CN113257399B - Automatic emergency first-aid article acquisition method and system based on semantic analysis - Google Patents
Automatic emergency first-aid article acquisition method and system based on semantic analysis Download PDFInfo
- Publication number
- CN113257399B CN113257399B CN202110730768.4A CN202110730768A CN113257399B CN 113257399 B CN113257399 B CN 113257399B CN 202110730768 A CN202110730768 A CN 202110730768A CN 113257399 B CN113257399 B CN 113257399B
- Authority
- CN
- China
- Prior art keywords
- information
- emergency
- aid
- semantic
- obtaining
- 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
Images
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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Medical Informatics (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Epidemiology (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses an automatic emergency first-aid article acquisition method and system based on semantic analysis, wherein a first recognition result is obtained according to first voice information; traversing and comparing the first recognition result with the first-aid article information base to obtain a comparison result, and inputting the first recognition result into a semantic analysis model to obtain first semantic information when the comparison result is not matched with the first-aid article; obtaining matched emergency service semantics according to the first semantic information and the emergency service semantics database; obtaining a first matched first-aid article according to the matched first-aid semantics; a first aid order is sent according to the first matched first aid item. Content identification analysis is carried out through the semanteme to the realization, and the intelligence carries out the recommendation of first aid article, automatic output first aid related article, and convenience of customers uses swiftly, ensures to carry out the technological effect that first aid article acquireed fast and guide, solves among the prior art to the user that lacks medical knowledge have the misuse and the image first aid effect when carrying out the selection of first aid article and using.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an automatic emergency first-aid article acquisition method and system based on semantic analysis.
Background
First aid, i.e. emergency treatment, means that when any accident or emergency occurs, a rescuer performs preliminary rescue and nursing for the wounded temporarily and properly by using on-site applicable materials according to the principle of medical nursing before medical care personnel arrive, and then delivers the wounded to a hospital quickly. The purpose of first aid is: preserving life-recovering respiration and heartbeat, stopping bleeding, and treating shock. Preventing the deterioration of the wound-treating the wound and fixing the bone. Promoting rehabilitation-avoidance of unnecessary movements, careful handling, maintenance of the most comfortable sitting/lying posture, good comfort. Meanwhile, the first-aid article can be used in the first-aid process, particularly the first-aid medicine for trauma is very important to the first-aid effect, and common first-aid articles comprise sterilized cotton, sterilized gauze, dressing bags, adhesive tapes, bandages, medicinal hot wine, mild disinfectants such as sabolone, adhesive tapes, safety pins, scissors, triangular towels, disposable rubber gloves and the like.
Medical knowledge is involved in the use process of the first-aid articles, and the technical problem that the users who lack medical knowledge are not used properly to image the first-aid effect when the users select and use the first-aid articles is solved.
Disclosure of Invention
The present invention is directed to solve at least one of the above technical drawbacks, and provides a method and a system for automatically acquiring emergency first-aid articles based on semantic analysis, so as to solve the technical problem in the prior art that the image first-aid effect is caused by improper use when a user lacking medical knowledge selects and uses the first-aid articles. Content recognition and analysis are carried out through semantics, first-aid articles are recommended intelligently, first-aid associated articles are output automatically, convenience is brought to users to use the system quickly, the system is particularly suitable for users in emergency situations or users lacking medical knowledge, and the technical effects that the users can acquire and guide the first-aid articles quickly are achieved.
To this end, a first object of the present invention is to provide an automatic emergency first-aid article acquisition method based on semantic analysis, which includes: obtaining first voice information; obtaining a first recognition result according to the first voice information; obtaining an emergency article information base; traversing and comparing the first identification result with the first-aid item information base to obtain a comparison result, wherein the comparison result comprises a first result and a second result, the first result is that the first-aid item is matched, and the second result is that the first-aid item is not matched; when the comparison result is the second result, inputting the first recognition result into a semantic analysis model to obtain first semantic information; obtaining a first-aid semantic database; obtaining matched emergency semantics according to the first semantic information and the emergency semantic database; obtaining a first matched first-aid article according to the matched first-aid semantics; and sending a first-aid order according to the first matched first-aid article.
The second purpose of the present invention is to provide an automatic emergency first-aid article acquisition system based on semantic analysis, which includes:
a first obtaining unit configured to obtain first voice information;
a second obtaining unit, configured to obtain a first recognition result according to the first voice information;
a third obtaining unit for obtaining an emergency item information base;
a fourth obtaining unit, configured to perform traversal comparison on the first identification result and the emergency item information base to obtain a comparison result, where the comparison result includes a first result and a second result, the first result is that the emergency item is matched, and the second result is that the emergency item is not matched;
the first execution unit is used for inputting the first recognition result into a semantic analysis model to obtain first semantic information when the comparison result is the second result;
a fifth obtaining unit, configured to obtain a first-aid semantic database;
a sixth obtaining unit, configured to obtain matching emergency semantics according to the first semantic information and the emergency semantic database;
a seventh obtaining unit, configured to obtain a first matching emergency item according to the matching emergency semantic;
a first sending unit to send a first aid order according to the first matched first aid item.
