CN116364240B - Remote nutrition information processing method and system based on Internet - Google Patents
Remote nutrition information processing method and system based on Internet Download PDFInfo
- Publication number
- CN116364240B CN116364240B CN202310093769.1A CN202310093769A CN116364240B CN 116364240 B CN116364240 B CN 116364240B CN 202310093769 A CN202310093769 A CN 202310093769A CN 116364240 B CN116364240 B CN 116364240B
- Authority
- CN
- China
- Prior art keywords
- user
- recommendation
- personal information
- processing server
- recommendation model
- 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
- 235000016709 nutrition Nutrition 0.000 title claims abstract description 58
- 230000035764 nutrition Effects 0.000 title claims abstract description 46
- 230000010365 information processing Effects 0.000 title claims abstract description 9
- 238000003672 processing method Methods 0.000 title claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 87
- 239000013598 vector Substances 0.000 claims description 69
- 238000000034 method Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 8
- 238000012550 audit Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 description 8
- 238000012552 review Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000004171 remote diagnosis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- 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
- G06F16/90—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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Nutrition Science (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to a remote nutrition information processing method and system based on the Internet, wherein the system comprises a user client, a doctor client and a processing server which are connected through the Internet, and the processing server comprises a user database, a scheme database, a basic recommendation model and a quick recommendation model. The processing server selects a corresponding recommendation model according to the personal information uploaded by the user client to generate a recommended nutrition scheme, so that quick service response can be provided for large-scale users on the Internet.
Description
[ field of technology ]
The invention belongs to the field of telemedicine, and particularly relates to a remote nutrition information processing method and system based on the Internet.
[ background Art ]
The hospital nutrition doctors can evaluate the nutrition of the patients according to the personal conditions of the patients, such as height, weight, diet intake condition, current illness condition, past medical history and the like, and can provide corresponding nutrition support schemes according to personalized nutrition guidance of the evaluation conditions.
With the rise of the internet, patients can be subjected to remote diagnosis and treatment through the internet at present. By means of remote medical treatment on the Internet, a nutritional doctor can provide personalized nutritional guidance for patients and common users. However, because of the large number of internet users, there is a great demand for nutrition guidance, and the number of doctors participating in remote nutrition guidance is small, it is difficult to satisfy the large-scale demand of the internet. For this reason, methods for analyzing and recommending nutrition guidance schemes through a computer have been developed, that is, a recommendation model is run by a computer to analyze personal information provided by users, a nutrition guidance scheme is recommended according to the personal information, and then a doctor reviews and adjusts the recommended scheme, so that the workload of the doctor can be reduced, and the doctor can serve more users
However, if accurate recommendation is required, the calculation time of the existing recommendation model is generally longer, so that the user needs to wait for a longer time, and the user experience is poor.
[ invention ]
In order to solve the problems in the prior art, the invention provides a remote nutrition information processing method and a remote nutrition information processing system based on the Internet, which can rapidly recommend a nutrition guidance scheme according to personal information of a user.
The technical scheme adopted by the invention is as follows:
an internet-based remote nutrition information processing method comprises the following steps:
step 1: a user logs in a processing server by using a user client and uploads personal information;
step 2: the processing server converts the personal information into corresponding personal information vector V now ；
Step 3: the processing server judges whether a nutrition guidance scheme is recommended for the user or not in the past;
step 4: the processing server vectors the personal information V if the processing server has not previously recommended a nutrition guidance program to the user now Inputting a basic recommendation model, and outputting a corresponding recommendation scheme according to the input personal information vector by the basic recommendation model; then jump to step 7;
step 5: if the processing server recommends a nutrition guidance scheme for the user, the processing server queries the last recommended record of the user from a user database, and acquires a corresponding personal information vector V from the recommended record last Recommendation scheme identifier ProjectID last ；
Step 6: the processing server calculates the current personal information vector V now And last personal information vector V last Similarity of (2); the processing server sets the personal information vector V if the similarity is smaller than a predetermined threshold now Inputting a basic recommendation model to obtain corresponding recommendation schemes, and if the similarity is greater than or equal to a preset threshold value, processing the serviceThe personal information vector V now And the last recommendation identifier ProjectID last Inputting a quick recommendation model to obtain a corresponding recommendation scheme;
step 7: and the processing server sends the personal information and the corresponding recommended scheme to a doctor client, and a doctor audits and adjusts the recommended scheme on the doctor client to generate a final scheme.
