CN113254786B - Big data-based diet information pushing method and system and cloud platform - Google Patents
Big data-based diet information pushing method and system and cloud platform Download PDFInfo
- Publication number
- CN113254786B CN113254786B CN202110689406.5A CN202110689406A CN113254786B CN 113254786 B CN113254786 B CN 113254786B CN 202110689406 A CN202110689406 A CN 202110689406A CN 113254786 B CN113254786 B CN 113254786B
- Authority
- CN
- China
- Prior art keywords
- diet
- preference
- behavior
- eating
- learning 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.)
- Expired - Fee Related
Links
- 235000005911 diet Nutrition 0.000 title claims abstract description 481
- 230000037213 diet Effects 0.000 title claims abstract description 467
- 238000000034 method Methods 0.000 title claims abstract description 39
- 235000021061 dietary behavior Nutrition 0.000 claims abstract description 155
- 235000004280 healthy diet Nutrition 0.000 claims abstract description 24
- 230000020595 eating behavior Effects 0.000 claims description 94
- 235000005686 eating Nutrition 0.000 claims description 77
- 238000011156 evaluation Methods 0.000 claims description 18
- 230000036541 health Effects 0.000 claims description 18
- 230000000378 dietary effect Effects 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 14
- 235000020785 dietary preference Nutrition 0.000 claims description 10
- 238000005457 optimization Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 7
- 235000006694 eating habits Nutrition 0.000 claims description 7
- 239000000470 constituent Substances 0.000 claims description 2
- 238000013461 design Methods 0.000 description 15
- 238000013459 approach Methods 0.000 description 12
- 230000015654 memory Effects 0.000 description 12
- 230000004048 modification Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 6
- 230000004927 fusion Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000000644 propagated effect Effects 0.000 description 3
- 230000000699 topical effect Effects 0.000 description 3
- 238000002716 delivery method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000035764 nutrition Effects 0.000 description 2
- 235000016709 nutrition Nutrition 0.000 description 2
- 208000017667 Chronic Disease Diseases 0.000 description 1
- 208000008589 Obesity Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 235000005118 dietary health Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000037406 food intake Effects 0.000 description 1
- 235000020803 food preference Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 235000001497 healthy food Nutrition 0.000 description 1
- 239000010977 jade Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 235000021048 nutrient requirements Nutrition 0.000 description 1
- 235000020824 obesity Nutrition 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06N20/00—Machine learning
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- Nutrition Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Computer Networks & Wireless Communication (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a diet information pushing method, a system and a cloud platform based on big data, wherein a first key diet tendency attribute sequence in diet behavior big data of a preset time period is obtained through a diet behavior characteristic learning model, so that first diet preference object data and first diet preference characteristic distribution in the diet behavior big data of the preset time period are obtained, the first diet preference object data are clustered into a plurality of diet preference object groups, diet preference indexes corresponding to each diet preference object group in the first diet preference object data are identified based on the first diet preference characteristic distribution, healthy diet preference indexes of each diet preference object unit in the first diet preference object data are obtained, then diet behavior portrait results are obtained, and hot diet information pushing is carried out on a diet information service terminal based on the diet behavior results, the accuracy of hot diet information propelling movement is improved.
Description
Technical Field
The disclosure relates to the technical field of big data, in particular to a diet information pushing method and system based on big data and a cloud platform.
Background
As the standard of living increases, personalized diets are more and more concerned by consumers, and users often have confusion about their daily diet: the nutrient requirement can be met by what and how much food should be eaten every day, and obesity caused by excessive ingestion is avoided. At present, all book-type diet suggestions are based on the average value of the common public, but the living habits and diet hobbies of each individual are different, so that the book-type diet suggestions are greatly different. Especially, the food is particularly favored by special people such as pregnant women, nursing mothers, chronic diseases and the like, and a healthy food menu suitable for the user can be recommended according to the physical condition and the ordinary food preference of the user. At present, various nutrition application programs APP appear on the mobile phone application market, and convenient nutrition learning software is provided for users. However, most of the recommendation systems available in the market are fixed templates, but the recommendation systems only can crudely classify users into a certain category and further recommend a certain category of suggestions to the users. Personalized dietary preferences and dietary trends of the relevant user are not taken into account, thereby resulting in recommended information that is not really suited for the user.
Disclosure of Invention
In order to overcome at least the above disadvantages in the prior art, an object of the present disclosure is to provide a diet information pushing method, system and cloud platform based on big data.
In a first aspect, the present disclosure provides a diet information pushing method based on big data, which is applied to a diet pushing cloud platform, where the diet pushing cloud platform is in communication connection with a plurality of diet information service terminals, and the method includes:
inputting diet behavior big data of a preset time period into a diet behavior characteristic learning model;
acquiring a first key diet tendency attribute sequence in the diet behavior big data of the preset time period through the diet behavior feature learning model;
acquiring first diet preference object data and first diet preference feature distribution in the diet behavior big data of the preset time period based on the first key diet tendency attribute sequence through the diet behavior feature learning model, wherein the first diet preference object data is diet preference object data corresponding to the first key diet tendency attribute sequence in the diet behavior big data of the preset time period;
clustering the first diet preference object data into a plurality of diet preference object groups through the diet behavior characteristic learning model, identifying diet preference indexes corresponding to each diet preference object group in the first diet preference object data based on the first diet preference characteristic distribution through the diet behavior characteristic learning model, and acquiring healthy diet preference indexes of each diet preference object unit in the first diet preference object data through the diet behavior characteristic learning model, wherein the diet preference indexes corresponding to the diet preference object groups are confidence degrees of key diet preference attributes existing in the diet preference object groups;
and acquiring a diet behavior portrait result based on the diet preference index of each diet preference object group in the first diet preference object data, the information of the first key diet tendency attribute sequence and the healthy diet preference index of each diet preference object unit in the first diet preference object data, and pushing hot diet information to the diet information service terminal based on the diet behavior portrait result.
