CN113889209A - Recommendation system and storage medium for health management service products - Google Patents
Recommendation system and storage medium for health management service products Download PDFInfo
- Publication number
- CN113889209A CN113889209A CN202111126143.3A CN202111126143A CN113889209A CN 113889209 A CN113889209 A CN 113889209A CN 202111126143 A CN202111126143 A CN 202111126143A CN 113889209 A CN113889209 A CN 113889209A
- Authority
- CN
- China
- Prior art keywords
- health
- module
- user
- recommendation
- recommendation system
- 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.)
- Pending
Links
- 230000036541 health Effects 0.000 title claims abstract description 109
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 238000005259 measurement Methods 0.000 claims abstract description 5
- 238000012216 screening Methods 0.000 claims description 10
- 201000010099 disease Diseases 0.000 claims description 8
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 8
- 239000013598 vector Substances 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 230000008707 rearrangement Effects 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 2
- 230000035790 physiological processes and functions Effects 0.000 claims description 2
- 208000024891 symptom Diseases 0.000 claims description 2
- 230000003862 health status Effects 0.000 claims 2
- 238000000034 method Methods 0.000 abstract description 6
- 230000008901 benefit Effects 0.000 abstract description 2
- 239000000047 product Substances 0.000 description 36
- 206010058467 Lung neoplasm malignant Diseases 0.000 description 9
- 201000005202 lung cancer Diseases 0.000 description 9
- 208000020816 lung neoplasm Diseases 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 6
- 230000000391 smoking effect Effects 0.000 description 4
- 208000004998 Abdominal Pain Diseases 0.000 description 3
- 235000008694 Humulus lupulus Nutrition 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 206010012601 diabetes mellitus Diseases 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000439 tumor marker Substances 0.000 description 2
- 208000008035 Back Pain Diseases 0.000 description 1
- 208000020084 Bone disease Diseases 0.000 description 1
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 208000008930 Low Back Pain Diseases 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- LEHOTFFKMJEONL-UHFFFAOYSA-N Uric Acid Chemical compound N1C(=O)NC(=O)C2=C1NC(=O)N2 LEHOTFFKMJEONL-UHFFFAOYSA-N 0.000 description 1
- TVWHNULVHGKJHS-UHFFFAOYSA-N Uric acid Natural products N1C(=O)NC(=O)C2NC(=O)NC21 TVWHNULVHGKJHS-UHFFFAOYSA-N 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 206010003549 asthenia Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 208000026106 cerebrovascular disease Diseases 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000015872 dietary supplement Nutrition 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000035935 pregnancy Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 229940116269 uric acid Drugs 0.000 description 1
- 229960005486 vaccine Drugs 0.000 description 1
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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Epidemiology (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to a recommendation system and a storage medium of a health management service product, which relate to the field of medical health and comprise a knowledge map module and a recommendation system module; performing measurement calculation on the correlation between the user and the health management service product by using the knowledge graph module, the recommendation system module and the health state of the user; the knowledge graph module is used for generating service product recommendation reasons described by natural language and explaining the logic of recommended products; the recommendation method and the recommendation system have the advantages that the recommendation of the health management service products is carried out for the users through the combination of the knowledge map and the recommendation technology, the problems that the reliability of the recommendation system of the health management service products is low and the recommendation reason is not clear are effectively solved, the recommendation path is more scientific and accurate, the recommendation reason is clearer and more understandable, the recommendation system better meets the user requirements in the health management scene, and the health management effectiveness and the customer satisfaction of the users are improved.
Description
Technical Field
The invention relates to the field of medical treatment and health, in particular to a recommendation system and a storage medium of health management service products.
Background
With the development of society and the improvement of health consciousness of people, health management services gradually enter the lives of everyone. Whether the health examination, the risk assessment or the health intervention is carried out, a large amount of health management services or products can be selected by the user in each stage, but the health management knowledge of the user is very limited, and reasonable purchasing decisions cannot be made, so that the user needs to be assisted by the intervention of the knowledge in the professional field to select. The conventional method is to make one-to-one consultation with health management experts, provide suggestions and complete decisions by using the background knowledge and communication of the experts, but the method has high cost of money and time and cannot meet the requirements of most users.