Further, the user database is used for storing the registration information of the user and the recommendation record of the user; the recommendation record comprises a recommendation time, a personal information vector of a user and a recommendation scheme identifier obtained by the processing server according to the personal information vector.
Further, the scheme database stores a plurality of nutrition guidance schemes designed in advance, each scheme has at least one corresponding personal information vector in advance, and the identifier of each scheme in the scheme database and the corresponding at least one personal information vector are used as training samples to train the basic recommendation model; the personal information vector is input into the trained basic recommendation model to output the identifier of the corresponding recommendation.
Further, the fast recommendation model is a pre-trained recommendation model, which inputs a current personal information vector of a user and an identifier of a last recommendation of the user, and outputs a recommendation identifier currently suitable for the user.
Further, the deep neural network model is adopted for both the basic recommendation model and the quick recommendation model, and the number of layers of the neural network of the quick recommendation model is smaller than that of the basic recommendation model.
Further, obtaining a training sample of the fast recommendation model through a calculation result of the basic recommendation model includes: acquiring two personal information vectors V with similarity greater than or equal to a predetermined threshold 1 And V 2 Then V is obtained through a basic recommendation model 1 Corresponding recommendation scheme identifier ID 1 And V 2 Corresponding recommendation scheme identifier ID 2 Will (V) 1 ，ID 2 Tag ID 1 ) Sum (V) 2 ，ID 1 Tag ID 2 ) As training samples for the fast recommendation model.
Further, the processing server records the final scenario and corresponding personal information vector into a scenario database for retraining the underlying recommendation model.
Further, the doctor client returns the final solution to the processing server, and the processing server returns the final solution to the user client.
The invention also provides a remote nutrition information processing system based on the Internet, which is used for realizing the method, and comprises a user client, a doctor client and a processing server which are connected through the Internet, wherein the processing server comprises a user database, a scheme database, a basic recommendation model and a quick recommendation model, and the user database is used for storing registration information of a user and recommendation records of the user; the recommendation record comprises a recommendation time, a personal information vector of a user and a recommendation scheme identifier obtained by a processing server according to the personal information vector; the regimen database stores a plurality of pre-designed nutritional instruction regimens, each regimen having at least one corresponding personal information vector in advance, each regimen having a respective unique identifier; the basic recommendation model inputs personal information vectors and outputs identifiers of corresponding recommendation schemes; the fast recommendation model is a pre-trained recommendation model, which inputs a current personal information vector of a user and an identifier of a last recommendation of the user, and outputs a recommendation identifier currently suitable for the user.
Further, the user client is a personal computer, a smart phone or a tablet computer, the doctor client is a personal computer, a smart phone or a tablet computer, and the processing server is a single server or a server cluster.
The beneficial effects of the invention are as follows: the invention can provide nutrition guidance scheme for common users on the Internet, and can provide faster service response for large-scale users on the Internet under the condition of less number of nutritionists.
[ description of the drawings ]
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate and together with the description serve to explain the invention, if necessary:
FIG. 1 is a basic block diagram of a telematic system of the present invention.
[ detailed description ] of the invention
The present invention will now be described in detail with reference to the drawings and the specific embodiments thereof, wherein the exemplary embodiments and the description are for the purpose of illustrating the invention only and are not to be construed as limiting the invention.
Referring to fig. 1, there is shown the basic architecture of the telematic system of the present application, including a user client, a processing server, and a doctor client. The clients and the servers are connected and communicated with each other through the Internet.