A third object of the present invention is to provide a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above method when executing the computer program.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
according to the method and the system for automatically acquiring emergency first-aid articles based on semantic analysis, provided by the embodiment of the invention, first voice information is acquired; obtaining a first recognition result according to the first voice information; obtaining an emergency article information base; traversing and comparing the first identification result with the first-aid item information base to obtain a comparison result, wherein the comparison result comprises a first result and a second result, the first result is that the first-aid item is matched, and the second result is that the first-aid item is not matched; when the comparison result is the second result, inputting the first recognition result into a semantic analysis model to obtain first semantic information; obtaining a first-aid semantic database; obtaining matched emergency semantics according to the first semantic information and the emergency semantic database; obtaining a first matched first-aid article according to the matched first-aid semantics; and sending a first-aid order according to the first matched first-aid article. Content identification and analysis are carried out through the semanteme, the first-aid article is recommended to intelligence, the first-aid associated article is output automatically, convenience of customers is used rapidly, the emergency treatment system is particularly suitable for users who lack medical knowledge or medical conditions, the technical effect that the users rapidly acquire and guide the first-aid articles is guaranteed, and therefore the technical problem that image first-aid effects are caused by improper use when the users who lack medical knowledge select and use the first-aid articles in the prior art is solved.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
Fig. 1 is a schematic flowchart illustrating an emergency first-aid article automatic acquisition method based on semantic analysis according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of an emergency first-aid article automatic acquisition system based on semantic analysis according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of reference numerals: a first obtaining unit 11, a second obtaining unit 12, a third obtaining unit 13, a fourth obtaining unit 14, a first executing unit 15, a fifth obtaining unit 16, a sixth obtaining unit 17, a seventh obtaining unit 18, a first sending unit 19, a bus 300, a receiver 301, a processor 302, a sender 303, a memory 304, and a bus interface 305.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention. On the contrary, the embodiments of the invention include all changes, modifications and equivalents coming within the spirit and terms of the claims appended hereto.
In the description of the present invention, it is to be noted that, unless otherwise explicitly specified or limited, the terms "connected" and "connected" are to be interpreted broadly, e.g., as being fixed or detachable or integrally connected; can be mechanically or electrically connected; may be directly connected or indirectly connected through an intermediate. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art. In addition, in the description of the present invention, "a plurality" means two or more unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
An emergency first-aid article automatic acquisition method based on semantic analysis according to an embodiment of the present invention is described below with reference to the accompanying drawings.
The technical scheme of the application is as follows: obtaining first voice information; obtaining a first recognition result according to the first voice information; obtaining an emergency article information base; traversing and comparing the first identification result with the first-aid item information base to obtain a comparison result, wherein the comparison result comprises a first result and a second result, the first result is that the first-aid item is matched, and the second result is that the first-aid item is not matched; when the comparison result is the second result, inputting the first recognition result into a semantic analysis model to obtain first semantic information; obtaining a first-aid semantic database; obtaining matched emergency semantics according to the first semantic information and the emergency semantic database; obtaining a first matched first-aid article according to the matched first-aid semantics; and sending a first-aid order according to the first matched first-aid article. The problem of among the prior art to the user that lacks medical knowledge have the misuse and image first aid effect when carrying out the selection and the use of first aid article is solved.
Example one
As shown in fig. 1, an embodiment of the present application provides an automatic emergency first-aid article acquisition method based on semantic analysis, where the method includes:
step S100, obtaining first voice information;
specifically, the first voice information is voice information sent by a user to an automatic emergency article acquisition system, the automatic emergency article acquisition method based on semantic analysis according to the embodiment of the application is used in the automatic emergency article acquisition system, the system is usually used in an automatic emergency article acquisition cabinet set in a public place or the like, the voice information is transmitted through a voice acquisition part in the automatic acquisition cabinet, and the system acquires and analyzes received voice through the voice acquisition part.
Step S200, obtaining a first recognition result according to the first voice information;
specifically, the first voice information is directly converted and extracted, for example, converted into characters, or the voice content is extracted to obtain the corresponding voice content, and the first recognition result is the result of recognizing and extracting the content of the first voice information, that is, the first recognition result is the surface and literal direct recognition and extraction of the first voice information.
Step S300, obtaining an emergency article information base;
specifically, the first-aid article information base is a set of common first-aid article information, and according to different use environments, the first-aid article information base can be correspondingly adjusted, such as to be matched with articles contained in the first-aid article automatic acquisition cabinet. If the method is used for the intelligent terminal for purchasing instructions, the information of all first-aid articles can be obtained through channels such as professional first-aid documents, big data, medical institutions and the like.
Step S400, based on the first identification result and the first-aid article information base, performing traversal comparison to obtain a comparison result, wherein the comparison result comprises a first result and a second result, the first result is that the first-aid article is matched, and the second result is that the first-aid article is not matched;
further, the method comprises: when the comparison result is a first result, obtaining a second matched first-aid article according to the first result; and sending a second first-aid order according to the second matched first-aid article.