In a second aspect, an embodiment of the present disclosure further provides a diet information pushing system based on big data, where the diet information pushing system based on big data includes a diet pushing cloud platform and a plurality of diet information service terminals in communication connection with the diet pushing cloud platform;
the diet pushing cloud platform is used for:
inputting diet behavior big data of a preset time period into a diet behavior characteristic learning model;
acquiring a first key diet tendency attribute sequence in the diet behavior big data of the preset time period through the diet behavior feature learning model;
acquiring first diet preference object data and first diet preference feature distribution in the diet behavior big data of the preset time period based on the first key diet tendency attribute sequence through the diet behavior feature learning model, wherein the first diet preference object data is diet preference object data corresponding to the first key diet tendency attribute sequence in the diet behavior big data of the preset time period;
clustering the first diet preference object data into a plurality of diet preference object groups through the diet behavior characteristic learning model, identifying diet preference indexes corresponding to each diet preference object group in the first diet preference object data based on the first diet preference characteristic distribution through the diet behavior characteristic learning model, and acquiring healthy diet preference indexes of each diet preference object unit in the first diet preference object data through the diet behavior characteristic learning model, wherein the diet preference indexes corresponding to the diet preference object groups are confidence degrees of key diet preference attributes existing in the diet preference object groups;
and acquiring a diet behavior portrait result based on the diet preference index of each diet preference object group in the first diet preference object data, the information of the first key diet tendency attribute sequence and the healthy diet preference index of each diet preference object unit in the first diet preference object data, and pushing hot diet information to the diet information service terminal based on the diet behavior portrait result.
According to any one of the above aspects, the present disclosure provides an embodiment, obtaining a first key diet tendency attribute sequence in the diet behavior big data of a preset time period through the diet behavior feature learning model, obtaining a first diet preference object data and a first diet preference feature distribution in the diet behavior big data of the preset time period based on the first key diet tendency attribute sequence, clustering the first diet preference object data into a plurality of diet preference object groups, identifying a diet preference index corresponding to each diet preference object group in the first diet preference object data based on the first diet preference feature distribution, obtaining a healthy diet preference index of each diet preference object unit in the first diet preference object data, and obtaining information of the diet preference index, the first key diet tendency attribute sequence and the healthy diet preference index of each diet preference object unit in the first diet preference object data based on the diet preference index of each diet preference object group in the first diet preference object data, the first key diet preference attribute sequence and the healthy diet preference index of each diet preference object unit in the first diet preference object data And the diet preference index acquires a diet behavior portrait result, and pushes hot diet information to the diet information service terminal based on the diet behavior portrait result, so that personalized diet preference and diet tendency of related users are considered, and the accuracy of pushing hot diet information is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that need to be called in the embodiments are briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present disclosure, and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic view of an application scenario of a big data-based diet information pushing system provided in an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of a big data-based diet information pushing method provided by an embodiment of the present disclosure;
fig. 3 is a block diagram illustrating the structure of a diet delivery cloud platform for implementing the above-mentioned diet information delivery method based on big data according to an embodiment of the present disclosure.
Detailed Description
The present disclosure is described in detail below with reference to the drawings, and the specific operation methods in the method embodiments can also be applied to the device embodiments or the system embodiments.
Fig. 1 is a schematic application scenario diagram of a big data-based diet information pushing system 10 according to an embodiment of the present disclosure. The big data-based diet information pushing system 10 may include a diet pushing cloud platform 100 and a diet information service terminal 200 communicatively connected to the diet pushing cloud platform 100. The big data based diet information pushing system 10 shown in fig. 1 is only one possible example, and in other possible embodiments, the big data based diet information pushing system 10 may also include only at least some of the components shown in fig. 1 or may also include other components.
In a possible design idea, the diet delivery cloud platform 100 and the diet information service terminal 200 in the diet information delivery system 10 based on big data may cooperatively perform the diet information delivery method based on big data described in the following method embodiment, and the detailed description of the method embodiment may be referred to in the specific steps of the diet delivery cloud platform 100 and the diet information service terminal 200.
In order to solve the technical problem in the foregoing background technology, the big data based diet information pushing method provided by the present embodiment may be executed by the diet pushing cloud platform 100 shown in fig. 1, and the big data based diet information pushing method is described in detail below.
Step S110: and inputting the diet behavior big data of the preset time period into the diet behavior characteristic learning model.
For example, the dietary behavior big data of the preset time period can be dietary habit big data, dietary climate big data, dietary health big data and the like, and the dietary behavior feature learning model can be a relevant machine learning model/artificial intelligence neural network for learning and classifying the dietary behavior feature.
Step S120: and acquiring a first key diet tendency attribute sequence in the diet behavior big data of the preset time period through the diet behavior characteristic learning model.
For example, the first key eating tendency attribute sequence may be a sequence of big data in an eating tendency state.
In a possible design approach, the step S120 of obtaining the first key eating tendency attribute sequence in the big data of the eating behaviors in the preset time period through the eating behavior feature learning model can be implemented by the schemes described in the following steps S1201 and S1202.
Step S1201: and acquiring first frequent eating behavior label characteristic distribution in the eating behavior big data of the preset time period through the eating behavior characteristic learning model.
For example, the frequent eating behavior tag feature distribution can be understood as a basic feature vector set of the frequent eating behavior corresponding to the eating behavior big data of the preset time period.
Step S1202: and acquiring a first key diet tendency attribute sequence in the diet behavior big data of the preset time period based on the first frequent diet behavior tag feature distribution through the diet behavior feature learning model.
In a possible design approach, the step S1202 of obtaining the first key eating tendency attribute sequence in the eating behavior big data of the preset time period based on the first frequent eating behavior tag feature distribution through the eating behavior feature learning model may be specifically implemented through the following steps S12021-S12023.