The user client is a client used by an Internet user, and the user can log in a processing server in the system by using the user client, communicate with the processing server, fill in and upload personal information, and receive a nutrition guidance scheme returned by the processing server. Although only one user client is shown in fig. 1, those skilled in the art will appreciate that a plurality of different user clients may be included in the system for use by a plurality of users. The specific user client may be a personal computer, a smart phone, a tablet computer, etc.
The processing server is core processing equipment of the application, and can receive personal information uploaded by a login user, obtain a recommended nutrition guidance scheme through analysis of the personal information, inform a doctor client of the recommended nutrition guidance scheme (hereinafter referred to as a recommended scheme), receive a final nutrition guidance scheme (hereinafter referred to as a final scheme) returned by the doctor client, and return the final scheme to the user client. The processing server further comprises a user database, a scheme database, a basic recommendation model and a quick recommendation model, and specific roles of the user database, the scheme database, the basic recommendation model and the quick recommendation model are described later. It should be noted that the model may be a recommendation model implemented by software programming, a recommendation model implemented by hardware, or a recommendation model implemented by a combination of software and hardware, which is not limited in this aspect of the present invention. In a specific implementation, the processing server may be a single server or may be a server cluster, which is not limited in this respect by the present invention.
The doctor client is a client used by a nutriment doctor, and the doctor can log in the processing server by using the doctor client, receive personal information and recommended schemes submitted by the processing server, and return the final scheme after the doctor is audited and regulated to the processing server. Although only one doctor client is shown in fig. 1, one skilled in the art will appreciate that a plurality of different doctor clients may be included in the system for use by a plurality of doctors. The specific doctor client may be a personal computer, smart phone, tablet computer, etc.
Based on the basic structure of the above system, the following describes in detail the telematic method of the present application.
Step 1: the user logs in the processing server by using the user client and uploads personal information.
Specifically, the user needs to register in the system first and then log in the processing server using the registration information, for example, the user can log in the processing server using the registered account and password. Registration and login are well known in the art and will not be described in detail herein.
After the user logs in the processing server, if the user needs to acquire the nutrition guidance scheme of the user, the user client is used for filling in personal information of the user. Specific items of the personal information may be made in advance by the system, such as gender, birth month, height, weight, blood pressure, meal preference, bad preference, past medical history, family medical history, and the like. Preferably, the personal information collected by the user client may be in the form of a questionnaire, which is formulated in advance by a nutriment doctor or a system administrator, and the user fills in the questionnaire in the user client and answers each question (which may be a selection question or a blank question) in the questionnaire, so that the user client may obtain the personal information of the user according to the answer filled in by the user. After the user completes the filling of the personal information, the user client submits the personal information to the processing server.
Step 2: the processing server converts the personal information into corresponding personal information vector V now 。
Before the recommendation model performs data analysis, the personal information needs to be processed correspondingly and converted into corresponding vector data. For data with fixed options, such as gender data, the specified values may be directly converted as vector values, e.g. "male" to 1 and "female" to 0. For data having a corresponding value, the value thereof may be directly used, for example, the current age of the user is calculated from the birth year and month as a vector value. For personal data in text form, after data cleaning and invalid data removal are needed, text or keywords are converted into vector values by a predetermined method, and various existing methods exist in the art to convert text into vectors, such as Word2vec, etc., and the specific method adopted is not limited by the present invention. If some item of data is missing from the uploaded personal information, the corresponding vector value may be set to 0.
In summary, the processing server, after processing the personal information, can convert it into an n-dimensional personal information vector V now ＝<P 1 ，P 2 ，……，P n >。
Step 3: the processing server determines whether a nutritional instruction has been previously recommended for the user.
Specifically, if the user is requesting nutrition guidelines using the system of the present invention for the first time, the processing server may determine that no nutrition guidelines have been previously recommended for the user, and currently recommend nutrition guidelines for the first time. If the user has previously obtained a nutritional guidance program using the system of the present invention, the processing server will have a corresponding record of recommendations in the user database, so that the processing server can determine that a nutritional guidance program has been recommended for the user.