In order to solve the above problems, workers in the art have conducted various studies:
chinese patent application 201710155797.6 discloses a health management system, which can take the health condition of a user as the center, record and analyze the health condition of the user for a long time, construct a health file, and provide professional health assessment and health guidance for the user. In addition, the health analysis method can provide reference for the user when selecting physical examination packages and insurance products under the personal permission of the user according to the health analysis result, and helps the user to quickly find products suitable for the user. Different from other health management systems, the system can transfer the traditional health management, insurance and physical examination services to the online and create an insurance, physical examination and user health integrated system.
According to the technical scheme, long-term recording and analysis are only carried out on the health condition of the user, a health file is constructed, professional health assessment and health guidance can be provided for the user, traditional health management, insurance and physical examination services are transferred to the online, reference is provided for the user when a physical examination package and insurance products are selected and purchased according to the health analysis result, and the user is helped to quickly find products suitable for the user. However, the complete logic analysis is not provided for the client, and the natural language description service product recommendation reason is not generated, so that the client has doubts about the products provided in the proposal and has poor credibility, and the client is difficult to select the products from the recommended proposal.
Therefore, there is a need for further improvement of the recommendation system and storage medium of health management service products to solve the above-mentioned disadvantages.
Disclosure of Invention
The purpose of the application is: the recommendation method and the recommendation system for the health management service product solve and overcome the defects of the prior art and the application, effectively solve the problems that the reliability of the recommendation system for the health management service product is not high, and the recommendation reason is not clear, are more scientific and accurate, and the recommendation reason is clearer and more understandable, so that the recommendation system better meets the user requirements in the health management scene, and the health management effectiveness and the customer satisfaction of the user are improved.
The recommendation system for the health management service product comprises a knowledge graph module and a recommendation system module;
performing measurement calculation on the correlation between the user and the health management service product by using the knowledge graph module, the recommendation system module and the health state of the user;
the knowledge graph module is used for generating service product recommendation reasons described by natural language and explaining the logic of recommended products;
preferably, the knowledge-graph module comprises:
the user portrait module is used for constructing the relationship between a user entity and a portrait label by utilizing the physiological state and the social relationship of the user, the portrait label is abstract description of the current health state of the user, the labels also have mutual relationship, for example, the labels have a subordinate relationship between abdominal pain and abdominal pain, the labels have a reasoning relationship between fasting blood sugar and diabetes high risk, and the portrait label which is possibly not discovered by the user can be intelligently mined by utilizing the relationship between the labels;
the health demand module abstracts the health demand of the user and helps the user to manage and control the health risk of the user, the health demand module is composed of health demand entities and relations among the health demand entities, and the health demand entities are mainly divided into four categories: discomfort symptoms (such as lumbago, abdominal pain, asthenia and the like), disease screening (such as middle-aged cardiovascular and cerebrovascular disease early screening, senile bone disease screening, common tumor screening and the like), disease reexamination (such as diabetes reexamination, uric acid abnormality reexamination and the like), risk factors (such as smoking-related disease examination, dust environment disease examination and the like);
the service product module is used for combing products or services (such as physical examination items, nutritional supplements, insurance products, vaccines, treatment services and the like) which can be purchased in an actual business scene, constructing the relationship between the products or services and the health requirements of the user and preparing for reasoning in a recommendation system;
the medical knowledge module integrates knowledge in medical fields such as diseases, indexes, parts, departments and the like, and represents the medical knowledge in text forms such as documents and books in the form of a graph.
The modules respectively depict and describe the health state, health requirement, health management service products and medical knowledge of a user, a whole set of health management knowledge graph is formed by building the attributes of entities and the relationship between the entities, the implicit relationship buried under the conventional table structure data can be deduced by using the information in the knowledge graph, the implicit relationship is usually identified by the relationship link of two hops, three hops and even more hops, the common data result is difficult to identify visually, the understanding level of the health state and the health requirement of the user can be deepened by using the implicit relationship, so that the health risk of the user can be discovered more timely, the loophole of health management is complemented, and effective health management service products are recommended for the user.