Step S12021: and acquiring a first candidate diet tendency attribute series in the diet behavior big data of the preset time period based on the first frequent diet behavior label characteristic distribution through the diet behavior characteristic learning model.
Step S12022: and acquiring a second diet preference characteristic distribution in the diet behavior big data of the preset time period by the diet behavior characteristic learning model based on the first candidate diet tendency attribute series and the first frequent diet behavior tag characteristic distribution.
Step S12023: and acquiring the first key diet tendency attribute sequence based on the second diet preference characteristic distribution through the diet behavior characteristic learning model.
For example, the diet preference object data may be understood as any object in which diet preferences exist, such as a taste object, a dish object, a cooking style object, and the like.
In a possible design approach, the obtaining the first key diet tendency attribute sequence based on the second diet preference feature distribution through the diet behavior feature learning model described in the above step S12023 may include the following steps S120231 and S120232.
Step S120231: and acquiring preference heat characteristic distribution and preference sharing characteristic distribution corresponding to the second diet preference characteristic distribution through the diet behavior characteristic learning model.
In one possible design approach, the preference popularity feature distribution is used to represent the confidence that the first candidate series of eating tendency attributes belongs to each trending preference object, and the first preference sharing feature distribution is used to represent the external sharing feature of the first key eating tendency attribute sequence relative to the first candidate series of eating tendency attributes.
Step S120232: and acquiring the information of the first key diet tendency attribute sequence based on the preference heat characteristic distribution corresponding to the second diet preference characteristic distribution and the preference sharing characteristic distribution corresponding to the second diet preference characteristic distribution.
In one possible design approach, the information of the first key eating tendency attribute sequence further includes a tendency component of the first key eating tendency attribute sequence and a distribution label of the first key eating tendency attribute sequence. Based on this, the acquiring information of the first key dietary tendency attribute sequence based on the preference heat characteristic distribution corresponding to the second dietary preference characteristic distribution and the preference sharing characteristic distribution corresponding to the second dietary preference characteristic distribution described in step S120232 may include: performing label clustering on the preference heat characteristic distribution corresponding to the second diet preference characteristic distribution to obtain a distribution label of the first key diet preference attribute sequence; and performing feature optimization on the preference sharing feature distribution corresponding to the second dietary preference feature distribution and the tendency component of the first candidate dietary tendency attribute series to obtain the tendency component of the first key dietary tendency attribute series. For example, the tendency component may be various features of the eating tendency attribute, and thus, a high correlation between the information of the first key eating tendency attribute sequence and the actual eating behavior generation scenario can be ensured.
Through the steps S12021 to S12023, the first key eating tendency attribute sequence can be accurately and reliably determined by taking the eating preference object data into consideration.
In some optional embodiments, before the step S120 of obtaining the first key eating tendency attribute sequence in the big data of the eating behavior in the preset time period through the eating behavior feature learning model, the method may further include the step S100 of: and performing model optimization updating on the eating behavior characteristic learning model.
It is to be understood that model-optimized updating of the eating behavior feature learning model corresponds to training of the relevant eating behavior feature learning model. Accordingly, the model optimization updating of the eating behavior characteristic learning model described in step S100 may include steps S101 to S106.
Step S101: inputting the reference diet behavior big data into the diet behavior characteristic learning model.
Step S102: and acquiring second frequent eating behavior label characteristic distribution of the reference eating behavior big data through the eating behavior characteristic learning model.
Step S103: and acquiring second diet preference object data and third diet preference feature distribution in the reference diet behavior big data based on the second frequent diet behavior tag feature distribution through the diet behavior feature learning model.
Step S104: clustering the second diet preference object data into a plurality of diet preference object groups through the diet behavior characteristic learning model, identifying diet preference indexes corresponding to each diet preference object group in the second diet preference object data based on the third diet preference characteristic distribution through the diet behavior characteristic learning model, and performing health concern characteristic extraction on the second frequent diet behavior label characteristic distribution through the diet behavior characteristic learning model to obtain second health concern characteristic distribution.
Step S105: and acquiring a first model evaluation index of the eating behavior characteristic learning model based on difference information between the eating preference index and a first reference eating preference index corresponding to each eating preference object group in the second eating preference object data, and acquiring a second model evaluation index of the eating behavior characteristic learning model based on difference information between the second health concern characteristic distribution and a second reference eating preference index.
For example, the model assessment indicator may be a loss function of the eating behavior feature learning model.
Step S106: improving model weight configuration data of the eating behavior feature learning model based on the first model assessment index and the second model assessment index.
For example, the model weight configuration data may be weight parameters of a dietary behavior feature learning model.
In a possible design approach, the obtaining, by the eating behavior feature learning model, the second eating preference object data and the third eating preference feature distribution in the eating behavior big data of the preset time period based on the second frequent eating behavior tag feature distribution may include the following: acquiring a second candidate eating tendency attribute series of the reference eating behavior big data based on the second frequent eating behavior tag feature distribution through the eating behavior feature learning model, and taking the corresponding eating preference object data of the second candidate eating tendency attribute series in the reference eating behavior big data as the second eating preference object data; and acquiring the third diet preference feature distribution based on the second candidate diet tendency attribute series and the second frequent diet behavior label feature distribution through the diet behavior feature learning model.
In a possible design approach, after the obtaining of the third distribution of eating preference characteristics based on the second series of candidate eating tendency attributes and the second distribution of frequent eating behavior tag characteristics by the eating behavior characteristic learning model, the following may be included: acquiring preference heat characteristic distribution and preference sharing characteristic distribution corresponding to the third diet preference characteristic distribution through the diet behavior characteristic learning model, wherein the preference heat characteristic distribution corresponding to the third diet preference characteristic distribution is used for representing confidence degrees that the second candidate diet tendency attribute series belong to the respective popular preference objects, and the preference sharing characteristic distribution corresponding to the third diet preference characteristic distribution is used for representing external sharing characteristics of a second key diet tendency attribute sequence relative to the second candidate diet tendency attribute series; acquiring a third model evaluation index of the eating behavior characteristic learning model based on difference information between a preference heat characteristic distribution corresponding to the third eating preference characteristic distribution and a third reference eating preference index, and acquiring a fourth model evaluation index of the eating behavior characteristic learning model based on difference information between the preference sharing characteristic distribution corresponding to the third eating preference characteristic distribution and a fourth reference eating preference index; improving model weight configuration data of the eating behavior feature learning model based on the third model assessment index and the fourth model assessment index.