The user database of the processing server is used for storing the registration information of the user and the recommendation record of the user. That is, each time a user requests and obtains a nutrition instruction regimen via the processing server, the user database stores a recommendation record that includes the personal information vector of the personal information uploaded by the user at the time, and an identifier (e.g., regimen number) of the nutrition instruction regimen that the processing server recommended at the time. The processing server, by querying the user database, can determine whether the user is requesting nutritional instructions for the first time, and whether a nutritional instruction regimen has been previously recommended for the user.
Step 4: the processing server vectors the personal information V if the processing server has not previously recommended a nutrition guidance program to the user now Inputting a basic recommendation model, and outputting a corresponding recommendation scheme according to the input personal information vector by the basic recommendation model; and then jumps to step 7.
Specifically, the processing server calls the basic recommendation model to complete the recommendation of the nutrition guidance scheme when judging that the nutrition guidance scheme is not recommended to the user before, namely, the user requests the nutrition guidance for the first time. The basic recommendation model is a pre-trained recommendation model, inputs personal information vectors of users and outputs recommendation schemes suitable for the users. The specific recommendation model may be any existing recommendation model in the art, and the present invention is not limited thereto. Preferably, the underlying recommendation model may employ a deep neural network model.
In a specific implementation, the nutritional physician may consider different individual situations (i.e. different personal information vectors), design a corresponding nutritional guidance solution for each individual situation in advance, thereby obtaining a plurality of nutritional guidance solutions, and store all the pre-designed solutions in a solution database of the processing server, that is, each solution in the solution database has at least one corresponding personal information vector in advance. Each scheme may have its corresponding unique identifier, e.g., a unique number of the scheme. And the identifier of each scheme in the scheme database and at least one corresponding personal information vector are used as training samples, and the basic recommendation model is trained to obtain a trained basic recommendation model. Thus, the personal information vector is input into the trained basic recommendation model, the model can output the identifier of the recommendation scheme, and the processing server queries a scheme database according to the identifier to obtain a specific nutrition guidance scheme.
Step 5: if the processing server recommends a nutrition guidance scheme for the user, the processing server queries the last recommended record of the user from a user database, and acquires a corresponding personal information vector V from the recommended record last Recommendation scheme identifier ProjectID last 。
As described above, the user database stores the recommendation record of each time of the user, including the recommendation time of the recommendation record, the personal information vector calculated according to the personal information uploaded by the user at the time, and the recommendation scheme identifier obtained by the processing server according to the personal information vector; and the final proposal obtained after the doctor audits and adjusts the recommended proposal can also be included. Thus, the processing server may query and obtain the last recommended record of the user from the user database, and may obtain the last personal information vector of the user, and the last recommended program identifier from the recommended record.
Step 6: the processing server calculates the current personal information vector V now And last personal information vector V last Similarity of (2); the processing server sets the personal information vector V if the similarity is smaller than a predetermined threshold now Inputting a basic recommendation model to obtain a corresponding recommendation scheme, and if the similarity is greater than or equal to a predetermined threshold value, the processing server converting the personal information vector V now And the last recommendation identifier ProjectID last And inputting a quick recommendation model to acquire a corresponding recommendation scheme.
The processing server is according to V now And V last Is selected to use the basic recommendation model or the fast recommendation model. That is, if the personal information is changed greatly, the original recommendation scheme has poor referenceability, and the basic recommendation model needs to be reused for recommendation, and if the personal information is changed less than the last time, the original recommendation scheme has high referenceability, and even the recommendation scheme may not change, and the quick recommendation model can be used for recommendation. In actual use, personal information is not changed too much compared with the last time, and only the items such as age, weight and the like are likely to be changed, so that a quick recommendation model can be applied and is used for quick recommendation based on the last recommendation scheme, and the overall operation efficiency of the system is improved.