Specifically, the content in the first identification result is used as the feature information, and is compared with the first-aid articles in the first-aid article information base to obtain whether the first identification result contains the corresponding first-aid articles, for example, the first identification result includes alcohol, cotton swabs and bandages, and the matching with the content in the first-aid article information base is successful, in this case, the first result is generated according to the corresponding first-aid articles obtained by comparison, in the second first-aid order, the articles successfully matched with the first identification result in the first-aid article information base are sent to the user, and when the first-aid article is used in the first-aid article automatic acquisition cabinet, the articles in the cabinet are matched according to the articles in the second first-aid order, and the first-aid articles in the order are extracted from the first-aid article automatic acquisition cabinet and automatically acquired. If the consultation terminal or the intelligent terminal can recommend nearby purchasing places, the user selects according to the recommendation, and the system automatically connects and automatically places orders.
Step S500, when the comparison result is the second result, inputting the first recognition result into a semantic analysis model to obtain first semantic information;
specifically, if the first recognition result does not have the corresponding first-aid item, which is the second result, when the feature comparison result is the second result, performing deep semantic analysis on the first recognition result to determine the first-aid content fed back therein, such as that the first recognition result includes leg-breaking bleeding and does not have the corresponding first-aid item but has the corresponding symptom description, performing deep semantic analysis on the content in the recognition result to obtain the expression content, and performing semantic analysis on the content in the first recognition result to obtain the bleeding due to the trauma of the user, which are all corresponding first semantic information.
Step S600, obtaining a first-aid semantic database;
step S700, obtaining matched emergency semantics according to the first semantic information and the emergency semantic database;
specifically, the emergency semantic database is a database determined by a large number of emergency symptoms, emergency symptoms corresponding to emergency articles, medical knowledge and emergency documents, contents obtained according to the first semantic information are compared with articles in the emergency semantic database to obtain corresponding emergency semantics, that is, the first semantic information includes expression contents of symptoms, but those contents are contents related to the emergency articles, at this time, the first semantic information and the emergency contents in the emergency semantic database are used for performing matching analysis, so that the first semantic information includes semantic contents related to emergency, and the matched emergency semantics is the semantic contents related to emergency included in the first semantic information. If the first identification result comprises that a person falls down from the stairs, the head and the legs are broken to bleed, further screening related emergency semantic contents from the contents to obtain that the head and the legs are broken to bleed, disinfecting the corresponding objects according to the emergency semantic database, and connecting alcohol or iodophor and cotton swabs; hemostasis (hemostasis corresponds to gauze and adhesive tape wrapping) is performed on the first-aid contents, and the contents correspond to matching first-aid semantics.
Step S800, obtaining a first matched first-aid article according to the matched first-aid semantics;
specifically, corresponding item matching is performed according to the matching emergency semantic content to obtain a corresponding matching emergency item, and if the matching emergency semantic content is: disinfecting with alcohol or iodophor and cotton swab, bandaging with gauze and adhesive tape, and making the first matched first-aid article be alcohol or iodophor, cotton swab, gauze and adhesive tape.
Step S900 sends a first aid order according to the first matched first aid item.
Specifically, the first-aid order is generated according to the environment that the first matched first-aid article is used in combination, if the first-aid order is used in the automatic first-aid article acquisition cabinet, the corresponding first-aid article is obtained by matching the automatic first-aid article acquisition cabinet with the content in the first matched first-aid article, if the first-aid order is used at the terminal, the corresponding first-aid article is obtained by matching the recently matched article in the purchase place, the corresponding first-aid order is generated and sent to the user, the user can select and execute the first-aid article according to the content of the order, content identification and analysis are realized through semantics, the first-aid article is recommended intelligently, the first-aid associated article is output automatically, the first-aid order is convenient for the user to use quickly, the first-aid order is particularly suitable for the user in emergency or lacking medical knowledge, the technical effect of rapid acquisition and guidance of the first-aid article by the user is ensured, and the technical effect that the first-aid article is selected and used by the user lacking medical knowledge in the prior art is solved The technical problem of image emergency treatment effect caused by improper use exists.
Further, the obtaining a first matched emergency article according to the matched emergency semantics comprises: according to the emergency semantic database, obtaining symptom description information as a first grading characteristic; according to the emergency semantic database and the symptom description information, acquiring emergency grade information as a second grading characteristic; obtaining first-aid elements according to the symptom description information and the first-aid grade information, and using the first-aid elements as third grading characteristics; constructing a multi-level emergency analysis decision tree according to the first hierarchical features, the second hierarchical features and the third hierarchical features; inputting the matching emergency semantics into the multi-level emergency decision tree to obtain the first matching emergency item.
Specifically, the analysis of the emergency symptom description content is performed according to the emergency semantic database as a first hierarchical feature, i.e., it is first determined that those emergency symptoms occur. When the first-aid grade is analyzed according to symptoms, the first-aid measures and article use requirements corresponding to the same illness state first-aid grade have certain difference, the first-aid grade information is used as a second grading characteristic, the first-aid elements are analyzed according to the first-aid grade and the symptoms, the first-aid elements correspond to the first-aid measures needed to achieve the effects, and the basic requirements are those, for example, disinfection and hemostasis are performed on main elements of falling injuries, cooling and drug analgesia are performed on main elements of scalding, and multi-layer analysis is performed according to different first-aid conditions, so that the accuracy and reliability of analysis results are improved. The Decision Tree (Decision Tree) is a Decision analysis method for obtaining the probability that the expected value of the net present value is greater than or equal to zero by forming the Decision Tree on the basis of the known occurrence probability of various conditions, evaluating the risk of the project and judging the feasibility of the project, is a graphical method for intuitively applying probability analysis, can give correct classification to newly-appeared objects, and consists of a root node, an internal node and leaf nodes. The first hierarchical feature, the second hierarchical feature and the third hierarchical feature can be used as internal nodes of the multi-level emergency decision tree, the features with the minimum entropy value can be classified preferentially by calculating the information entropy of the internal nodes, the multi-level emergency decision tree is constructed recursively by the method until the final feature leaf node cannot be subdivided, and the classification is finished, so that the multi-level emergency decision tree is formed.