The method has the advantages that the performance of the eating behavior characteristic learning model is reflected by the first model evaluation index, the second model evaluation index, the third model evaluation index and the fourth model evaluation index from different evaluation dimensions respectively, and by the design, the improvement of model weight configuration data of the eating behavior characteristic learning model can be realized by combining more levels of model evaluation indexes as far as possible, so that the anti-interference capability of the eating behavior characteristic learning model is improved.
Step S130: and acquiring first diet preference object data and first diet preference feature distribution in the diet behavior big data of the preset time period based on the first key diet tendency attribute sequence through the diet behavior feature learning model.
In a possible design approach, the first dietary preference object data is the dietary preference object data corresponding to the first key dietary tendency attribute sequence in the dietary behavior big data of the preset time period.
Step S140: clustering the first diet preference object data into a plurality of diet preference object groups through the diet behavior characteristic learning model, identifying diet preference indexes corresponding to each diet preference object group in the first diet preference object data based on the first diet preference characteristic distribution through the diet behavior characteristic learning model, and acquiring the healthy diet preference indexes of each diet preference object unit in the first diet preference object data through the diet behavior characteristic learning model.
In one possible design approach, the diet preference index corresponding to the diet preference object group is a confidence level that key diet tendency attributes exist in the diet preference object group. The diet preference index can also be understood as characteristic information of the diet preference object group.
In some examples, the information of the first key eating tendency attribute sequence includes a tendency component of the first key eating tendency attribute sequence. Based on this, the step S140 of obtaining the healthy diet preference index of each diet preference object unit in the first diet preference object data through the diet behavior feature learning model may include the following technical solutions described in the steps S1401 and S1402.
Step S1401: and performing health concern feature extraction on the first frequent eating behavior tag feature distribution through the eating behavior feature learning model to obtain first health concern feature distribution corresponding to each eating preference object unit in the eating behavior big data of the preset time period.
For example, the health concern feature extraction may be understood as extracting a feature vector based on a health state pair of eating behaviors.
Step S1402: determining a diet preference index corresponding to each diet preference object unit in the first health concern feature distribution in the first diet preference object data as a healthy diet preference index corresponding to the diet preference object unit in the first diet preference object data based on the trend constituent elements of the first key diet preference attribute sequence.
It is understood that through the steps S1401 and S1402, the health status of the eating behavior can be taken into account, thereby ensuring the integrity of the healthy eating preference index of each eating preference object unit (which may be clustered according to the time-series characteristics) in the first eating preference object data.
Step S150: and acquiring a diet behavior portrait result based on the diet preference index of each diet preference object group in the first diet preference object data, the information of the first key diet tendency attribute sequence and the healthy diet preference index of each diet preference object unit in the first diet preference object data, and pushing hot diet information to the diet information service terminal based on the diet behavior portrait result.
For example, the diet behavior portrait result can be used for guiding subsequent diet information pushing, and the accuracy of diet information pushing is improved.
In some examples, the information of the first key eating tendency attribute sequence includes a distribution tag of the first key eating tendency attribute sequence. Based on this, the step S150 of obtaining the diet behavior profile result based on the diet preference index of each diet preference object group in the first diet preference object data, the information of the first key diet tendency attribute sequence, and the healthy diet preference index of each diet preference object unit in the first diet preference object data may include the steps S1501 and S1502.
Step S1501: determining diet preference object data with the key diet preference attribute in the first diet preference object data based on the diet preference index corresponding to each diet preference object group in the first diet preference object data, and determining the distribution label corresponding to the diet preference object unit in the first diet preference object data based on the healthy diet preference index of each diet preference object unit in the first diet preference object data.
In one possible design approach, the diet preference index corresponding to the diet preference object group corresponding to the diet preference object data with the key diet tendency attribute is larger than a target index;
step S1502: and determining the diet preference object units belonging to the distribution labels of the first key diet tendency attribute sequence in the diet preference object data with key diet tendency attributes as the diet behavior sketch result based on the distribution labels of each diet preference object unit in the first diet preference object data.
For example, the diet preference object units belonging to the distribution labels of the first key diet tendency attribute sequence in the diet preference object data with key diet tendency attributes may include the commonalities of related big data, and the diet behavior profiling result is accurately obtained through the diet preference object units belonging to the distribution labels of the first key diet tendency attribute sequence in the diet preference object data with key diet tendency attributes.
For example, in one possible design concept, the step of pushing popular diet information to the diet information service terminal based on the result of the diet behavior picture in step S150 may include the following steps.
Step S1501: acquiring a diet matching content source set corresponding to the diet behavior portrait result, wherein the diet matching content source set comprises i groups of diet matching content sources related to diet subject characteristics, and i is an integer greater than or equal to 1;
step S1502: and acquiring a topical subject object sequence of popular diets according to the diet matching content source set, wherein the topical subject object sequence of popular diets comprises i groups of topical subject objects related to the topic features of diets.
Step S1503: based on the diet matching content source set, acquiring a diet matching content feature sequence through a first tracking unit included in a popular diet topic tracking model, wherein the diet matching content feature sequence comprises i diet matching content features.
Step S1504: based on the popular diet subject object sequence, acquiring a diet topic tracking feature sequence through a second tracking unit included in the popular diet topic tracking model, wherein the diet topic tracking feature sequence comprises i diet topic tracking features.
