CN114758749B - Nutritional diet management map creation method and device based on gestation period - Google Patents
Nutritional diet management map creation method and device based on gestation period Download PDFInfo
- Publication number
- CN114758749B CN114758749B CN202210293527.2A CN202210293527A CN114758749B CN 114758749 B CN114758749 B CN 114758749B CN 202210293527 A CN202210293527 A CN 202210293527A CN 114758749 B CN114758749 B CN 114758749B
- Authority
- CN
- China
- Prior art keywords
- entity
- word
- target
- description
- cosine similarity
- 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
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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/60—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to nutrition control, e.g. diets
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
- G06F16/243—Natural language query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/313—Selection or weighting of terms for indexing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Primary Health Care (AREA)
- Software Systems (AREA)
- Epidemiology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Animal Behavior & Ethology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Nutrition Science (AREA)
- Machine Translation (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides a nutritional diet management map creation method and device based on gestation period, wherein the method comprises the following steps: acquiring target structured data and target unstructured data related to gestational diabetes; determining symptoms of gestational diabetes and nutritional diet information having an association relationship with the symptoms based on the target structured data, and creating a nutritional diet management profile body of gestational period based on the symptoms and the nutritional diet information; identifying a target entity relationship in the target unstructured data that matches the symptom and/or the nutritional diet information; and carrying out fusion treatment on the nutrition diet management map body and the target entity relationship to generate a gestational diabetes nutrition diet management map. The invention can provide visual system scientific diet guidance for pregnant users, and reduce the acquisition cost of the nutritional diet scheme, thereby greatly improving the management effect of the nutritional diet in gestation period.
Description
Technical Field
The invention relates to the technical field of pregnancy health management, in particular to a nutritional diet management map creation method and device based on gestation.
Background
Gestation refers to the physiological period from the time of conception to the time of delivery, and the metabolism, digestive system, vascular system, endocrine system, reproductive system and bone joint ligaments of the mother are changed correspondingly during pregnancy, so that the risk of gestational diabetes is increased if the organism changes during pregnancy and improper diet and exercise are performed. Therefore, how to healthy and scientifically manage the diet of pregnant women becomes a key problem to be solved.
In the related art, for the nutrition diet management of gestational diabetes, generally, a pregnancy diet tabu and a pregnant woman diet recipe are extracted from a cloud network database, and then the nutrition diet proposal for gestational diabetes is obtained by combining the pregnancy diet tabu and the pregnant woman diet recipe.
However, since the diet taboo during pregnancy and the diet recipe of pregnant women belong to different databases, the nutritional diet scheme cannot be intuitively and systematically obtained, and the obtaining cost of the nutritional diet scheme is high, so that the management effect of the nutritional diet during pregnancy is not obviously improved.
Disclosure of Invention
The invention provides a gestational nutrient diet management map creation method and device, which are used for solving the defect that in the prior art, the gestational nutrient diet management effect is not obviously improved due to the fact that diet taboo during pregnancy and diet recipes of pregnant women belong to different databases and the acquisition cost of a nutrient diet scheme is high.
The invention provides a nutritional diet management map creation method based on gestation period, which comprises the following steps:
acquiring target structured data and target unstructured data related to gestational diabetes;
determining symptoms of gestational diabetes and nutritional diet information having an association relationship with the symptoms based on the target structured data, and creating a nutritional diet management profile body of gestational period based on the symptoms and the nutritional diet information;
identifying a target entity relationship in the target unstructured data that matches the symptom and/or the nutritional diet information;
and carrying out fusion treatment on the nutrition diet management map body and the target entity relationship to generate a gestational diabetes nutrition diet management map.
According to the method for creating the nutritional diet management map based on gestation, the method for acquiring the target structured data and the target unstructured data related to gestational diabetes comprises the following steps:
collecting first structured data, semi-structured data and unstructured data for gestational diabetes;
extracting entity relations in the semi-structured data according to preset keywords and relation keywords contained in each type of entity to obtain second structured data;
And verifying the first structured data, the second structured data and the unstructured data to generate target structured data and target unstructured data related to gestational diabetes.
According to the method for creating the nutritional diet management map based on gestation, the identifying the target entity relationship matched with the symptom and/or the nutritional diet information in the target unstructured data comprises the following steps:
determining an entity tag to be marked and an entity relationship tag to be extracted in the target unstructured data based on the nutrition diet management map body; wherein the entity tag is used to characterize the entity of the symptom and the nutritional diet information;
performing word segmentation on the target unstructured data to obtain word segmentation results;
matching the word segmentation result with the entity tag;
labeling a first entity in the word segmentation result when the word segmentation result is successfully matched with the entity tag;
and extracting the relation of the first entity based on the entity relation label to obtain a target entity relation matched with the symptom and/or the nutritional diet information in the target unstructured data.
According to the nutritional diet management map creation method based on gestation, after the step of matching the word segmentation result with the entity tag, the method further comprises the following steps:
when the matching of the second word description in the word segmentation result and the entity tag fails, calculating a first cosine similarity between the second word description and an entity in the nutrient diet management map body;
determining an entity to be aligned, a center word segment description and an adjacent word segment description from the second word segment description according to the first cosine similarity;
calculating second cosine similarity between the entity to be aligned and the center word segment description and the adjacent word segment description respectively, and determining a second entity in the second word segment description based on the second cosine similarity;
and extracting the relationship of the second entity in the second word description based on the entity relationship label to obtain a target entity relationship matched with the symptom and/or the nutritional diet information in the target unstructured data.