The similarity can be any existing similarity calculation method, for example, cosine similarity can be used as similarity between two vectors, and the specific similarity algorithm is not limited by the invention.
The fast recommendation model is a pre-trained recommendation model, which inputs the current personal information vector of the user and the identifier of the last recommendation scheme, and outputs the recommendation scheme identifier currently suitable for the user.
Similar to the base recommendation model, the quick recommendation model may also employ any of the existing recommendation models in the art, as the present invention is not limited in this regard. But the computational efficiency of the fast recommendation model should be significantly improved over the basic recommendation model. For example, in a preferred embodiment of the present invention, the base recommendation model and the fast recommendation model both use the deep neural network model, but the number of layers of the fast recommendation model is smaller than that of the base recommendation model, for example, the base recommendation model may have n hidden layers, and the fast recommendation model may have only n/2 hidden layers, so that the fast recommendation model has a smaller calculation scale and a higher calculation efficiency than the base recommendation model.
The training sample of the quick recommendation model can be obtained through the calculation result of the basic recommendation model. For example, two personal information vectors V with similarity equal to or greater than a predetermined threshold are obtained 1 And V 2 Then lead toAcquiring V through basic recommendation model 1 Corresponding recommendation scheme identifier ID 1 And V 2 Corresponding recommendation scheme identifier ID 2 . Then (V) 1 ，ID 2 Tag ID 1 ) Sum (V) 2 ，ID 1 Tag ID 2 ) Can be used as a training sample of the fast recommendation model.
Although the quick recommendation model is relatively simplified compared with the basic recommendation model, the quick recommendation model utilizes the calculation result of the basic recommendation model, so that the accuracy, precision and recall rate of the quick recommendation model through training can be slightly reduced compared with the basic recommendation model, the calculation speed is greatly improved, and the popularization and the use of the system are facilitated in the whole.
Step 7: and the processing server sends the personal information and the corresponding recommended scheme to a doctor client, and a doctor audits and adjusts the recommended scheme on the doctor client to generate a final scheme.
For the existing machine recommendation model, the output result cannot be guaranteed to be completely correct, and the generated recommendation scheme has small probability of error, so that the final scheme needs to be checked by a true doctor. Specifically, the processing server determines the corresponding recommended solution, that is, the recommended solution identifier in step 4 or step 6, and may acquire specific recommended solution content by querying the solution database. The processing server then sends the specific recommended program content, along with the personal information of the user, to the doctor client for the doctor to review and adjust.
The doctor uses the doctor client to review the current personal information of the user and the specific recommended program content, and if necessary, the specific nutrition guidance content can be adjusted to form a final program. The doctor client returns the final scheme to the processing server, and the processing server returns the final scheme to the user client. The processing server may also save the final solution to the user database for subsequent querying. If the final solution is different from the specific content of the recommended solution, the processing server may also record the final solution and the corresponding personal information vector into the solution database for subsequent retraining of the recommended model.
Through the method steps and the system, the invention can provide a nutrition guidance scheme for common users on the Internet, and can provide faster service response for large-scale users on the Internet under the condition of less number of nutritionists.
The foregoing description is only of the preferred embodiments of the invention, and all changes and modifications that come within the meaning and range of equivalency of the structures, features and principles of the invention are therefore intended to be embraced therein.