Step S1505: based on the diet matching content feature sequence and the diet topic tracking feature sequence, obtaining a tracking output decision description component corresponding to the diet matching content source through a tracking output decision unit included in the popular diet topic tracking model.
Step S1506: determining a hot spot pushing rule component of the diet matching content source set according to the tracking output decision description component, and pushing hot spot diet content based on the hot spot pushing rule component.
For example, in a possible design approach, the obtaining, by a tracking output decision unit included in the popular diet topic tracking model, a tracking output decision description component corresponding to the diet matching content source set based on the diet matching content feature sequence and the diet topic tracking feature sequence includes: acquiring i first content attention features by a first attention feature extraction unit included in the popular diet topic tracking model based on the diet matching content feature sequence, wherein each first content attention feature corresponds to a diet matching content feature; acquiring i second content attention features by a second attention feature extraction unit included in the popular diet topic tracking model based on the diet topic tracking feature sequence, wherein each second content attention feature corresponds to one diet topic tracking feature; performing feature fusion on the i first content attention features and the i second content attention features to obtain i target content attention features, wherein each target content attention feature comprises a first content attention feature and a second content attention feature; based on the i target content attention features, obtaining a tracking output decision description component corresponding to the diet matching content source set through the tracking output decision unit included in the popular diet topic tracking model.
For example, in one possible design approach, the obtaining i first content attention features by a first attention feature extraction unit included in the popular diet topic tracking model based on the diet matching content feature sequence includes: for each group of diet matching content features in the diet matching content feature sequence, acquiring a first clustering feature through a clustering node included in the first attention feature extraction unit, wherein the first attention feature extraction unit belongs to the trending diet topic tracking model; for each group of diet matching content features in the diet matching content feature sequence, acquiring a first part of clustering features through a part of clustering nodes included in the first attention feature extraction unit; acquiring a first fusion feature through a fusion unit included in the first attention feature extraction unit based on the first clustering feature and the first partial clustering feature for each group of diet matching content features in the diet matching content feature sequence; and acquiring a first content attention feature through a first part of clustering nodes included by the first attention feature extraction unit based on the first fusion feature and the diet matching content feature for each group of diet matching content features in the diet matching content feature sequence.
Through the mode, the method obtains the first key diet tendency attribute sequence in the diet behavior big data of the preset time period through the diet behavior characteristic learning model, obtains the first frequent diet behavior label characteristic distribution and the first diet preference characteristic distribution of the diet behavior big data of the preset time period based on the first key diet tendency attribute sequence, selects the key diet tendency attribute of diet preference object grouping for the first diet preference object data, can quickly realize the preliminary screening of the key diet tendency attribute in the first diet preference object data, obtains the healthy diet preference index of each diet preference object unit in the first diet preference object data through the diet behavior characteristic learning model, and can obtain the diet behavior result portrait by combining the mining result of the key diet tendency attribute in the first diet preference object data and the healthy diet preference index of each diet preference object unit, and then the accuracy of information push is improved.
Fig. 3 illustrates a hardware structure of the diet pushing cloud platform 100 for implementing the big data-based diet information pushing method, which is provided by the embodiment of the present disclosure, and as shown in fig. 3, the diet pushing cloud platform 100 may include a processor 110, a machine-readable storage medium 120, a bus 130, and a communication unit 140.
In a specific implementation process, the processors 110 execute the computer executable instructions stored in the machine readable storage medium 120, so that the processors 110 may execute the big data based diet information pushing method according to the above method embodiment, the processors 110, the machine readable storage medium 120, and the communication unit 140 are connected through the bus 130, and the processors 110 may be configured to control the transceiving action of the communication unit 140, so as to perform data transceiving with the aforementioned diet information service terminal 200.
Machine-readable storage medium 120 may store data and/or instructions. In some embodiments, the machine-readable storage medium 120 may store data and/or instructions used by the diet push cloud platform 100 to perform or use to accomplish the exemplary methods described in this disclosure. In some embodiments, the machine-readable storage medium 120 may include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), and the like, or any combination thereof. Exemplary mass storage devices may include magnetic disks, optical disks, solid state disks, and the like. Exemplary removable memory may include flash drives, floppy disks, optical disks, memory cards, compact disks, magnetic tape, and the like. Exemplary volatile read and write memories can include Random Access Memory (RAM). Exemplary RAM may include healthy random access memory (DRAM), double data rate synchronous healthy random access memory (DDR SDRAM), Static Random Access Memory (SRAM), thyristor random access memory (T-RAM), and zero capacitance random access memory (Z-RAM), among others. Exemplary read-only memories may include mask read-only memory (MROM), programmable read-only memory (PROM), erasable programmable read-only memory (perrom), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), digital versatile disc read-only memory, and the like. In some embodiments, the machine-readable storage medium 120 may be implemented on the diet push cloud platform 100. By way of example only, the diet push cloud platform 100 may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-tiered cloud, and the like, or any combination thereof.
For a specific implementation process of the processor 110, reference may be made to the above-mentioned various method embodiments executed by the diet delivery cloud platform 100, which implement principles and technical effects are similar, and this embodiment is not described herein again.
In addition, the embodiment of the disclosure also provides a readable storage medium, which is preset with computer-executable instructions, and when a processor executes the computer-executable instructions, the method for pushing the diet information based on the big data is implemented.
It should be understood that the foregoing description is for purposes of illustration only and is not intended to limit the scope of the present disclosure. Many modifications and variations will be apparent to those of ordinary skill in the art in light of the description of the present disclosure. However, such modifications and variations do not depart from the scope of the present disclosure.
While the basic concepts have been described above, it will be apparent to those of ordinary skill in the art in view of this disclosure that the above disclosure is intended to be exemplary only and is not intended to limit the disclosure. Various modifications, improvements and adaptations to the present disclosure may occur to those skilled in the art, although not explicitly described herein. Such alterations, modifications, and improvements are intended to be suggested in this disclosure, and are intended to be within the spirit and scope of the exemplary embodiments of this disclosure.