According to the method for creating the nutritional diet management map based on gestation, the entity to be aligned, the center word description and the adjacent word description are determined from the second word description according to the first cosine similarity, and the method comprises the following steps:
Selecting a first highest cosine similarity in the first cosine similarity, determining an entity to be aligned and a center word description corresponding to the first highest cosine similarity in the second word description, and then selecting adjacent word descriptions before and after the center word description in the second word description.
According to the method for creating the nutritional diet management map based on gestation, the determining the second entity in the second word description based on the second cosine similarity comprises the following steps:
and selecting a second highest cosine similarity in the second cosine similarity, and determining a second entity corresponding to the second highest cosine similarity in the second word description.
According to the method for creating the nutritional diet management map based on gestation, the calculating of the first cosine similarity between the second word description and the entity in the nutritional diet management map body comprises the following steps:
wherein x is m A coded representation representing m of said second partial word descriptions, y n A coded representation of n entities within said nutritional diet management profile, cos θ1 representing m x n of said first cosine similarities, m and n Are all positive integers.
The invention also provides a nutrient diet management map creation device based on gestation period, which comprises:
the acquisition module is used for acquiring target structured data and target unstructured data related to gestational diabetes;
the creation module is used for determining the symptom of gestational diabetes and nutritional diet information with an association relation with the symptom based on the target structural data, and creating a nutritional diet management map body in gestation based on the symptom and the nutritional diet information;
the identifying module is used for identifying a target entity relationship matched with the symptom and/or the nutritional diet information in the target unstructured data;
and the fusion module is used for carrying out fusion treatment on the nutrition diet management map body and the target entity relationship to generate a gestational diabetes nutrition diet management map.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the gestation-based nutrient diet management profile creation method as described in any one of the above when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a gestational-based nutrient diet management profile creation method as described in any one of the above.
The invention also provides a computer program product comprising a computer program which when executed by a processor implements a gestational-based nutrient diet management profile creation method as described in any one of the above.
The invention provides a method and a device for creating a nutritional diet management map based on gestation, wherein the method for creating the nutritional diet management map based on gestation firstly acquires target structural data and target unstructured data related to gestational diabetes, then determines symptoms of gestational diabetes and nutritional diet information with association relation with the symptoms based on the target structural data, creates a nutritional diet management map body based on the symptoms and the nutritional diet information, further identifies a target entity relation matched with the symptoms and/or the nutritional diet information in the target unstructured data, and finally carries out fusion processing on the nutritional diet management map body and the target entity relation to generate a nutritional diet management map of gestational diabetes. By combining the target structured data and the target unstructured data related to gestational diabetes, the gestational diabetes nutrition diet management map which covers different symptoms of gestational diabetes and corresponding nutrition diet information is created, a scientific diet guidance of an intuitive system is provided for a gestational user in a targeted manner, the acquisition cost of a nutrition diet scheme is reduced, and therefore the management effect of gestational nutrition diet is greatly improved.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a gestation-based nutrient diet management profile creation method provided by the invention;
FIG. 2 is a flow chart of a method for creating a nutritional diet management profile for gestation period according to the present invention;
fig. 3 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, 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.
The method and apparatus for creating a nutritional diet management profile based on gestation period according to the present invention will be described below with reference to fig. 1 to 3, wherein an execution subject of the method for creating a nutritional diet management profile based on gestation period may be a device for creating a nutritional diet management profile of gestation period, and the device for creating a nutritional diet management profile of gestation period may be implemented as part or all of a terminal device in a manner of software, hardware or a combination of software and hardware. Alternatively, the terminal device may be a personal computer (Personal Computer, PC), a portable device, a notebook computer, a smart phone, a tablet computer, a portable wearable device, or other electronic devices. The invention is not limited to the specific form of the terminal device.
It should be noted that, the execution body of the method embodiment described below may be part or all of the terminal device described above. The following method embodiments are described taking an execution body as a terminal device as an example.
Fig. 1 is a schematic flow chart of a method for creating a nutritional diet management map based on gestation, as shown in fig. 1, comprising the following steps:
step 110, obtaining target structured data and target unstructured data related to gestational diabetes.
Specifically, the terminal device may acquire the target structured data related to gestational diabetes at the internet end, and may acquire the target unstructured data related to gestational diabetes from paper texts such as books, professional documents, and the like, for example, by processing the data related to gestational diabetes in the books, the professional documents into a recognizable and editable manner for the terminal device by using an optical character recognition (Optical Character Recognition, OCR) technology.
Step 120, determining the symptom of gestational diabetes and nutritional diet information related to the symptom based on the target structural data, and creating a nutritional diet management map body of gestational period based on the symptom and the nutritional diet information.
Specifically, aiming at target structural data related to gestational diabetes, each symptom stored in the target structural data is arranged, symptom nodes corresponding to each symptom are created, and nutrition diet information which is stored in the target structural data and has association relation with each symptom is respectively adjusted by combining expert advice, so that a nutrition diet management map body of gestational period, namely a nutrition diet management map skeleton or a nutrition diet management map frame of gestational period is generated. For example, when a "skin itch" node exists in the nutrient diet management profile body, the nutrient diet information having an association relationship with the "skin itch" node may include: it is not suitable for eating high fat and irritation, light, high protein, high vitamins, and more vegetables and fruits, and less spicy and fried food.