Different from the traditional recommendation system based on data statistics and numerical calculation, the inference path based on the knowledge graph can generate service product recommendation reasons described by natural language through integration and organization, on one hand, the inference system explains the logic of recommended products and eliminates the confusion of users when selecting and purchasing, on the other hand, the users can absorb and understand health management knowledge in the process of reading the recommendation reasons, the health management awareness is improved, and the health education is profoundly subordinated. For example, if the user has risk factors of "passive smoking", ages over "40 years, and a" family history of lung cancer ", the user has a health management requirement of" lung cancer screening ", and the user can be recommended a lung cancer related examination item, such as" low dose chest CT ", and the recommendation reason for this item, the" low dose chest CT ", can include a recommendation logic, for example, the recommendation reason can be a complete sentence" in view of your age, passive smoking, and family history information of lung cancer, we recommend you to screen lung cancer, and low dose chest CT is the most effective means for lung cancer screening, and can effectively reduce your health risk. The "lung cancer" may be a set of tags such as "over age # 40", "family history of" lung cancer "," passive smoking "," screening of "lung cancer".
Preferably, the recommendation system module comprises:
the system comprises a recalling module, a recommendation module and a recommendation module, wherein the recalling module is used for selecting services or products meeting the health requirements of users from a large number of candidate sets by using a knowledge map, and delineating the approximate range of recommended items;
the rough arrangement module is used for sorting the recalled items in a rough granularity mode by utilizing the reasoning path and the entity attributes, filtering a part of items with lower matching degree, reducing the number of the recalled sets, only one item capable of completely covering the health requirements may be reserved for the similar health requirements, and filtering the items with the same effectiveness;
the fine ranking module is used for calculating the matching degree between the items and the users by utilizing all available dimensions, fine ranking relies on a deep learning-based graph embedding neural network, the reasonability of the sequence between the items is improved, graph embedding vectors capable of representing the health state of the users and graph embedding vectors capable of representing the function of the items are input into a similarity measurement model for calculation, the obtained scores are used as the basis of the fine ranking, and the model is trained and optimized according to on-line real-time data;
the combination module combines some service products in the result, recommends in the form of package or service package, reduces the selection cost of users, improves the purchase intention, for example, a plurality of items related to the tumor marker can be combined and replaced by a 'tumor marker package';
and the rearrangement module is used for readjusting the combined result by combining the service scene and the sales logic on the basis of combination to form a final recommendation result.
The invention also provides a computer-readable storage medium storing a computer program executable by a computer processor to execute computer-readable instructions implementing a recommendation system according to any one of claims 1 to 6.
Compared with the prior art, the application has the following obvious advantages and effects:
1. in the invention, a user portrait module, a health requirement module, a service product module and a medical knowledge module respectively depict and describe the health state, the health requirement, a health management service product and medical knowledge of a user, a whole set of health management knowledge map is formed by constructing the attributes of entities and the relationship between the entities, and the implicit relationship buried under the structural data of a conventional table can be deduced by utilizing the information in the knowledge map, so that the understanding level of the health state and the health requirement of the user is deepened, the health risk of the user is discovered more timely, and effective health management service products are recommended.
2. In the invention, different from the traditional recommendation system based on data statistics and numerical calculation, the reasoning path based on the knowledge graph can generate the service product recommendation reason described by natural language through integration and organization, on one hand, the reasoning path explains the logic of the recommended product and eliminates the confusion of users when selecting and purchasing, on the other hand, the users can absorb and understand the health management knowledge in the process of reading the recommendation reason, the health management consciousness is improved, and the system is subjected to the subtler health education.
3. The recommendation path is more scientific and accurate, the recommendation reason is clearer and more understandable, the recommendation system better meets the user requirements in the health management scene, and the health management effectiveness and the customer satisfaction of the user are improved.
Drawings
Fig. 1 is an overall architecture diagram of the present application.
FIG. 2 is a schematic diagram of the structure of a knowledge-graph module in the present application.
FIG. 3 is a flow chart of the processing of the recommendation system module of the present application.
Reference numbers in this application:
the system comprises a knowledge graph module 1, a user portrait module 11, a health requirement module 12, a service product module 13, a medical knowledge module 14, a database 15, an inference mode 16, an image quantity 17, a recommendation system 2, a recall 21, a candidate set 211, a bold line 22, a fine line 23, a neural network 231, a combination 24, a package combination 241, a rearrangement 25, a business rule 251, a medical database 3, a medical expert 4 and a recommendation result 5.