Also, this disclosure uses specific words to describe embodiments of the disclosure. For example, "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the disclosure is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the disclosure may be combined as appropriate.
Further, those of ordinary skill in the art will understand that aspects of the present disclosure may be illustrated and described as embodied in several patentable categories or contexts, including any new and useful combination of processes, machines, articles, or materials, or any new and useful modification thereof. Accordingly, various aspects of the present disclosure may be carried out entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as a "unit", "module", or "system". Furthermore, aspects of the present disclosure may take the form of a computer program product embodied in one or more computer-readable media, with computer-readable program code embodied therein.
A computer readable signal medium may comprise a propagated data signal with computer program code embodied therein, for example, on a baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including electro-magnetic, optical, and the like, or any suitable combination. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code on a computer readable signal medium may be propagated over any suitable medium, including radio, electrical cable, fiber optic cable, RF, or the like, or any combination thereof.
Computer program code required for operation of portions of the present disclosure may be written in any one or more programming languages, including a subject oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, vb. net, Python, etc., a conventional programming language such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, a health programming language such as Python, Ruby, and Groovy, or other programming languages, etc. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).
Additionally, the order in which the elements and sequences of the present disclosure are processed, the use of numerical letters, or the use of other names are not intended to limit the order of the processes and methods of the present disclosure, unless explicitly recited in the claims. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the disclosed embodiments. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.
Similarly, it should be noted that in the preceding description of embodiments of the disclosure, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. Similarly, it should be noted that in the preceding description of embodiments of the disclosure, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments.
Claims (8)
1. A big data-based diet information pushing method is applied to a diet pushing cloud platform, the diet pushing cloud platform is in communication connection with a plurality of diet information service terminals, and the method comprises the following steps:
inputting the diet behavior big data of the diet information service terminal in a preset time period into a diet behavior characteristic learning model;
acquiring a first key diet tendency attribute sequence in the diet behavior big data of the preset time period through the diet behavior feature learning model;
acquiring first diet preference object data and first diet preference feature distribution in the diet behavior big data of the preset time period based on the first key diet tendency attribute sequence through the diet behavior feature learning model, wherein the first diet preference object data is diet preference object data corresponding to the first key diet tendency attribute sequence in the diet behavior big data of the preset time period;
clustering the first diet preference object data into a plurality of diet preference object groups through the diet behavior characteristic learning model, identifying diet preference indexes corresponding to each diet preference object group in the first diet preference object data based on the first diet preference characteristic distribution through the diet behavior characteristic learning model, and acquiring healthy diet preference indexes of each diet preference object unit in the first diet preference object data through the diet behavior characteristic learning model, wherein the diet preference indexes corresponding to the diet preference object groups are confidence degrees of key diet preference attributes existing in the diet preference object groups;
acquiring a diet behavior portrait result based on the diet preference index of each diet preference object group in the first diet preference object data, the information of the first key diet tendency attribute sequence and the healthy diet preference index of each diet preference object unit in the first diet preference object data, and pushing hot diet information to the diet information service terminal based on the diet behavior portrait result;
before the obtaining of the first key diet tendency attribute sequence in the diet behavior big data of the preset time period through the diet behavior feature learning model, the method comprises the following steps:
performing model optimization updating on the eating behavior characteristic learning model;
wherein the performing model optimization updating on the eating behavior characteristic learning model comprises:
inputting reference diet behavior big data into the diet behavior characteristic learning model;
acquiring a second frequent eating behavior tag characteristic distribution of the reference eating behavior big data through the eating behavior characteristic learning model;
acquiring second diet preference object data and third diet preference feature distribution in the reference diet behavior big data based on the second frequent diet behavior tag feature distribution through the diet behavior feature learning model;
clustering the second diet preference object data into a plurality of diet preference object groups through the diet behavior characteristic learning model, identifying diet preference indexes corresponding to each diet preference object group in the second diet preference object data based on the third diet preference characteristic distribution through the diet behavior characteristic learning model, and performing health concern characteristic extraction on the second frequent diet behavior tag characteristic distribution through the diet behavior characteristic learning model to obtain a second health concern characteristic distribution;
acquiring a first model evaluation index of the eating behavior characteristic learning model based on difference information between the eating preference index and a first reference eating preference index corresponding to each eating preference object group in the second eating preference object data, and acquiring a second model evaluation index of the eating behavior characteristic learning model based on difference information between the second health concern characteristic distribution and a second reference eating preference index;
improving model weight configuration data of the eating behavior feature learning model based on the first model assessment index and the second model assessment index;
wherein the obtaining, by the eating behavior feature learning model, a second eating preference object data and a third eating preference feature distribution in the eating behavior big data of the preset time period based on the second frequent eating behavior tag feature distribution includes:
acquiring a second candidate eating tendency attribute series of the reference eating behavior big data based on the second frequent eating behavior tag feature distribution through the eating behavior feature learning model, and taking the corresponding eating preference object data of the second candidate eating tendency attribute series in the reference eating behavior big data as the second eating preference object data;
acquiring the third diet preference feature distribution based on the second candidate diet tendency attribute series and the second frequent diet behavior tag feature distribution through the diet behavior feature learning model;
correspondingly, after the obtaining, by the eating behavior feature learning model, the third eating preference feature distribution based on the second candidate eating tendency attribute series and the second frequent eating behavior tag feature distribution, the method includes:
acquiring preference heat characteristic distribution and preference sharing characteristic distribution corresponding to the third diet preference characteristic distribution through the diet behavior characteristic learning model, wherein the preference heat characteristic distribution corresponding to the third diet preference characteristic distribution is used for representing confidence degrees that the second candidate diet tendency attribute series belong to the respective popular preference objects, and the preference sharing characteristic distribution corresponding to the third diet preference characteristic distribution is used for representing external sharing characteristics of a second key diet tendency attribute sequence relative to the second candidate diet tendency attribute series;
acquiring a third model evaluation index of the eating behavior characteristic learning model based on difference information between a preference heat characteristic distribution corresponding to the third eating preference characteristic distribution and a third reference eating preference index, and acquiring a fourth model evaluation index of the eating behavior characteristic learning model based on difference information between the preference sharing characteristic distribution corresponding to the third eating preference characteristic distribution and a fourth reference eating preference index;
improving model weight configuration data of the eating behavior feature learning model based on the third model assessment index and the fourth model assessment index.