It should be noted that, in order to improve the comprehensiveness and accuracy of the subsequently created gestational diabetes nutrition diet management map, the internet end may be used to obtain a structured data set related to all diseases, and then the constituent components of the structured data set and the nutrition diet information of each constituent component may be analyzed, where the constituent components may be various diseases, including hypertension, gestational diabetes, and the like, and for example, the nutrition diet information corresponding to hypertension includes: high salt, high fat, high cholesterol and alcohol are not eaten, and the food is suitable for eating: high protein, high vitamins, high eating vegetables, fruits, seafood, and low eating high salt foods, high cholesterol foods, and fried foods; for example, the nutritional diet information corresponding to gestational diabetes includes: high oil and fat, alcohol, high protein, low sugar and low salt, and high sugar food, fried food and alcoholic food, which are eaten more than vegetables, fruits and seafood; the components of the structured dataset may also be individual symptoms of each disease, including other symptoms of gestational diabetes such as cutaneous pruritus and hunger sensation. And then, the expert advice is combined to extract the target structural data related to gestational diabetes from the structural data set, so that errors are reduced, and accuracy is improved.
Step 130, identifying a target entity relationship in the target unstructured data that matches the symptom and/or the nutritional diet information.
Specifically, for the target unstructured data of gestational diabetes mellitus, a word segmentation tool is used for segmenting the target unstructured data to obtain a word segmentation result, then the word segmentation result is matched with all entities contained in a nutrition diet management map body, a first entity corresponding to the word segmentation result is determined when matching is successful, a second word description corresponding to the word segmentation result is determined when matching is failed, then a Chinese natural language pre-training model (MacBERT) is used for processing all entities contained in the second word description and the nutrition diet management map body, so that a second entity in the second word description is identified, finally the first entity and the second entity are combined, and a target entity relationship matched with symptoms and/or nutrition diet information contained in the nutrition diet management map body in the target unstructured data is identified and extracted. Wherein, all entities contained in the nutrient diet management map body consist of each symptom in the nutrient diet management map body and the entity corresponding to the nutrient diet information.
And 140, carrying out fusion treatment on the nutrition diet management map body and the target entity relationship to generate a gestational diabetes nutrition diet management map.
Specifically, the target entity relationship identified and extracted from the target unstructured data, which is matched with symptoms and/or nutritional diet information contained in the nutritional diet management map body, may be a new entity relationship triplet formed by classifying relationships among entities, for example, (a first entity, a second entity, a target entity relationship 1), (a first entity, a target entity relationship 2), (a second entity, a target entity relationship 3), where the target entity relationship 1, the target entity relationship 2, and the target entity relationship 3 are different types of entity relationships. And then, carrying out fusion treatment on all entity relation triplets and the nutrition diet management map body, and storing the fusion treatment result by adopting a map database, thereby obtaining the required nutrition diet management map for gestational diabetes. The preferred graph database is the graph database neo4j.
According to the gestational nutrient diet management map creation method, target structural data and target unstructured data related to gestational diabetes are firstly obtained, then symptoms of the gestational diabetes and nutrient diet information with association relation with the symptoms are determined based on the target structural data, a gestational nutrient diet management map body is created based on the symptoms and the nutrient diet information, a target entity relation matched with the symptoms and/or the nutrient diet information in the target unstructured data is further identified, and finally fusion processing is carried out on the nutrient diet management map body and the target entity relation, so that a gestational nutrient diet management map is generated. By combining the target structured data and the target unstructured data related to gestational diabetes, the gestational diabetes nutrition diet management map which covers different symptoms of gestational diabetes and corresponding nutrition diet information is created, a scientific diet guidance of an intuitive system is provided for a gestational user in a targeted manner, the acquisition cost of a nutrition diet scheme is reduced, and therefore the management effect of gestational nutrition diet is greatly improved.
Optionally, the implementation procedure of step 110 may include:
firstly, collecting first structured data, semi-structured data and unstructured data aiming at gestational diabetes; then, extracting entity relations in the semi-structured data according to preset keywords and relation keywords contained in each type of entity to obtain second structured data; and finally, verifying the first structured data, the second structured data and the unstructured data to generate target structured data and target unstructured data related to gestational diabetes.
Specifically, the terminal device may collect first structured data and semi-structured data related to gestational diabetes on the internet by using a crawler technology, where the first structured data may be structured data related to gestational diabetes, for example, structured data of indexes such as weight, blood sugar, and sugar tolerance, and may also be structured data of symptoms such as hunger, pruritus, and the like; the semi-structured data may be semi-structured data related to nutritional diets, such as structured data for other diets that are suitable for eating, are contraindicated, etc.; the terminal device can process all data aiming at gestational diabetes in books and professional documents into identifiable and editable unstructured data by adopting OCR technology, wherein the unstructured data comprises symptom data related to gestational diabetes and nutritional diet data related to gestational diabetes.
Then, the terminal device performs extraction of entity and entity relation based on rules on the semi-structured data, for example, performs word segmentation processing on the semi-structured data by using a jieba Chinese word segmentation tool, removes "stop words" with meaning in layout such as "etc.", "class" in the semi-structured data by setting contents such as words or word segments frequently appearing in the semi-structured data as stop words, or performs relation extraction in the semi-structured data by regarding "stop words" with actual meaning such as "ok, tabu, more, less, influence, index" as entity relation, for example, when "ok/eat examples" appear in the semi-structured data: when the food is light, high in protein and high in vitamin, the entities are light, high in protein and high in vitamin, and the extracted entity relationship is suitable for eating. The semi-structured data is structured in this way, whereby the second structured data is obtained.