Further, the method comprises: performing information theory encoding operation on the first hierarchical features to obtain first feature information entropy, performing information theory encoding operation on the second hierarchical features to obtain second feature information entropy, and performing information theory encoding operation on the third hierarchical features to obtain third feature information entropy; training a comparison model of the first feature information entropy, the second feature information entropy and the third feature information entropy input data to obtain first root node feature information; constructing the multi-level emergency decision tree based on the first root node feature information and the emergency semantic database.
Specifically, in order to specifically construct the multi-level first aid decision tree, information entropy calculation may be performed on the first hierarchical feature, the second hierarchical feature, and the third hierarchical feature, respectively, that is, specific calculation of an information entropy value is performed on the first hierarchical feature, the second hierarchical feature, and the third hierarchical feature through a shannon formula in an information theory code, so as to obtain the corresponding first feature information entropy, the second feature information entropy, and the third feature information entropy, further, the information entropy represents uncertainty of information, when the uncertainty is larger, an information amount contained in the information is larger, the information entropy is higher, and purity is lower, and when all samples in a set are uniformly mixed, the information entropy is maximum, and purity is lowest. Therefore, the first feature information entropy, the second feature information entropy and the third feature information entropy are compared with the magnitude value of the first feature information entropy, the feature with the minimum entropy, namely the first root node feature information, is obtained based on the data magnitude comparison model, the features with the minimum entropy are classified in sequence according to the sequence from the minimum entropy to the maximum entropy by preferentially classifying the features with the minimum entropy, and finally the multi-level emergency decision tree is constructed, so that each emergency state corresponds to accurate emergency article matching recommendation, and further the specific construction of the multi-level emergency decision tree is realized.
Further, before the obtaining the first voice information, the method includes: acquiring preset trigger information; obtaining first starting information; and when the first starting information contains the preset triggering information, obtaining a first starting instruction, wherein the first starting instruction is used for starting the semantic analysis emergency system and automatically starting a semantic receiving function.
Specifically, in order to avoid daily voice interference to the system, particularly for an automatic emergency article acquisition cabinet arranged in a public area, the occurring voice information is messy and cannot be collected and analyzed at any time, so that the voice function needs to be started. So as to maintain the normal use of the system and avoid useless processing caused by interference information.
Further, said sending a first aid order according to said first matched first aid item, comprising: obtaining article use information according to the first matched emergency article and the matched emergency semantics; obtaining a preset first-aid article use information base; obtaining first article explanation information according to the article use information and the preset first-aid article use information base; associating the first item interpretation information with the first aid order, the first item interpretation information being automatically initiated when the first aid order is opened.
Specifically, in order to ensure normal use of the first-aid articles by the user, article use explanation content is added into the first-aid order, when the first-aid order is selected to be opened, the first article explanation information is automatically started, and the use requirements and the method of the first-aid articles are explained, so that the user is ensured to correctly use the first-aid articles, and the first-aid effect is ensured. The technical problem that the image emergency treatment effect is caused by improper use of a user who lacks medical knowledge when the user selects and uses the emergency treatment article in the prior art is further solved.
Further, the method is applied to a semantic analysis emergency system, the system includes an image monitoring device, the image monitoring device is connected to the semantic analysis emergency system, and the method further includes: obtaining a first image information set through the image monitoring device; obtaining an emergency image characteristic information set; taking the emergency image characteristic information in the emergency image characteristic information set as convolution characteristics; performing traversal feature comparison on the first image information set based on the convolution feature to obtain an image feature comparison result; and when the image feature comparison result has the emergency image feature information, obtaining first early warning information.
Specifically, the semantic analysis emergency system of the embodiment of the application further includes an image monitoring device, which performs image monitoring on specific places and areas, when sudden images such as surrounding and people falling down suddenly appear in a monitored area, early warning is carried out, workers are provided for rescue through early warning, particularly, people are not easy to find the condition that people flow is rare in a certain area, serious consequences are avoided, when the content appearing in the emergency image characteristic information set is identified by comparing the video information in the monitoring equipment with the preset emergency image characteristic information set, and sending out early warning, wherein staff in the monitoring center can check corresponding monitoring pictures in the monitoring system according to early warning content, rescue or broadcast corresponding departments when determining that emergency situations or personal injuries occur, so as to ensure the technical effect of timely knowing and processing states occurring in the monitoring area.