Claims (9)
1. The remote nutrition information processing method based on the Internet is characterized by comprising the following steps of:
step 1: a user logs in a processing server by using a user client and uploads personal information;
step 2: the processing server converts the personal information into corresponding personal information vector V now ；
Step 3: the processing server judges whether a nutrition guidance scheme is recommended for the user or not in the past;
step 4: the processing server vectors the personal information V if the processing server has not previously recommended a nutrition guidance program to the user now Inputting a basic recommendation model, and outputting a corresponding recommendation scheme according to the input personal information vector by the basic recommendation model; then jump to step 7;
step 5: if the processing server recommends a nutrition guidance scheme for the user, the processing server queries the last recommended record of the user from a user database, and acquires a corresponding personal information vector V from the recommended record last Recommendation scheme identifier ProjectID last ；
Step 6: the processing server calculates the current personal information vector V now And last personal information vector V last Similarity of (2); if the similarity is less than a predetermined valueThreshold value, the processing server will vector the personal information V now Inputting a basic recommendation model to obtain a corresponding recommendation scheme, and if the similarity is greater than or equal to a predetermined threshold value, the processing server converting the personal information vector V now And the last recommendation identifier ProjectID last Inputting a quick recommendation model to obtain a corresponding recommendation scheme;
step 7: and the processing server sends the personal information and the corresponding recommended scheme to a doctor client, and a doctor audits and adjusts the recommended scheme on the doctor client to generate a final scheme.
2. The method of claim 1, wherein the user database is used for storing registration information of a user and a recommendation record of the user; the recommendation record comprises a recommendation time, a personal information vector of a user and a recommendation scheme identifier obtained by the processing server according to the personal information vector.
3. The method according to any one of claims 1-2, wherein a protocol database stores a plurality of pre-designed nutrition instruction protocols, each protocol having at least one corresponding personal information vector in advance, the basic recommendation model being trained using an identifier of each protocol in the protocol database and its corresponding at least one personal information vector as training samples; the personal information vector is input into the trained basic recommendation model to output the identifier of the corresponding recommendation.
4. The method according to any one of claims 1-2, wherein the fast recommendation model is a pre-trained recommendation model that inputs a current personal information vector of a user and an identifier of a last recommendation of the user, and outputs a recommendation identifier currently suitable for the user.
5. The method according to any one of claims 1-2, wherein the base recommendation model and the fast recommendation model both employ deep neural network models, the number of neural network layers of the fast recommendation model being less than the number of layers of the base recommendation model.
6. The method of claim 1, wherein the processing server records the final project and corresponding personal information vectors into a project database for retraining the underlying recommendation model.
7. The method of claim 1, wherein the doctor client returns the final solution to the processing server, which in turn returns the final solution to the user client.
8. An internet-based telematic system for implementing the method of claim 1, comprising a user client, a doctor client, and a processing server connected via the internet, the processing server comprising a user database, a protocol database, a base recommendation model, and a quick recommendation model, wherein
The user database is used for storing the registration information of the user and the recommendation record of the user; the recommendation record comprises a recommendation time, a personal information vector of a user and a recommendation scheme identifier obtained by a processing server according to the personal information vector;
the regimen database stores a plurality of pre-designed nutritional instruction regimens, each regimen having at least one corresponding personal information vector in advance, each regimen having a respective unique identifier;
the basic recommendation model inputs personal information vectors and outputs identifiers of corresponding recommendation schemes; the fast recommendation model is a pre-trained recommendation model, which inputs a current personal information vector of a user and an identifier of a last recommendation of the user, and outputs a recommendation identifier currently suitable for the user.