Finally, considering the problem that the universal word segmentation tool of jieba can cover all entities but only most entity relations during word segmentation, the second structured data can be manually verified, entities with incorrect identification such as numbers and symbols or improper word segmentation are corrected, the omitted entity relations are complemented through manual operation, so that second structured data after manual processing is obtained, and the second structured data after manual processing and the first structured data are determined to be target structured data. Considering that the OCR recognition technology refers to a technology that a terminal device converts characters in a paper document into an image file of a black-and-white lattice by adopting an optical mode for print characters on paper, and converts the characters in the image into a text format by using recognition software for further editing and processing by using word processing software, the target unstructured data obtained in this way is also inevitably error or missing, and therefore, the unstructured data also needs to be manually checked, so that the target unstructured data is obtained.
It should be noted that, a structured data set related to all diseases is obtained by using an internet terminal for a terminal device, where the structured data set includes a first structured data subset and a semi-structured data subset, at this time, the semi-structured data subset may be first extracted based on a rule and an entity relationship, and then manually checked, so as to obtain a second structured data subset, and then the first structured data subset and the second structured data subset are determined as a target structured data set, and then target structured data related to gestational diabetes is extracted from the target result data set.
According to the nutritional diet management map creation method based on gestation, the semi-structured data are converted into the second structured data in a manner of extracting entity relations from the collected semi-structured data aiming at gestational diabetes mellitus, and then the target structured data and the target unstructured data related to gestational diabetes mellitus are obtained in a manner of manually checking the first structured data, the second structured data and the target unstructured data. By combining the entity relation extraction and the manual verification, the method not only can ensure the integrity and the accuracy of the data, but also can provide sufficient data assurance for generating a rich and reliable required map later.
Optionally, the implementation procedure of step 130 may include:
firstly, determining an entity tag to be marked and an entity relationship tag to be extracted in the target unstructured data based on the nutrition diet management map body; wherein the entity tag is used to characterize the entity of the symptom and the nutritional diet information; then, word segmentation is carried out on the target unstructured data to obtain word segmentation results; further matching the word segmentation result with the entity tag; labeling a first entity in the word segmentation result when the word segmentation result is successfully matched with the entity tag; and then, based on the entity relation label, extracting the relation of the first entity to obtain a target entity relation matched with the symptom and/or the nutritional diet information in the target unstructured data.
Specifically, because the relationship extraction is performed on the target unstructured data, the emphasis is on labeling the entities existing in the target unstructured data first and then classifying the relationship among the labeled entities. Before relation extraction, the entity existing in the target unstructured data can be marked by means of the entity in the nutrient diet management map body, namely the entity existing in the nutrient diet management map body can be determined to be the entity label, the entity relation existing in the nutrient diet management map body is determined to be the entity relation label, each entity label and each entity relation label can be used as a reference basis for entity marking and entity relation extraction in the target unstructured data, and the entity labels are used for representing the relation between the entities in the nutrient diet management map body.
Based on the relation extraction of the target unstructured data, respectively setting the target unstructured data to comprise k sentence data description, and setting n entities in total in the nutrient diet management map body, wherein the number of the entity tags is n, and k and n are positive integers respectively; at this time, firstly, a named entity recognition algorithm is used for recognizing the j-th sentence data description in the target unstructured data, wherein j=1, 2, … and k; for example, a pkuseg Chinese word segmentation tool can be used for segmenting the j-th sentence data description, and a word segmentation result of the j-th sentence data description more accurate than that of a general word segmentation tool similar to jieba can be obtained by selecting a medicine field word segmentation function in a specific field word segmentation function of the pkuseg Chinese word segmentation tool; then, entity matching is carried out on the word segmentation result described by the jth sentence data and n entity tags, if the word segmentation result described by the jth sentence data and the n entity tags can be directly matched to the same description, the corresponding same description in the word segmentation result described by the jth sentence data is determined to be a first entity, and each first entity can be an entity of the nutritional diet information corresponding to the symptoms in the nutritional diet management map body and/or each symptom and existing in the target unstructured data; traversing the k sentence data description in the target unstructured data in the mode, thereby obtaining the target entity relationship among all the first entities in the target unstructured data, namely obtaining the target entity relationship matched with the symptom and/or the nutritional diet information in the nutritional diet management map body in the target unstructured data.
According to the nutritional diet management map creation method based on gestation, the entity label and the entity relation label are determined firstly based on the nutritional diet management map body, then the relation of the marked first entity is extracted in a mode of firstly word segmentation on the target structured data and then matching the word segmentation result with the entity label, and in this way, the target entity relation which can be directly matched with the entity relation in the nutritional diet management map body in the target unstructured data is rapidly extracted, so that the purpose of further improving and refining the entity relation in the nutritional diet management map body is achieved.
Optionally, after the step of matching the word segmentation result with the entity tag, the method further includes:
when the matching of the second word description in the word segmentation result and the entity tag fails, calculating a first cosine similarity between the second word description and an entity in the nutrient diet management map body; determining an entity to be aligned, a center word segment description and an adjacent word segment description from the second word segment description according to the first cosine similarity; calculating second cosine similarity between the entity to be aligned and the center word segment description and the adjacent word segment description respectively, and determining a second entity in the second word segment description based on the second cosine similarity; and extracting the relationship of the second entity in the second word description based on the entity relationship label to obtain a target entity relationship matched with the symptom and/or the nutritional diet information in the target unstructured data.