2. The big data-based diet information pushing method according to claim 1, wherein the information of the first key diet tendency attribute sequence includes a distribution label of the first key diet tendency attribute sequence, and the obtaining of the diet behavior profiling result based on the diet preference index of each diet preference object group in the first diet preference object data, the information of the first key diet tendency attribute sequence and the healthy diet preference index of each diet preference object unit in the first diet preference object data includes:
determining diet preference object data with the key diet preference attribute in the first diet preference object data based on the diet preference index corresponding to each diet preference object group in the first diet preference object data, and determining the distribution label corresponding to the diet preference object unit in the first diet preference object data based on the healthy diet preference index of each diet preference object unit in the first diet preference object data, wherein the diet preference index corresponding to the diet preference object group with the key diet preference attribute is larger than a target index;
and determining the diet preference object units belonging to the distribution labels of the first key diet tendency attribute sequence in the diet preference object data with key diet tendency attributes as the diet behavior sketch result based on the distribution labels of each diet preference object unit in the first diet preference object data.
3. The big data-based diet information pushing method according to claim 1, wherein the obtaining of the first key diet tendency attribute sequence in the diet behavior big data of the preset time period through the diet behavior feature learning model comprises:
acquiring first frequent eating behavior label characteristic distribution in the eating behavior big data of the preset time period through the eating behavior characteristic learning model;
and acquiring a first key diet tendency attribute sequence in the diet behavior big data of the preset time period based on the first frequent diet behavior tag feature distribution through the diet behavior feature learning model.
4. The big data-based diet information pushing method according to claim 3, wherein the information of the first key diet tendency attribute sequence includes tendency component elements of the first key diet tendency attribute sequence, and the obtaining of the healthy diet preference index of each diet preference object unit in the first diet preference object data through the diet behavior feature learning model includes:
performing health concern feature extraction on the first frequent eating behavior tag feature distribution through the eating behavior feature learning model to obtain first health concern feature distribution corresponding to each eating preference object unit in the eating behavior big data of the preset time period;
determining a diet preference index corresponding to each diet preference object unit in the first health concern feature distribution in the first diet preference object data as a healthy diet preference index corresponding to the diet preference object unit in the first diet preference object data based on the trend constituent elements of the first key diet preference attribute sequence.
5. The big data-based eating information pushing method according to claim 3, wherein the obtaining of the first key eating tendency attribute sequence in the eating behavior big data of the preset time period based on the first frequent eating behavior tag feature distribution through the eating behavior feature learning model comprises:
acquiring a first candidate diet tendency attribute series in the diet behavior big data of the preset time period based on the first frequent diet behavior label characteristic distribution through the diet behavior characteristic learning model;
acquiring second diet preference characteristic distribution in the diet behavior big data of the preset time period based on the first candidate diet tendency attribute series and the first frequent diet behavior tag characteristic distribution through the diet behavior characteristic learning model;
and acquiring the first key diet tendency attribute sequence based on the second diet preference characteristic distribution through the diet behavior characteristic learning model.
6. The big data-based dietary information pushing method according to claim 5, wherein said obtaining said first key dietary propensity attribute sequence based on said second dietary preference feature distribution through said dietary behavior feature learning model comprises:
acquiring preference heat characteristic distribution and preference sharing characteristic distribution corresponding to the second diet preference characteristic distribution through the diet behavior characteristic learning model, wherein the preference heat characteristic distribution is used for representing the confidence degree that the first candidate diet tendency attribute series belongs to each popular preference object, and the preference sharing characteristic distribution is used for representing the external sharing characteristic of the first key diet tendency attribute series relative to the first candidate diet tendency attribute series;
acquiring information of the first key diet tendency attribute sequence based on preference heat characteristic distribution corresponding to the second diet preference characteristic distribution and preference sharing characteristic distribution corresponding to the second diet preference characteristic distribution;
correspondingly, the information of the first key dietary tendency attribute sequence further includes tendency components of the first key dietary tendency attribute sequence and distribution tags of the first key dietary tendency attribute sequence, and the information of the first key dietary tendency attribute sequence is obtained based on the preference popularity characteristic distribution corresponding to the second dietary preference characteristic distribution and the preference sharing characteristic distribution corresponding to the second dietary preference characteristic distribution, and includes:
performing label clustering on the preference heat characteristic distribution corresponding to the second diet preference characteristic distribution to obtain a distribution label of the first key diet preference attribute sequence;
and performing feature optimization on the preference sharing feature distribution corresponding to the second dietary preference feature distribution and the tendency component of the first candidate dietary tendency attribute series to obtain the tendency component of the first key dietary tendency attribute series.