Detailed Description
Specific embodiments thereof are described below in conjunction with the following description and the accompanying drawings to teach those skilled in the art how to make and use the best mode of the present application. For the purpose of teaching application principles, the following conventional aspects have been simplified or omitted. Those skilled in the art will appreciate variations from these embodiments that fall within the scope of the application. Those skilled in the art will appreciate that the features described below can be combined in various ways to form multiple variations of the present application. In the present application, the terms "upper", "lower", "left", "right", "middle" and "one" are used for clarity of description, and are not used to limit the scope of the invention, and the relative relationship between the terms and the corresponding terms may be changed or adjusted without substantial technical change. Thus, the present application is not limited to the specific embodiments described below, but only by the claims and their equivalents.
Fig. 1 to 3 show a specific embodiment of the recommendation system 2 for health management service products of the present application.
The knowledge graph module 1 comprises four knowledge modules in the health management field: a user imaging module 11, a health needs module 12, a service products module 13, and a medical knowledge module 14. Each module respectively depicts and describes the health state, health requirement, health management service product and medical knowledge of the user, and a whole set of health management knowledge map is formed through the construction of the attributes of the entities and the relationship among the entities.
The implementation of the knowledge graph comprises three aspects of construction, storage and application.
In view of the requirement of the medical health field for knowledge accuracy, knowledge required by knowledge map construction needs to be acquired from a professional medical database 3 or labeled by a medical expert 4, the knowledge comprises two parts of entity attributes and relations, and metadata of the attributes and the relations can be defined and constrained through a mode, so that management and application are facilitated.
Generally, a special graph database 15 is selected to store knowledge, and the graph database 15 performs a large amount of optimization on the storage, query and analysis of data results such as graphs, thereby being beneficial to subsequent application scenarios.
In application, the knowledge graph mainly performs two aspects of implementation.
In one aspect, the inference patterns 16 defining the item recommendations, the matching patterns specifying the inferred paths, the specific inference path needs to be defined, the start node, the end node, and the attributes of the paths, such as the number of passing nodes, the attributes of passing edges, the specific definition of these rules depends on the choice of the graph database 15, and different query languages are used for different graph databases 15.
On the other hand, the user and the project need to be trained by the embedded vector 17, a specific embedded vector generation algorithm can be selected according to the service data, and after training is completed, a low-dimensional vector mapped in the same semantic space can be obtained according to the user ID and the project ID.
The recommendation system 2 is implemented to deploy models or projects according to algorithms at various stages.
The recall stage 21 is to mainly use the knowledge graph to perform screening of the candidate set 211, and the screening rule is based on the recommendation path defined in the knowledge graph application stage. Because the reason for the recommendation is generated at a later stage, only the IDs of the items in the candidate set 211 of recalls 21 cannot be returned at this stage, and the full inference path is preserved.
In the rough arrangement 22 stage, the recommendation items which are too similar are removed according to the attributes and the relations among the items, and meanwhile, some too long paths are also removed, so that the risk association is not a particularly strong path, the accurate range of the user recommendation result 5 is narrowed, and the number of subsequent calculations is reduced.
In refinement 23, the neural network 231 model is used to predict the similarity between the user and the project, and the input of the model is the embedded vector trained from the knowledge graph.
According to the business situation and the sales strategy, different recommended items can be combined 24 to form different business sales packages, then the packages are recommended for the user in a unified mode, so that the understanding cost of the user can be lower, the purchase intention can be enhanced, the strategy of the combination 24 mainly matches the coverage degree of the recommendation result 5 to the package combination 241 items, and the package combination 241 with higher coverage degree is recommended preferentially.
The rearrangement 25 stage mainly uses the business rules 251 and other dimension requirements (such as daily allowance of the number of people for examining the organization project, the pregnancy preparation requirement of the user, etc.) to perform final sorting, filtering and integration, and uniformly generates the recommendation result 5 (recommendation reason).
All or part of the processes in the above embodiments are implemented by a computer program instructing associated hardware, and the computer software product is stored in a computer readable storage medium, which can be any portable computer program code entity apparatus or device, for example, a usb disk, a removable magnetic disk, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, and the like.
Since any modifications, equivalents, improvements, etc. made within the spirit and principles of the application may readily occur to those skilled in the art, it is intended to be included within the scope of the claims of this application.