Specifically, for k sentence data description included in the target unstructured data, a pkuseg chinese word segmentation tool is used to segment a j sentence data description, and a word segmentation result of the j sentence data description is subjected to entity matching with n entity tags, in the j sentence data description, besides a successfully matched first entity, there are remaining word segmentation descriptions which are not successfully matched, at this time, an entity relationship can be extracted from the remaining word descriptions, that is, if the word segmentation result of the j sentence data description has a condition that the matching with n entity tags fails, the fact that m second word descriptions which are not successfully matched in the j sentence data description are m can be counted, then first cosine similarities of the m second word descriptions and n entities in the nutrient diet management map body are calculated, the m second word descriptions and the n entities are respectively encoded, and then m first cosine similarities of the encoding of the m second word descriptions and the encoding of the n entities are calculated, and the calculation formula is shown in formula (1).
Wherein x is m A coded representation representing m second word descriptions, y n The code representing n entities in the nutrient diet management map body represents cos theta 1 representing m x n first cosine similarities, and m and n are positive integers.
Then selecting a target cosine similarity from m x n first cosine similarities, determining an entity corresponding to the target cosine similarity as an entity to be aligned, determining a second word description corresponding to the target cosine similarity as a central word description, selecting adjacent word descriptions from the periphery of the central word description, further calculating second cosine similarities of the entity to be aligned and the central word description and the adjacent word descriptions respectively, and determining 1 second entity in the m second word descriptions based on the second cosine similarities; then removing the second word description of the second entity in the m second word descriptions, calculating (m-1) n first cosine similarities of the rest (m-1) second word descriptions and n entities in the nutrient diet management map body, and determining 1 second entity in the (m-1) second word descriptions based on the (m-1) n first cosine similarities; and so on until m second entities in the j-th sentence data description are determined. When k data descriptions exist in the target unstructured data, all second entities existing in each data description can be determined in this way, and each second entity can also be an entity of the nutritional diet information corresponding to symptoms and/or each symptom in the nutritional diet management map body existing in the target unstructured data.
And finally, based on the entity relationship label, extracting the relationship among all the second entities determined in the target unstructured data, thereby obtaining the target entity relationship among all the second entities in the target unstructured data, namely obtaining the target entity relationship matched with the symptom and/or the nutritional diet information in the nutritional diet management map body in the target unstructured data.
According to the method for creating the nutritional diet management map based on gestation, aiming at each successfully matched second word description in the target unstructured data, the second entity in the second word description is determined by calculating the first cosine similarity between the second word description and the entity in the nutritional diet management map body and calculating the second cosine similarity between the entity to be aligned and the central word description and the second cosine similarity between the entity to be aligned and the adjacent word description, and the second entity is further subjected to relation extraction, so that the target entity relation which cannot be directly matched with the entity relation in the nutritional diet management map body in the target unstructured data is extracted efficiently, and the flexibility and the reliability of extracting the target entity relation from the target unstructured data are improved.
Optionally, the determining, according to the first cosine similarity, the entity to be aligned, the center word description and the adjacent word description from the second word description includes:
Selecting a first highest cosine similarity in the first cosine similarity, determining an entity to be aligned and a center word description corresponding to the first highest cosine similarity in the second word description, and then selecting adjacent word descriptions before and after the center word description in the second word description.
Specifically, the target cosine similarity is selected for the m×n first cosine similarities, where the target cosine similarity may be a first highest cosine similarity of the m×n first cosine similarities, that is, a maximum value of the m×n first cosine similarities. For convenience of subsequent explanation, m second word descriptions that are not successfully matched in the jth sentence data description may be recorded as m token, the token corresponding to the first highest cosine similarity is used as a center-token, that is, the center word description, and the second word description corresponding to the first highest cosine similarity is determined as the entity to be aligned. And then, taking the principle of selection that the difference between the cosine similarity of the entity to be aligned and the center-token and the cosine similarity of the entity to be aligned is not more than 50%, respectively selecting p continuous tokens before and after the center-token as new-token, wherein the value of p can be 1 or 2, so that at most 4 new-token can be obtained, namely at most 4 adjacent word segmentation descriptions can be determined. It should be noted that, for (m-1) ×n first cosine similarities, the process of selecting the entity to be aligned, the description of the center word segment, and the description of the adjacent word segment may be referred to with the above process, which is not repeated herein.
According to the nutritional diet management map creation method based on gestation, the entity to be aligned and the center word segmentation description are determined by selecting the first highest cosine similarity from the plurality of first cosine similarities, and then adjacent word segmentation descriptions are further selected before and after the center word segmentation description in the second word segmentation description, so that accuracy and reliability of determining the entity to be aligned, the center word segmentation description and the adjacent word segmentation description by combining the cosine similarities are improved, and a powerful basis is provided for rapid subsequent labeling of the second entity.
Optionally, the determining, based on the second cosine similarity, a second entity in the second word description includes:
and selecting a second highest cosine similarity in the second cosine similarity, and determining a second entity corresponding to the second highest cosine similarity in the second word description.
Specifically, for m second word descriptions which are not successfully matched in the j-th sentence data description of the target unstructured data, determining at most 4 adjacent word descriptions, namely at most 4 new-token based on m x n first cosine similarities, calculating second cosine similarities of each adjacent word description and each center word description and an entity to be aligned respectively, thereby obtaining at most 5 second cosine similarities, further selecting a second highest cosine similarity from the at most 5 second cosine similarities, namely the maximum value in the at most 5 second cosine similarities, and determining that the word description corresponding to the second highest cosine similarity is 1 second entity in the m second word descriptions.
According to the method for creating the nutritional diet management map in gestation, the second entity existing in the second word description is determined by selecting the second highest cosine similarity from the plurality of second cosine similarities, and the accuracy and the reliability of determining the second entity by combining the cosine similarities are improved in the method, so that the stability of the extracted second entity is also effectively improved.