9. The system of claim 8, wherein the user client is a personal computer, a smart phone, or a tablet computer, the doctor client is a personal computer, a smart phone, or a tablet computer, and the processing server is a single server or a cluster of servers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310093769.1A CN116364240B (en) | 2023-02-02 | 2023-02-02 | Remote nutrition information processing method and system based on Internet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310093769.1A CN116364240B (en) | 2023-02-02 | 2023-02-02 | Remote nutrition information processing method and system based on Internet |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116364240A CN116364240A (en) | 2023-06-30 |
| CN116364240B true CN116364240B (en) | 2024-01-26 |
Family
ID=86938526
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310093769.1A Active CN116364240B (en) | 2023-02-02 | 2023-02-02 | Remote nutrition information processing method and system based on Internet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116364240B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106971069A (en) * | 2017-03-20 | 2017-07-21 | 云南火地科技有限公司 | A kind of intelligent recipe recommendation system for nutrient health |
| CN111191020A (en) * | 2019-12-27 | 2020-05-22 | 江苏省人民医院（南京医科大学第一附属医院） | Prescription recommendation method and system based on machine learning and knowledge graph |
| CN112242187A (en) * | 2020-10-26 | 2021-01-19 | 平安科技（深圳）有限公司 | Medical scheme recommendation system and method based on knowledge graph representation learning |
| CN113378049A (en) * | 2021-06-10 | 2021-09-10 | 平安科技（深圳）有限公司 | Training method and device of information recommendation model, electronic equipment and storage medium |
| CN114780837A (en) * | 2022-04-08 | 2022-07-22 | 重庆大学 | Intelligent personalized life style recommendation system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8996530B2 (en) * | 2012-04-27 | 2015-03-31 | Yahoo! Inc. | User modeling for personalized generalized content recommendations |
-
2023
- 2023-02-02 CN CN202310093769.1A patent/CN116364240B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106971069A (en) * | 2017-03-20 | 2017-07-21 | 云南火地科技有限公司 | A kind of intelligent recipe recommendation system for nutrient health |
| CN111191020A (en) * | 2019-12-27 | 2020-05-22 | 江苏省人民医院（南京医科大学第一附属医院） | Prescription recommendation method and system based on machine learning and knowledge graph |
| CN112242187A (en) * | 2020-10-26 | 2021-01-19 | 平安科技（深圳）有限公司 | Medical scheme recommendation system and method based on knowledge graph representation learning |
| CN113378049A (en) * | 2021-06-10 | 2021-09-10 | 平安科技（深圳）有限公司 | Training method and device of information recommendation model, electronic equipment and storage medium |
| CN114780837A (en) * | 2022-04-08 | 2022-07-22 | 重庆大学 | Intelligent personalized life style recommendation system |
Non-Patent Citations (1)
| Title |
|---|
| 基于营养饮食推荐系统研究;刘兴姿;《中国优秀硕士学位论文全文数据库 医药卫生科技辑》(第02期);E054-77 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116364240A (en) | 2023-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210133970A1 (en) | System to collect and identify skin conditions from images and expert knowledge | |
| JP6523498B1 (en) | Learning device, learning method and learning program | |
| CN112035741B (en) | Reservation method, device, equipment and storage medium based on user physical examination data | |
| CN112015917A (en) | Data processing method and device based on knowledge graph and computer equipment | |
| CN116756579A (en) | Training method of large language model and text processing method based on large language model | |
| US10474926B1 (en) | Generating artificial intelligence image processing services | |
| CN112287232B (en) | Method and device for generating recommendation information | |
| CN112074828A (en) | Training image embedding model and text embedding model | |
| US11194820B1 (en) | Personalized smart provider search | |
| CN114005509B (en) | Treatment scheme recommendation system, method, device and storage medium | |
| CN111091010A (en) | Similarity determination method, similarity determination device, network training device, network searching device and storage medium | |
| CN116235191A (en) | Selecting a training dataset for training a model | |
| CN113903442A (en) | Special doctor recommendation method and device | |
| US20230368028A1 (en) | Automated machine learning pre-trained model selector | |
| KR20210052122A (en) | System and method for providing user-customized food information service | |
| US20190332569A1 (en) | Integrating deep learning into generalized additive mixed-effect (game) frameworks | |
| CN113707323B (en) | Disease prediction method, device, equipment and medium based on machine learning | |
| CN115631008B (en) | Commodity recommendation method, device, equipment and medium | |
| CN113657086A (en) | Word processing method, device, equipment and storage medium | |
| CN116364240B (en) | Remote nutrition information processing method and system based on Internet | |
| CN116956183A (en) | Multimedia resource recommendation method, model training method, device and storage medium | |
| CN114743647A (en) | Medical data processing method, device, equipment and storage medium | |
| US20210133627A1 (en) | Methods and systems for confirming an advisory interaction with an artificial intelligence platform | |
| JP6751955B1 (en) | Learning method, evaluation device, and evaluation system | |
| CN112035567A (en) | Data processing method and 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 |