Claims (7)
1. A recommendation system of health management service products is characterized by comprising a knowledge graph module and a recommendation system module;
performing measurement calculation on the correlation between the user and the health management service product by using the knowledge graph module, the recommendation system module and the health state of the user;
and the knowledge graph module is used for generating service product recommendation reasons described by natural language and explaining the logic of recommended products.
2. The recommendation system for a health management service product as claimed in claim 1, wherein said knowledge-graph module comprises:
the user portrait module is used for constructing the relationship between the user entity and the portrait label by utilizing the physiological state and the social relationship of the user;
the health requirement module abstracts the health requirements of the users and helps the users to control the health risks, and the health requirement module consists of health requirement entities and relations among the health requirement entities;
the service product module is used for combing products or services which can be purchased in an actual business scene and constructing a relationship between the products or services and the health requirements of the user;
the medical knowledge module integrates knowledge in medical fields such as diseases, indexes, parts, departments and the like, and represents the medical knowledge in text forms such as documents and books in the form of a graph.
3. The recommendation system for a health management service product as claimed in claim 1, wherein said recommendation system module comprises:
the recall module is used for selecting services or products meeting the health requirements of the user from a large number of candidate sets by using a knowledge map and delineating the approximate range of recommended items;
the rough arrangement module is used for sorting the recalled items in a coarse granularity mode by using the reasoning path and the entity attributes, filtering a part of items with lower matching degree and reducing the number of the recalled sets;
the fine ranking module is used for calculating the matching degree between the items and the users by utilizing multiple dimensions;
the combination module is used for combining some service products in the result and recommending the service products in a package or service pack form, so that the selection cost of a user is reduced;
and the rearrangement module is used for readjusting the combined result by combining the service scene and the sales logic on the basis of combination to form a final recommendation result.
4. The recommendation system of claim 2, wherein the portrait tags are abstract descriptions of the current health status of the user, the tags have mutual relationships, and the portrait tags that may not be detected by the user can be intelligently mined by using the relationships between the tags.
5. The recommendation system of claim 2, wherein said health need entities are classified mainly into discomfortable symptom class, disease screening class, disease review class, risk factor class.
6. The recommendation system of a health management service product according to claim 3, wherein the fine ranking is based on a deep learning graph-embedded neural network, graph-embedded vectors capable of representing the health status of the user and graph-embedded vectors capable of representing the functional actions of the project are input into a similarity measurement model for calculation, the obtained scores are used as the basis of the fine ranking, and the model is trained and optimized according to on-line real-time data.
7. A computer-readable storage medium, in which a computer program is stored, wherein the computer program is executable by a computer processor to execute computer-readable instructions implementing the recommendation system according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111126143.3A CN113889209A (en) | 2021-09-26 | 2021-09-26 | Recommendation system and storage medium for health management service products |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111126143.3A CN113889209A (en) | 2021-09-26 | 2021-09-26 | Recommendation system and storage medium for health management service products |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113889209A true CN113889209A (en) | 2022-01-04 |
Family
ID=79006612
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111126143.3A Pending CN113889209A (en) | 2021-09-26 | 2021-09-26 | Recommendation system and storage medium for health management service products |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113889209A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115547457A (en) * | 2022-10-14 | 2022-12-30 | 广东省第二人民医院（广东省卫生应急医院） | Intelligent recipe recommendation method, device, equipment and medium based on physical examination data |