The description of the nutritional diet management profile creation apparatus for gestation provided by the present invention will be given below, and the nutritional diet management profile creation apparatus for gestation described below and the nutritional diet management profile creation method for gestation described above may be referred to correspondingly to each other.
As shown in fig. 2, the present invention provides a nutrient diet management profile creation apparatus for gestation, in fig. 2, a nutrient diet management profile creation apparatus 200 for gestation comprising:
an acquisition module 210 for acquiring target structured data and target unstructured data related to gestational diabetes; a creation module 220, configured to determine, based on the target structured data, symptoms of gestational diabetes and nutritional diet information having an association relationship with the symptoms, and create a nutritional diet management profile body for gestation based on the symptoms and the nutritional diet information; an identification module 230 for identifying a target entity relationship in the target unstructured data that matches the symptom and/or the nutritional diet information; and the fusion module 240 is configured to perform fusion processing on the nutritional diet management profile body and the target entity relationship, and generate a gestational diabetes nutritional diet management profile.
Optionally, the acquiring module 210 may be specifically configured to acquire first structured data, semi-structured data, and unstructured data for gestational diabetes; extracting entity relations in the semi-structured data according to preset keywords and relation keywords contained in each type of entity to obtain second structured data; and verifying the first structured data, the second structured data and the unstructured data to generate target structured data and target unstructured data related to gestational diabetes.
Optionally, the identifying module 230 may be specifically configured to determine, based on the nutritional diet management profile body, an entity tag to be labeled and an entity relationship tag to be extracted in the target unstructured data; wherein the entity tag is used to characterize the entity of the symptom and the nutritional diet information; performing word segmentation on the target unstructured data to obtain word segmentation results; matching the word segmentation result with the entity tag; labeling a first entity in the word segmentation result when the word segmentation result is successfully matched with the entity tag; and extracting the relation of the first entity based on the entity relation label to obtain a target entity relation matched with the symptom and/or the nutritional diet information in the target unstructured data.
Optionally, the identifying module 230 may be further configured to calculate a first cosine similarity between the second word description and the entity in the nutritional diet management map body when the matching between the second word description and the entity tag in the word segmentation result fails; determining an entity to be aligned, a center word segment description and an adjacent word segment description from the second word segment description according to the first cosine similarity; calculating second cosine similarity between the entity to be aligned and the center word segment description and the adjacent word segment description respectively, and determining a second entity in the second word segment description based on the second cosine similarity; and extracting the relationship of the second entity in the second word description based on the entity relationship label to obtain a target entity relationship matched with the symptom and/or the nutritional diet information in the target unstructured data.
Optionally, the identifying module 230 may be further specifically configured to select a first highest cosine similarity of the first cosine similarities, determine, in the second word description, a to-be-aligned entity and a center word description corresponding to the first highest cosine similarity, and then select, before and after the center word description, adjacent word descriptions in the second word description.
Optionally, the identifying module 230 may be further specifically configured to select a second highest cosine similarity among the second cosine similarities, and determine a second entity corresponding to the second highest cosine similarity in the second word description.
Optionally, the identifying module 230 may be further specifically configured to calculate a first cosine similarity between the second word description and the entity in the nutritional diet management profile body, including:
wherein x is m A coded representation representing m of said second partial word descriptions, y n And (3) coding the n entities in the nutrient diet management map body, wherein cos theta 1 represents m x n first cosine similarities, and m and n are positive integers.
Fig. 3 illustrates a physical schematic diagram of an electronic device, and as shown in fig. 3, the electronic device 300 may include: processor 310, communication interface 320, memory 330 and communication bus 340, wherein processor 310, communication interface 320 and memory 330 communicate with each other via communication bus 340. The processor 310 may invoke logic instructions in the memory 330 to perform a gestational-based nutrient diet management profile creation method comprising:
Acquiring target structured data and target unstructured data related to gestational diabetes;
determining symptoms of gestational diabetes and nutritional diet information having an association relationship with the symptoms based on the target structured data, and creating a nutritional diet management profile body of gestational period based on the symptoms and the nutritional diet information;
identifying a target entity relationship in the target unstructured data that matches the symptom and/or the nutritional diet information;
and carrying out fusion treatment on the nutrition diet management map body and the target entity relationship to generate a gestational diabetes nutrition diet management map.
