determined visual characteristics to obtain a document frame to be displayed;
performing rendering treatment to be displayed on the document frame to be displayed to obtain rendering results to be displayed;
The index searching on the medical diagnosis database by using the search keyword comprises the following steps:
Clustering with the index key words in the medical diagnosis database by using the search key words as centers to obtain a clustering result;
performing Euclidean distance calculation based on the clustering result, and obtaining a final index keyword based on the Euclidean distance calculation result;
constructing a keyword search formula by utilizing the final index keywords, and carrying out index search on the medical diagnosis database based on the constructed keyword search formula;
the sorting the medical diagnosis information retrieved by the index according to the relevance comprises the following steps:
Acquiring index keyword information corresponding to each piece of medical diagnosis information;
Assigning a corresponding weight to the index key information based on the Euclidean distance calculation result;
Giving corresponding weights to the index key information for accumulation processing, and sequencing according to the accumulation result;
The step of adding the corresponding weight by using the index key information comprises the following steps:
Accumulating according to the corresponding weight given by the index key words in each piece of medical diagnosis information;
The background server loads the rendering result to be displayed to the user terminal for visual display, and the method comprises the following steps:
The background server loads the rendering results to be displayed to the user terminal according to the display sequence to perform visual display;
Wherein, screening matching is carried out through similarity calculation during screening matching; the specific algorithm is as follows:
；
Wherein, To compare a set of similar initial keywords to a set of semantic analysis tags,/>Respectively is a collectionIn (1) initial keywords and semantic analysis tags,/>For/>, between the initial keyword and the semantic analysis tagSimilarity,/>Is/>And/>/>, Of all semantic analysis tags in (a)Maximum value of similarity,/>Is/>And/>/>, Of all initial keywords in (1)The maximum value of the degree of similarity is,Representing the number of sets.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010116976.0A CN111341457B (en) | 2020-02-25 | 2020-02-25 | Medical diagnosis information visualization method and device based on big data retrieval |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010116976.0A CN111341457B (en) | 2020-02-25 | 2020-02-25 | Medical diagnosis information visualization method and device based on big data retrieval |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111341457A CN111341457A (en) | 2020-06-26 |
| CN111341457B true CN111341457B (en) | 2024-05-10 |
Family
ID=71187889
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010116976.0A Active CN111341457B (en) | 2020-02-25 | 2020-02-25 | Medical diagnosis information visualization method and device based on big data retrieval |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111341457B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106462325A (en) * | 2014-05-27 | 2017-02-22 | 三星电子株式会社 | Method of controlling display and electronic device for providing the same |
| CN107766400A (en) * | 2017-05-05 | 2018-03-06 | 平安科技（深圳）有限公司 | Text searching method and system |
| CN108153843A (en) * | 2017-12-18 | 2018-06-12 | 广州七乐康药业连锁有限公司 | A kind of medical information personalized recommendation method and system based on cloud platform |
| CN109376230A (en) * | 2018-12-18 | 2019-02-22 | 广东博维创远科技有限公司 | Crime is determined a crime prediction technique, system, storage medium and server |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008117239A (en) * | 2006-11-06 | 2008-05-22 | Techmatrix Corp | Medical information processing system, observation data editing device, observation data editing method and program |
| US9465572B2 (en) * | 2011-11-09 | 2016-10-11 | Microsoft Technology Licensing, Llc | Dynamic server-side image sizing for fidelity improvements |
| US20160012038A1 (en) * | 2014-07-10 | 2016-01-14 | International Business Machines Corporation | Semantic typing with n-gram analysis |
| US10204033B2 (en) * | 2017-03-11 | 2019-02-12 | Wipro Limited | Method and system for semantic test suite reduction |
| CN107194163A (en) * | 2017-05-15 | 2017-09-22 | 上海联影医疗科技有限公司 | A kind of display methods and system |
-
2020
- 2020-02-25 CN CN202010116976.0A patent/CN111341457B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106462325A (en) * | 2014-05-27 | 2017-02-22 | 三星电子株式会社 | Method of controlling display and electronic device for providing the same |
| CN107766400A (en) * | 2017-05-05 | 2018-03-06 | 平安科技（深圳）有限公司 | Text searching method and system |
| CN108153843A (en) * | 2017-12-18 | 2018-06-12 | 广州七乐康药业连锁有限公司 | A kind of medical information personalized recommendation method and system based on cloud platform |
| CN109376230A (en) * | 2018-12-18 | 2019-02-22 | 广东博维创远科技有限公司 | Crime is determined a crime prediction technique, system, storage medium and server |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111341457A (en) | 2020-06-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110297988B (en) | Hot topic detection method based on weighted LDA and improved Single-Pass clustering algorithm | |
| CN109740148B (en) | Text emotion analysis method combining BiLSTM with Attention mechanism | |
| CN111274365B (en) | Intelligent inquiry method and device based on semantic understanding, storage medium and server | |
| CN108829822B (en) | Media content recommendation method and device, storage medium and electronic device | |
| CN112347244B (en) | Yellow-based and gambling-based website detection method based on mixed feature analysis | |
| US20210342658A1 (en) | Polysemant meaning learning and search result display | |
| US8792732B1 (en) | Automatic large scale video object recognition | |
| CN111291188B (en) | Intelligent information extraction method and system | |
| CN110134792B (en) | Text recognition method and device, electronic equipment and storage medium | |
| CN110046250A (en) | Three embedded convolutional neural networks model and its more classification methods of text | |
| CN115438166A (en) | Keyword and semantic-based searching method, device, equipment and storage medium | |
| CN113434636B (en) | Semantic-based approximate text searching method, semantic-based approximate text searching device, computer equipment and medium | |
| CN111061939B (en) | Scientific research academic news keyword matching recommendation method based on deep learning | |
| US10915756B2 (en) | Method and apparatus for determining (raw) video materials for news | |
| CN113239159B (en) | Cross-modal retrieval method for video and text based on relational inference network | |
| CN111506831A (en) | Collaborative filtering recommendation module and method, electronic device and storage medium | |
| CN115983233B (en) | Electronic medical record duplicate checking rate estimation method based on data stream matching | |
| CN115186665B (en) | Semantic-based unsupervised academic keyword extraction method and equipment | |
| CN113836896A (en) | Patent text abstract generation method and device based on deep learning | |
| CN116795947A (en) | Document recommendation method, device, electronic equipment and computer readable storage medium | |
| CN114048354A (en) | Test question retrieval method, device and medium based on multi-element characterization and metric learning | |
| CN111581943A (en) | Chinese-over-bilingual multi-document news viewpoint sentence identification method based on sentence association graph | |
| CN113641788B (en) | Unsupervised long and short film evaluation fine granularity viewpoint mining method | |
| CN118468061A (en) | Automatic algorithm matching and parameter optimizing method and system | |
| CN114758742A (en) | Medical record information processing method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: Room 109, First Floor, Building 2, No. 23 Hejing Road, Guangzhou, Guangdong Province, 510000 (for office purposes only) Patentee after: Guangzhou qilekang Digital Health Medical Technology Co.,Ltd. Country or region after: China Address before: Room 701-707, No. 2, Luju Road, Liwan District, Guangzhou, Guangdong 510000 Patentee before: GUANGZHOU 7LK PHARMACEUTICAL CHAIN CO.,LTD. Country or region before: China |