Further, the inputting the first recognition result into a semantic analysis model to obtain first semantic information includes: inputting the first recognition result as input data into the semantic analysis model, wherein the semantic analysis model is obtained by training a neural network model by using a large number of recognition results and a semantic knowledge base as training data, and the semantic knowledge base is a knowledge base constructed by analyzing corresponding relations between the large number of recognition results and the semantic analysis results; and obtaining an output result of the semantic analysis model, wherein the output result comprises the first semantic information, and the first semantic information is obtained by performing semantic analysis on the first recognition result and is used for describing semantic content of the first recognition result.
Specifically, when semantic analysis is performed by using the first recognition result, in order to improve the accuracy of the analysis result, the embodiment of the present application adds a neural network model, where the semantic analysis model is a neural network model in machine learning, and the neural network model can be continuously learned and adjusted, and is a highly complex nonlinear dynamical learning system. Briefly, it is a mathematical model. Through training of a large amount of training data, a semantic knowledge base is built by utilizing a large amount of identification information, namely the corresponding relation between literal meaning and corresponding deep semantic information, model training is carried out by taking a large amount of identification information and the semantic knowledge base as training data, a semantic analysis model is built, the identification information is input into a neural network model, and then first semantic information is output. Furthermore, the training process is essentially a supervised learning process, each group of supervised data comprises the first recognition result, the semantic knowledge base and identification information for identifying first semantic information, the first recognition result and the semantic knowledge base are input into a neural network model, the neural network model is continuously self-corrected and adjusted according to the identification information for identifying the first semantic information, and the group of supervised learning is ended and the next group of supervised learning is carried out until the obtained output result is consistent with the identification information; and when the output information of the neural network model reaches the preset accuracy rate/reaches the convergence state, finishing the supervised learning process. Through the supervised learning of the neural network model, the neural network model is enabled to process the input information more accurately, so that more accurate and suitable first semantic information is obtained, the purpose of expressing meaning according to the word face is achieved, deep semantic analysis is carried out according to the relation between words and expressions and the corresponding relation between the word face and deep semantic content, comprehensive mastering of voice content is achieved through semantic recognition, meanwhile, the neural network model is added, the efficiency and the accuracy of data operation processing results are improved, and a foundation is laid for providing more accurate and reliable emergency treatment article guidance tamping.
Example two
Based on the same inventive concept as the method for automatically acquiring emergency first-aid articles based on semantic analysis in the foregoing embodiments, the present invention further provides an automatic emergency first-aid article acquisition system based on semantic analysis, as shown in fig. 2, the system includes:
a first obtaining unit 11, where the first obtaining unit 11 is configured to obtain first voice information;
a second obtaining unit 12, where the second obtaining unit 12 is configured to obtain a first recognition result according to the first voice information;
a third obtaining unit 13, wherein the third obtaining unit 13 is used for obtaining an emergency article information base;
a fourth obtaining unit 14, where the fourth obtaining unit 14 is configured to perform traversal comparison with the emergency item information base based on the first identification result to obtain a comparison result, where the comparison result includes a first result and a second result, the first result is that the emergency item is matched, and the second result is that the emergency item is not matched;
a first executing unit 15, where the first executing unit 15 is configured to, when the comparison result is the second result, input the first recognition result into a semantic analysis model to obtain first semantic information;
a fifth obtaining unit 16, where the fifth obtaining unit 16 is configured to obtain a first-aid semantic database;
a sixth obtaining unit 17, where the sixth obtaining unit 17 is configured to obtain a matching emergency semantic according to the first semantic information and the emergency semantic database;
a seventh obtaining unit 18, wherein the seventh obtaining unit 18 is configured to obtain a first matching emergency item according to the matching emergency semantics;
a first sending unit 19, the first sending unit 19 being configured to send a first aid order according to the first matched first aid item.
Further, the system further comprises:
an eighth obtaining unit, configured to, when the comparison result is a first result, obtain a second matching first-aid item according to the first result;
a second sending unit for sending a second first aid order according to the second matched first aid item.
Further, the system further comprises:
the second execution unit is used for obtaining symptom description information according to the emergency semantic database and used as a first grading characteristic;
a third execution unit, configured to obtain emergency level information according to the emergency semantic database and the symptom description information, and use the emergency level information as a second hierarchical feature;
a fourth execution unit, configured to obtain an emergency factor according to the symptom description information and the emergency level information, and use the emergency factor as a third grading feature;
a first construction unit for constructing a multi-level first aid analysis decision tree from the first hierarchical features, the second hierarchical features, and the third hierarchical features;
a ninth obtaining unit, configured to input the matching emergency semantics into the multi-level emergency decision tree, to obtain the first matching emergency item.
Further, the system further comprises:
a tenth obtaining unit, configured to perform information-theoretic encoding operation on the first hierarchical feature to obtain a first feature information entropy, perform information-theoretic encoding operation on the second hierarchical feature to obtain a second feature information entropy, and perform information-theoretic encoding operation on the third hierarchical feature to obtain a third feature information entropy;
an eleventh obtaining unit, configured to train a comparison model of the first feature information entropy, the second feature information entropy, and the third feature information entropy input data size, and obtain first root node feature information;
a second construction unit for constructing the multi-level emergency decision tree based on the first root node feature information and the emergency semantic database.