Further, the logic instructions in the memory 330 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-only memory (ROM), a random access memory (RAM, randomAccessMemory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program, the computer program being storable on a non-transitory computer readable storage medium, the computer program, when executed by a processor, being capable of performing the gestational nutrient diet management profile creation method provided by the above methods, the method comprising:
acquiring target structured data and target unstructured data related to gestational diabetes;
determining symptoms of gestational diabetes and nutritional diet information having an association relationship with the symptoms based on the target structured data, and creating a nutritional diet management profile body of gestational period based on the symptoms and the nutritional diet information;
identifying a target entity relationship in the target unstructured data that matches the symptom and/or the nutritional diet information;
and carrying out fusion treatment on the nutrition diet management map body and the target entity relationship to generate a gestational diabetes nutrition diet management map.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which when executed by a processor is implemented to perform the gestational-based nutrient diet management profile creation method provided by the above methods, the method comprising:
Acquiring target structured data and target unstructured data related to gestational diabetes;
determining symptoms of gestational diabetes and nutritional diet information having an association relationship with the symptoms based on the target structured data, and creating a nutritional diet management profile body of gestational period based on the symptoms and the nutritional diet information;
identifying a target entity relationship in the target unstructured data that matches the symptom and/or the nutritional diet information;
and carrying out fusion treatment on the nutrition diet management map body and the target entity relationship to generate a gestational diabetes nutrition diet management map.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (5)
1. A gestational-based nutritional diet management profile creation method, comprising:
acquiring target structured data and target unstructured data related to gestational diabetes;
determining symptoms of gestational diabetes and nutritional diet information having an association relationship with the symptoms based on the target structured data, and creating a nutritional diet management profile body of gestational period based on the symptoms and the nutritional diet information;
identifying a target entity relationship in the target unstructured data that matches the symptom and/or the nutritional diet information;
determining an entity tag to be marked and an entity relationship tag to be extracted in the target unstructured data based on the nutrition diet management map body; wherein the entity tag is used to characterize the entity of the symptom and the nutritional diet information;
performing word segmentation on the target unstructured data to obtain word segmentation results;
matching the word segmentation result with the entity tag;
labeling a first entity in the word segmentation result when the word segmentation result is successfully matched with the entity tag;
based on the entity relation tag, relation extraction is carried out on the first entity, and a target entity relation matched with the symptom and/or the nutritional diet information in the target unstructured data is obtained;
After the step of matching the word segmentation result with the entity tag, the method further includes:
when the matching of the second word description in the word segmentation result and the entity tag fails, calculating a first cosine similarity between the second word description and an entity in the nutrient diet management map body;
determining an entity to be aligned, a center word segment description and an adjacent word segment description from the second word segment description according to the first cosine similarity;
calculating second cosine similarity between the entity to be aligned and the center word segment description and the adjacent word segment description respectively, and determining a second entity in the second word segment description based on the second cosine similarity;
based on the entity relation tag, carrying out relation extraction on the second entity in the second word description to obtain a target entity relation matched with the symptom and/or the nutritional diet information in the target unstructured data;
the determining the entity to be aligned, the center word description and the adjacent word description from the second word description according to the first cosine similarity comprises the following steps:
selecting a first highest cosine similarity in the first cosine similarity, determining an entity to be aligned and a center word segmentation description corresponding to the first highest cosine similarity in the second word segmentation description, and then selecting adjacent word segmentation descriptions before and after the center word segmentation description in the second word segmentation description;
The determining, based on the second cosine similarity, a second entity in the second word description includes:
selecting a second highest cosine similarity in the second cosine similarities, and determining a second entity corresponding to the second highest cosine similarity in the second word description;
the calculating a first cosine similarity of the second part-word description to an entity within the nutritional diet management profile body comprises:
wherein x is m A coded representation representing m of said second partial word descriptions, y n The encoding of n entities in the nutrient diet management map body is represented, cos theta 1 represents m x n first cosine similarity, and m and n are positive integers;
and carrying out fusion treatment on the nutrition diet management map body and the target entity relationship to generate a gestational diabetes nutrition diet management map.
2. The gestational-based nutrient diet management profile creation method of claim 1, wherein the acquiring the target structured data and the target unstructured data related to gestational diabetes comprises:
collecting first structured data, semi-structured data and unstructured data for gestational diabetes;
Extracting entity relations in the semi-structured data according to preset keywords and relation keywords contained in each type of entity to obtain second structured data;
and verifying the first structured data, the second structured data and the unstructured data to generate target structured data and target unstructured data related to gestational diabetes.
3. A nutritional diet management profile creation apparatus for gestation period, comprising:
the acquisition module is used for acquiring target structured data and target unstructured data related to gestational diabetes;
the creation module is used for determining the symptom of gestational diabetes and nutritional diet information with an association relation with the symptom based on the target structural data, and creating a nutritional diet management map body in gestation based on the symptom and the nutritional diet information;
the identifying module is used for identifying a target entity relationship matched with the symptom and/or the nutritional diet information in the target unstructured data;
determining an entity tag to be marked and an entity relationship tag to be extracted in the target unstructured data based on the nutrition diet management map body; wherein the entity tag is used to characterize the entity of the symptom and the nutritional diet information;
Performing word segmentation on the target unstructured data to obtain word segmentation results;
matching the word segmentation result with the entity tag;
labeling a first entity in the word segmentation result when the word segmentation result is successfully matched with the entity tag;
based on the entity relation tag, relation extraction is carried out on the first entity, and a target entity relation matched with the symptom and/or the nutritional diet information in the target unstructured data is obtained;
after the step of matching the word segmentation result with the entity tag, the method further comprises the following steps:
when the matching of the second word description in the word segmentation result and the entity tag fails, calculating a first cosine similarity between the second word description and an entity in the nutrient diet management map body;
determining an entity to be aligned, a center word segment description and an adjacent word segment description from the second word segment description according to the first cosine similarity;
calculating second cosine similarity between the entity to be aligned and the center word segment description and the adjacent word segment description respectively, and determining a second entity in the second word segment description based on the second cosine similarity;
Based on the entity relation tag, carrying out relation extraction on the second entity in the second word description to obtain a target entity relation matched with the symptom and/or the nutritional diet information in the target unstructured data;
the determining the entity to be aligned, the center word description and the adjacent word description from the second word description according to the first cosine similarity comprises the following steps:
selecting a first highest cosine similarity in the first cosine similarity, determining an entity to be aligned and a center word segmentation description corresponding to the first highest cosine similarity in the second word segmentation description, and then selecting adjacent word segmentation descriptions before and after the center word segmentation description in the second word segmentation description;
the determining, based on the second cosine similarity, a second entity in the second word description includes:
selecting a second highest cosine similarity in the second cosine similarities, and determining a second entity corresponding to the second highest cosine similarity in the second word description;
the calculating a first cosine similarity of the second part-word description to an entity within the nutritional diet management profile body comprises:
Wherein x is m A coded representation representing m of said second partial word descriptions, y n A coded representation of n entities within the nutritional diet management profile, cos θ1 representing m×n of said first cosine similarities, m andn is a positive integer;
and the fusion module is used for carrying out fusion treatment on the nutrition diet management map body and the target entity relationship to generate a gestational diabetes nutrition diet management map.
4. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the gestational-based nutritional diet management profile creation method of any one of claims 1 to 2 when the program is executed.
5. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the gestational-based nutritional diet management profile creation method of any one of claims 1 to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210293527.2A CN114758749B (en) | 2022-03-23 | 2022-03-23 | Nutritional diet management map creation method and device based on gestation period |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210293527.2A CN114758749B (en) | 2022-03-23 | 2022-03-23 | Nutritional diet management map creation method and device based on gestation period |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114758749A CN114758749A (en) | 2022-07-15 |
| CN114758749B true CN114758749B (en) | 2023-08-25 |
Family
ID=82327283
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210293527.2A Active CN114758749B (en) | 2022-03-23 | 2022-03-23 | Nutritional diet management map creation method and device based on gestation period |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114758749B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116417115B (en) * | 2023-06-07 | 2023-12-01 | 北京四海汇智科技有限公司 | Personalized nutrition scheme recommendation method and system for gestational diabetes patients |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
| CN109669994A (en) * | 2018-12-21 | 2019-04-23 | 吉林大学 | A kind of construction method and system of health knowledge map |
| CN111341456A (en) * | 2020-02-21 | 2020-06-26 | 中南大学湘雅医院 | Method and device for generating diabetic foot knowledge map and readable storage medium |
| CN111883230A (en) * | 2019-12-18 | 2020-11-03 | 深圳数字生命研究院 | Method and device for generating diet data, storage medium and electronic device |
| CN112507108A (en) * | 2020-11-25 | 2021-03-16 | 北京明略软件系统有限公司 | Knowledge extraction method and system based on json rule file and rule analysis engine |
| CN113590837A (en) * | 2021-07-29 | 2021-11-02 | 华中农业大学 | Deep learning-based food and health knowledge map construction method |
-
2022
- 2022-03-23 CN CN202210293527.2A patent/CN114758749B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
| CN109669994A (en) * | 2018-12-21 | 2019-04-23 | 吉林大学 | A kind of construction method and system of health knowledge map |
| CN111883230A (en) * | 2019-12-18 | 2020-11-03 | 深圳数字生命研究院 | Method and device for generating diet data, storage medium and electronic device |
| CN111341456A (en) * | 2020-02-21 | 2020-06-26 | 中南大学湘雅医院 | Method and device for generating diabetic foot knowledge map and readable storage medium |
| CN112507108A (en) * | 2020-11-25 | 2021-03-16 | 北京明略软件系统有限公司 | Knowledge extraction method and system based on json rule file and rule analysis engine |
| CN113590837A (en) * | 2021-07-29 | 2021-11-02 | 华中农业大学 | Deep learning-based food and health knowledge map construction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114758749A (en) | 2022-07-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jimeno Yepes et al. | ICDAR 2021 competition on scientific literature parsing | |
| CN112015917A (en) | Data processing method and device based on knowledge graph and computer equipment | |
| CN110569349B (en) | Method, system, equipment and storage medium for pushing ill teaching article based on big data | |
| CN112800766A (en) | Chinese medical entity identification and labeling method and system based on active learning | |
| CN113611405A (en) | Physical examination item recommendation method, device, equipment and medium | |
| CN114913942A (en) | Intelligent matching method and device for patient recruitment projects | |
| CN114912887B (en) | Clinical data input method and device based on electronic medical record | |
| CN113724830B (en) | Medication risk detection method based on artificial intelligence and related equipment | |
| CN114758749B (en) | Nutritional diet management map creation method and device based on gestation period | |
| CN108280389A (en) | Medical bill ICR identifying systems and its medical bank slip recognition method | |
| CN116992839B (en) | Automatic generation method, device and equipment for medical records front page | |
| CN113111159A (en) | Question and answer record generation method and device, electronic equipment and storage medium | |
| CN113707301A (en) | Remote inquiry method, device, equipment and medium based on artificial intelligence | |
| CN118364088A (en) | Medical literature intelligent question-answering system and method based on RAG and LLM technology | |
| CN113610375A (en) | Warranty underwriting method and underwriting device based on natural language processing | |
| CN115985506A (en) | Information extraction method and device, storage medium and computer equipment | |
| CN113435194B (en) | Vocabulary segmentation method and device, terminal equipment and storage medium | |
| CN114334049B (en) | Method, device and equipment for structuring electronic medical record | |
| CN112561714B (en) | Nuclear protection risk prediction method and device based on NLP technology and related equipment | |
| CN108231200A (en) | It is a kind of that strategy generation method is seen a doctor based on topic model and ILP | |
| Bhaskoro et al. | An extraction of medical information based on human handwritings | |
| Butala et al. | Natural language parser for physician’s handwritten prescription | |
| Bodile et al. | Text mining in radiology reports by statistical machine translation approach | |
| Dinh et al. | Unsupervised medical image classification by combining case-based classifiers | |
| CN112053760A (en) | Medication guide method, medication guide device, and computer-readable 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 |