| CN115905702A (en) * | 2022-12-06 | 2023-04-04 | 鄄城县馨宁网络科技有限公司 | Data recommendation method and system based on user demand analysis |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109885772A (en) * | 2019-02-27 | 2019-06-14 | 上海优谦智能科技有限公司 | The education content personalized recommendation system of knowledge based map |
| CN110221817A (en) * | 2019-06-17 | 2019-09-10 | 北京酷我科技有限公司 | A kind of data recall module and recommender system |
| US20190392924A1 (en) * | 2018-06-20 | 2019-12-26 | International Business Machines Corporation | Intelligent recommendation of useful medical actions |
| CN112182412A (en) * | 2020-11-26 | 2021-01-05 | 南京吉拉福网络科技有限公司 | Method, computing device, and computer storage medium for recommending physical examination items |
| CN112801760A (en) * | 2021-03-30 | 2021-05-14 | 南京蓝鲸人网络科技有限公司 | Sequencing optimization method and system of content personalized recommendation system |
-
2021
- 2021-09-26 CN CN202111126143.3A patent/CN113889209A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190392924A1 (en) * | 2018-06-20 | 2019-12-26 | International Business Machines Corporation | Intelligent recommendation of useful medical actions |
| CN109885772A (en) * | 2019-02-27 | 2019-06-14 | 上海优谦智能科技有限公司 | The education content personalized recommendation system of knowledge based map |
| CN110221817A (en) * | 2019-06-17 | 2019-09-10 | 北京酷我科技有限公司 | A kind of data recall module and recommender system |
| CN112182412A (en) * | 2020-11-26 | 2021-01-05 | 南京吉拉福网络科技有限公司 | Method, computing device, and computer storage medium for recommending physical examination items |
| CN112801760A (en) * | 2021-03-30 | 2021-05-14 | 南京蓝鲸人网络科技有限公司 | Sequencing optimization method and system of content personalized recommendation system |
Non-Patent Citations (1)
| Title |
|---|
| 刘辉等: "个性化推荐系统综述", 《常州大学学报（自然科学版）》, vol. 29, no. 3, 31 May 2017 (2017-05-31), pages 51 - 59 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115547457A (en) * | 2022-10-14 | 2022-12-30 | 广东省第二人民医院（广东省卫生应急医院） | Intelligent recipe recommendation method, device, equipment and medium based on physical examination data |
| CN115547457B (en) * | 2022-10-14 | 2023-06-30 | 广东省第二人民医院（广东省卫生应急医院） | Recipe intelligent recommendation method, device, equipment and medium based on physical examination data |
| CN115905702A (en) * | 2022-12-06 | 2023-04-04 | 鄄城县馨宁网络科技有限公司 | Data recommendation method and system based on user demand analysis |
| CN115905702B (en) * | 2022-12-06 | 2023-10-10 | 雨果跨境(厦门)科技有限公司 | Data recommendation method and system based on user demand analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Linden et al. | Conducting sensitivity analysis for unmeasured confounding in observational studies using E-values: the evalue package | |
| Joel et al. | Is romantic desire predictable? Machine learning applied to initial romantic attraction | |
| Beam et al. | Translating artificial intelligence into clinical care | |
| Keshavan et al. | Combining citizen science and deep learning to amplify expertise in neuroimaging | |
| Dey et al. | Big data analytics for intelligent healthcare management | |
| Lovell et al. | Skin color, racial identity, and life chances in Brazil | |
| CN104636430B (en) | Case base represents and case similarity acquisition methods and system | |
| Mosier | I. Problems and designs of cross-validation 1 | |
| Haviland et al. | Group-based trajectory modeling extended to account for nonrandom participant attrition | |
| JERVIS | Phenylpyruvic oligophrenia: Introductory study of fifty cases of mental deficiency associated with excretion of phenylpyruvic acid | |
| Arabie et al. | Overlapping clustering: A new method for product positioning | |
| Kassahun et al. | Automatic classification of epilepsy types using ontology-based and genetics-based machine learning | |
| Archenaa et al. | Health recommender system using big data analytics | |
| Wang et al. | Idiosyncratic tower of Babel: Individual differences in word-meaning representation increase as word abstractness increases | |
| Oliveira et al. | Neuroscience research in consumer behavior: A review and future research agenda | |
| CN113889209A (en) | Recommendation system and storage medium for health management service products | |
| Lage et al. | Learning interpretable concept-based models with human feedback | |
| Zhong et al. | Hierarchical reinforcement learning for automatic disease diagnosis | |
| Armstrong | Clinical prediction and the idea of a population | |
| Sandberg et al. | Individual, community, and social network influences on beliefs concerning the acceptability of intimate partner violence in rural Senegal | |
| Nayak et al. | An Intelligent Disease Prediction and Drug Recommendation Prototype by Using Multiple Approaches of Machine Learning Algorithms | |
| Choi et al. | Classification and sequential pattern analysis for improving managerial efficiency and providing better medical service in public healthcare centers | |
| Dedhia et al. | SCouT: synthetic counterfactuals via spatiotemporal transformers for actionable healthcare | |
| CN114902230A (en) | Improved utterance parsing | |
| Ali et al. | KARE: A hybrid reasoning approach for promoting active lifestyle |
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 |