Further, the system further comprises:
a twelfth obtaining unit, configured to obtain preset trigger information;
a thirteenth obtaining unit configured to obtain the first start-up information;
a fourteenth obtaining unit, configured to obtain a first start instruction when the first start information includes the preset trigger information, where the first start instruction is used to start a semantic analysis emergency system and automatically start a semantic receiving function.
Further, the system further comprises:
a fifteenth obtaining unit, configured to obtain item usage information according to the first matching emergency item and the matching emergency semantic;
a sixteenth obtaining unit, configured to obtain a preset first-aid item usage information base;
a seventeenth obtaining unit, configured to obtain first item explanation information according to the item usage information and the preset first-aid item usage information base;
a first associating unit to associate the first item explanation information with the first aid order, the first item explanation information being automatically initiated when the first aid order is opened.
Further, the system further comprises:
an eighteenth obtaining unit, configured to obtain the first image information set through the image monitoring apparatus;
a nineteenth obtaining unit, configured to obtain an emergency image feature information set;
a fifth execution unit, configured to use the emergency image feature information in the emergency image feature information set as a convolution feature;
a twentieth obtaining unit, configured to perform traversal feature comparison on the first image information set based on the convolution feature, and obtain an image feature comparison result;
a twenty-first obtaining unit, configured to obtain first early warning information when the image feature comparison result shows the emergency image feature information.
Further, the system further comprises:
a sixth execution unit, configured to input the first recognition result as input data into the semantic analysis model, where the semantic analysis model is obtained by training a neural network model using a large number of recognition results and a semantic knowledge base as training data, and the semantic knowledge base is a knowledge base constructed by analyzing correspondence between the large number of recognition results and the semantic analysis results;
and the twenty-second obtaining unit is used for obtaining an output result of the semantic analysis model, wherein the output result comprises the first semantic information, and the first semantic information is obtained by performing semantic analysis on the first recognition result and is used for describing semantic content of the first recognition result.
Various changes and specific examples of the method for automatically acquiring emergency first-aid articles based on semantic analysis in the first embodiment of fig. 1 are also applicable to the system for automatically acquiring emergency first-aid articles based on semantic analysis in this embodiment, and through the foregoing detailed description of the method for automatically acquiring emergency first-aid articles based on semantic analysis, those skilled in the art can clearly know that the method for automatically acquiring emergency first-aid articles based on semantic analysis in this embodiment is implemented, so for the sake of brevity of the description, detailed descriptions are not repeated here.
Exemplary electronic device
The electronic device of the embodiment of the present application is described below with reference to fig. 3.
Fig. 3 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of the automatic emergency first-aid article acquisition method based on semantic analysis as in the previous embodiments, the present invention further provides a computer device, on which a computer program is stored, which when executed by a processor implements the steps of any one of the aforementioned automatic emergency first-aid article acquisition methods based on semantic analysis.
Where in fig. 3 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 305 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other systems over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
according to the method and the system for automatically acquiring emergency first-aid articles based on semantic analysis, provided by the embodiment of the invention, first voice information is acquired; obtaining a first recognition result according to the first voice information; obtaining an emergency article information base; traversing and comparing the first identification result with the first-aid item information base to obtain a comparison result, wherein the comparison result comprises a first result and a second result, the first result is that the first-aid item is matched, and the second result is that the first-aid item is not matched; when the comparison result is the second result, inputting the first recognition result into a semantic analysis model to obtain first semantic information; obtaining a first-aid semantic database; obtaining matched emergency semantics according to the first semantic information and the emergency semantic database; obtaining a first matched first-aid article according to the matched first-aid semantics; and sending a first-aid order according to the first matched first-aid article. Content identification and analysis are carried out through the semanteme, the first-aid article is recommended to intelligence, the first-aid associated article is output automatically, convenience of customers is used rapidly, the emergency treatment system is particularly suitable for users who lack medical knowledge or medical conditions, the technical effect that the users rapidly acquire and guide the first-aid articles is guaranteed, and therefore the technical problem that image first-aid effects are caused by improper use when the users who lack medical knowledge select and use the first-aid articles in the prior art is solved.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form. The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit. The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (5)
1. An automatic emergency first-aid article acquisition method based on semantic analysis, wherein the method is applied to an automatic emergency article acquisition cabinet, and the method comprises the following steps:
obtaining first voice information;
obtaining a first recognition result according to the first voice information;
acquiring an emergency article information base;
traversing and comparing the first identification result with the first-aid item information base to obtain a comparison result, wherein the comparison result comprises a first result and a second result, the first result is that the first-aid item is matched, and the second result is that the first-aid item is not matched;
when the comparison result is a first result, obtaining a second matched first-aid article according to the first result;
sending a second first-aid order according to the second matched first-aid article;
when the comparison result is the second result, inputting the first recognition result into a semantic analysis model to obtain first semantic information;
obtaining a first-aid semantic database;
obtaining matched emergency semantics according to the first semantic information and the emergency semantic database;
obtaining a first matched first-aid article according to the matched first-aid semantics;
sending a first-aid order according to the first matched first-aid article;
wherein the obtaining a first matched first-aid item according to the matched first-aid semantics comprises:
according to the emergency semantic database, obtaining symptom description information as a first grading characteristic;
obtaining first-aid grade information according to the first-aid semantic database and the symptom description information, and using the first-aid grade information as a second grading characteristic;
obtaining first-aid elements according to the symptom description information and the first-aid grade information, and using the first-aid elements as third grading characteristics;
constructing a multi-level emergency analysis decision tree according to the first hierarchical features, the second hierarchical features and the third hierarchical features;
inputting the matched emergency semantics into the multi-level emergency analysis decision tree to obtain the first matched emergency item;
wherein constructing a multi-level emergency analysis decision tree from the first hierarchical features, the second hierarchical features, and the third hierarchical features comprises:
performing information theory encoding operation on the first hierarchical features to obtain first feature information entropy, performing information theory encoding operation on the second hierarchical features to obtain second feature information entropy, and performing information theory encoding operation on the third hierarchical features to obtain third feature information entropy;
training a comparison model of the first feature information entropy, the second feature information entropy and the third feature information entropy input data to obtain first root node feature information;
constructing the multi-level emergency analysis decision tree based on the first root node feature information and the emergency semantic database;
the method is applied to a semantic analysis emergency system, the semantic analysis emergency system is installed in the emergency article automatic acquisition cabinet, the system comprises an image monitoring device, and the image monitoring device is connected with the semantic analysis emergency system and comprises the following steps:
obtaining a first image information set through the image monitoring device;
obtaining an emergency image characteristic information set;
taking the emergency image characteristic information in the emergency image characteristic information set as convolution characteristics;
performing traversal feature comparison on the first image information set based on the convolution feature to obtain an image feature comparison result;
when the image feature comparison result has the emergency image feature information, obtaining first early warning information;
inputting the first recognition result into a semantic analysis model to obtain first semantic information, wherein the obtaining of the first semantic information comprises:
inputting the first recognition result as input data into the semantic analysis model, wherein the semantic analysis model is obtained by training a neural network model by using a large number of recognition results and a semantic knowledge base as training data, and the semantic knowledge base is a knowledge base constructed by analyzing corresponding relations between the large number of recognition results and the semantic analysis results;
and obtaining an output result of the semantic analysis model, wherein the output result comprises the first semantic information, and the first semantic information is obtained by performing semantic analysis on the first recognition result and is used for describing the semantic content of the first recognition result.
2. The method of claim 1, wherein obtaining the first speech information is preceded by:
acquiring preset trigger information;
obtaining first starting information;
and when the first starting information contains the preset triggering information, obtaining a first starting instruction, wherein the first starting instruction is used for starting the semantic analysis emergency system and automatically starting a semantic receiving function.
3. The method of claim 1, wherein said transmitting a first aid order according to said first matching first aid item comprises:
obtaining article use information according to the first matched emergency article and the matched emergency semantics;
obtaining a preset first-aid article use information base;
obtaining first article explanation information according to the article use information and the preset first-aid article use information base;
associating the first item interpretation information with the first aid order, the first item interpretation information being automatically initiated when the first aid order is opened.
4. An automatic emergency first-aid article acquisition system based on semantic analysis, wherein the system is applied to the method of any one of claims 1-3, and the system comprises:
a first obtaining unit configured to obtain first voice information;
a second obtaining unit, configured to obtain a first recognition result according to the first voice information;
a third obtaining unit for obtaining an emergency item information base;
a fourth obtaining unit, configured to perform traversal comparison on the first identification result and the emergency item information base to obtain a comparison result, where the comparison result includes a first result and a second result, the first result is that the emergency item is matched, and the second result is that the emergency item is not matched;
the first execution unit is used for inputting the first recognition result into a semantic analysis model to obtain first semantic information when the comparison result is the second result;
a fifth obtaining unit, configured to obtain a first-aid semantic database;
a sixth obtaining unit, configured to obtain matching emergency semantics according to the first semantic information and the emergency semantic database;
a seventh obtaining unit, configured to obtain a first matching emergency item according to the matching emergency semantic;
a first sending unit for sending a first aid order according to the first matched first aid item;
the second execution unit is used for obtaining symptom description information according to the emergency semantic database and used as a first grading characteristic;
a third execution unit, configured to obtain emergency level information according to the emergency semantic database and the symptom description information, and use the emergency level information as a second hierarchical feature;
a fourth execution unit, configured to obtain an emergency factor according to the symptom description information and the emergency level information, and use the emergency factor as a third grading feature;
a first construction unit for constructing a multi-level first aid analysis decision tree from the first hierarchical features, the second hierarchical features, and the third hierarchical features;
a ninth obtaining unit, configured to input the matching emergency semantics into the multi-level emergency analysis decision tree, to obtain the first matching emergency item;
an eighth obtaining unit, configured to, when the comparison result is a first result, obtain a second matching first-aid item according to the first result;
a second sending unit for sending a second first aid order according to the second matched first aid item;
a tenth obtaining unit, configured to perform information-theoretic encoding operation on the first hierarchical feature to obtain a first feature information entropy, perform information-theoretic encoding operation on the second hierarchical feature to obtain a second feature information entropy, and perform information-theoretic encoding operation on the third hierarchical feature to obtain a third feature information entropy;
an eleventh obtaining unit, configured to train a comparison model of the first feature information entropy, the second feature information entropy, and the third feature information entropy input data size, and obtain first root node feature information;
a second construction unit for constructing the multi-level emergency analysis decision tree based on the first root node feature information and the emergency semantic database;
an eighteenth obtaining unit, configured to obtain the first image information set through the image monitoring apparatus;
a nineteenth obtaining unit, configured to obtain an emergency image feature information set;
a fifth execution unit, configured to use the emergency image feature information in the emergency image feature information set as a convolution feature;
a twentieth obtaining unit, configured to perform traversal feature comparison on the first image information set based on the convolution feature, and obtain an image feature comparison result;
a twenty-first obtaining unit, configured to obtain first early warning information when the image feature comparison result has the emergency image feature information;
a sixth execution unit, configured to input the first recognition result as input data into the semantic analysis model, where the semantic analysis model is obtained by training a neural network model using a large number of recognition results and a semantic knowledge base as training data, and the semantic knowledge base is a knowledge base constructed by analyzing correspondence between the large number of recognition results and the semantic analysis results;
and the twenty-second obtaining unit is used for obtaining an output result of the semantic analysis model, wherein the output result comprises the first semantic information, and the first semantic information is obtained by performing semantic analysis on the first recognition result and is used for describing semantic content of the first recognition result.
5. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of the preceding claims 1-3 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110730768.4A CN113257399B (en) | 2021-06-30 | 2021-06-30 | Automatic emergency first-aid article acquisition method and system based on semantic analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110730768.4A CN113257399B (en) | 2021-06-30 | 2021-06-30 | Automatic emergency first-aid article acquisition method and system based on semantic analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113257399A CN113257399A (en) | 2021-08-13 |
| CN113257399B true CN113257399B (en) | 2022-08-05 |
Family
ID=77190166
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110730768.4A Active CN113257399B (en) | 2021-06-30 | 2021-06-30 | Automatic emergency first-aid article acquisition method and system based on semantic analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113257399B (en) |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108039170A (en) * | 2017-12-06 | 2018-05-15 | 北京小米移动软件有限公司 | Communication means, device and storage medium for Emergency Assistance |
| CN109949945A (en) * | 2019-02-26 | 2019-06-28 | 深圳市康智友科技有限公司 | A kind of intelligent sharing first-aid method and system |
| CN112863630A (en) * | 2021-01-20 | 2021-05-28 | 中国科学院自动化研究所 | Personalized accurate medical question-answering system based on data and knowledge |
-
2021
- 2021-06-30 CN CN202110730768.4A patent/CN113257399B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113257399A (en) | 2021-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Goligher et al. | Extracorporeal membrane oxygenation for severe acute respiratory distress syndrome and posterior probability of mortality benefit in a post hoc Bayesian analysis of a randomized clinical trial | |
| AU2003223333B2 (en) | A method and system of mass and multiple casualty triage | |
| Sacco et al. | Precise formulation and evidence‐based application of resource‐constrained triage | |
| US20100153133A1 (en) | Generating Never-Event Cohorts from Patient Care Data | |
| CN103690240A (en) | Medical system | |
| JPWO2016120955A1 (en) | BEHAVIOR PREDICTION DEVICE, BEHAVIOR PREDICTION DEVICE CONTROL METHOD, AND BEHAVIOR PREDICTION DEVICE CONTROL PROGRAM | |
| CN111899837A (en) | Operation report coordination method and system based on digital operating room | |
| CN112735610A (en) | Post-hospital follow-up system and follow-up method | |
| CN107910073A (en) | A kind of emergency treatment previewing triage method and device | |
| CN107122595A (en) | Intelligent preliminary examination and system for distribution of out-patient department | |
| EP3380963A1 (en) | Tracking usage of a pulse oximeter via a network system | |
| Ahmed | An intelligent healthcare service to monitor vital signs in daily life–a case study on health-iot | |
| CN117637153B (en) | Informationized management system and method for patient safety nursing | |
| CN113257399B (en) | Automatic emergency first-aid article acquisition method and system based on semantic analysis | |
| WO2021096467A1 (en) | Triage decision support method and the system using this method | |
| US20230130914A1 (en) | System and method for patient care handoff | |
| Kostoska et al. | Real-time smart advisory health system | |
| Subirats et al. | An ontology for computer-based decision support in rehabilitation | |
| CN112151178A (en) | Intelligent health cloud platform based on Java language development | |
| Iftadi et al. | Using NASA task load index and Maslach burnout inventory for evaluating the subjective mental and physical workload of nurse central surgical installation hospitals Karanganyar | |
| Gaindric et al. | Advanced pre-hospital triage based on vital signs in mass casualty situations | |
| Kuzomin et al. | Intelligent Geoinformatic Expert System For Providing Emergency Help During Extreme Situations | |
| KR101422064B1 (en) | Method for recommending personalized contents based on naive bayesian filtering approach for ubiquitous health service of semantic environment and ubuquitous health service platform based on digital television using the same | |
| Reis et al. | Monitoring system for emergency service in a hospital environment | |
| ÇELİK | A Novel Deep Learning Model for Pain Intensity Evaluation |
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 |