7. The diet information pushing system based on the big data is characterized by comprising a diet pushing cloud platform and a plurality of diet information service terminals in communication connection with the diet pushing cloud platform;
the diet pushing cloud platform is used for:
inputting diet behavior big data of a preset time period into a diet behavior characteristic learning model;
acquiring a first key diet tendency attribute sequence in the diet behavior big data of the preset time period through the diet behavior feature learning model;
acquiring first diet preference object data and first diet preference feature distribution in the diet behavior big data of the preset time period based on the first key diet tendency attribute sequence through the diet behavior feature learning model, wherein the first diet preference object data is diet preference object data corresponding to the first key diet tendency attribute sequence in the diet behavior big data of the preset time period;
clustering the first diet preference object data into a plurality of diet preference object groups through the diet behavior characteristic learning model, identifying diet preference indexes corresponding to each diet preference object group in the first diet preference object data based on the first diet preference characteristic distribution through the diet behavior characteristic learning model, and acquiring healthy diet preference indexes of each diet preference object unit in the first diet preference object data through the diet behavior characteristic learning model, wherein the diet preference indexes corresponding to the diet preference object groups are confidence degrees of key diet preference attributes existing in the diet preference object groups;
acquiring a diet behavior sketch result based on the diet preference index of each diet preference object group in the first diet preference object data, the information of the first key diet tendency attribute sequence and the healthy diet preference index of each diet preference object unit in the first diet preference object data;
before the first key diet tendency attribute sequence in the diet behavior big data of the preset time period is obtained through the diet behavior feature learning model, the diet push cloud platform is used for:
performing model optimization updating on the eating behavior characteristic learning model;
wherein the performing model optimization updating on the eating behavior characteristic learning model comprises:
inputting reference diet behavior big data into the diet behavior characteristic learning model;
acquiring a second frequent eating behavior tag characteristic distribution of the reference eating behavior big data through the eating behavior characteristic learning model;
acquiring second diet preference object data and third diet preference feature distribution in the reference diet behavior big data based on the second frequent diet behavior tag feature distribution through the diet behavior feature learning model;
clustering the second diet preference object data into a plurality of diet preference object groups through the diet behavior characteristic learning model, identifying diet preference indexes corresponding to each diet preference object group in the second diet preference object data based on the third diet preference characteristic distribution through the diet behavior characteristic learning model, and performing health concern characteristic extraction on the second frequent diet behavior tag characteristic distribution through the diet behavior characteristic learning model to obtain a second health concern characteristic distribution;
acquiring a first model evaluation index of the eating behavior characteristic learning model based on difference information between the eating preference index and a first reference eating preference index corresponding to each eating preference object group in the second eating preference object data, and acquiring a second model evaluation index of the eating behavior characteristic learning model based on difference information between the second health concern characteristic distribution and a second reference eating preference index;
improving model weight configuration data of the eating behavior feature learning model based on the first model assessment index and the second model assessment index;
wherein the obtaining, by the eating behavior feature learning model, a second eating preference object data and a third eating preference feature distribution in the eating behavior big data of the preset time period based on the second frequent eating behavior tag feature distribution includes:
acquiring a second candidate eating tendency attribute series of the reference eating behavior big data based on the second frequent eating behavior tag feature distribution through the eating behavior feature learning model, and taking the corresponding eating preference object data of the second candidate eating tendency attribute series in the reference eating behavior big data as the second eating preference object data;
acquiring the third diet preference feature distribution based on the second candidate diet tendency attribute series and the second frequent diet behavior tag feature distribution through the diet behavior feature learning model;
correspondingly, after the obtaining, by the eating behavior feature learning model, the third eating preference feature distribution based on the second candidate eating tendency attribute series and the second frequent eating behavior tag feature distribution, the method includes:
acquiring preference heat characteristic distribution and preference sharing characteristic distribution corresponding to the third diet preference characteristic distribution through the diet behavior characteristic learning model, wherein the preference heat characteristic distribution corresponding to the third diet preference characteristic distribution is used for representing confidence degrees that the second candidate diet tendency attribute series belong to the respective popular preference objects, and the preference sharing characteristic distribution corresponding to the third diet preference characteristic distribution is used for representing external sharing characteristics of a second key diet tendency attribute sequence relative to the second candidate diet tendency attribute series;
acquiring a third model evaluation index of the eating behavior characteristic learning model based on difference information between a preference heat characteristic distribution corresponding to the third eating preference characteristic distribution and a third reference eating preference index, and acquiring a fourth model evaluation index of the eating behavior characteristic learning model based on difference information between the preference sharing characteristic distribution corresponding to the third eating preference characteristic distribution and a fourth reference eating preference index;
improving model weight configuration data of the eating behavior feature learning model based on the third model assessment index and the fourth model assessment index.
8. A diet pushing cloud platform, characterized in that the diet pushing cloud platform comprises a processor and a machine-readable storage medium, wherein the machine-readable storage medium has at least one instruction, at least one program, a code set or a set of instructions stored therein, and the at least one instruction, the at least one program, the code set or the set of instructions is loaded and executed by the processor to realize the big data based diet information pushing method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110689406.5A CN113254786B (en) | 2021-06-22 | 2021-06-22 | Big data-based diet information pushing method and system and cloud platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110689406.5A CN113254786B (en) | 2021-06-22 | 2021-06-22 | Big data-based diet information pushing method and system and cloud platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113254786A CN113254786A (en) | 2021-08-13 |
| CN113254786B true CN113254786B (en) | 2021-09-17 |
Family
ID=77189007
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110689406.5A Expired - Fee Related CN113254786B (en) | 2021-06-22 | 2021-06-22 | Big data-based diet information pushing method and system and cloud platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113254786B (en) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2586112B (en) * | 2014-08-14 | 2021-07-07 | Kenwood Ltd | Food preparation |
| CN110598064A (en) * | 2018-06-13 | 2019-12-20 | 佛山市顺德区美的电热电器制造有限公司 | Recipe recommendation method and system, computer device and computer-readable storage medium |
| CN112233772A (en) * | 2020-10-13 | 2021-01-15 | 杭州电子科技大学 | Healthy recipe recommendation system based on machine learning |
| CN112820379B (en) * | 2021-01-26 | 2024-02-02 | 吾征智能技术(北京)有限公司 | Intelligent diet recommendation method and system integrating user images |
-
2021
- 2021-06-22 CN CN202110689406.5A patent/CN113254786B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN113254786A (en) | 2021-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111615706A (en) | Analysis of spatial sparse data based on sub-manifold sparse convolutional neural network | |
| US20150278350A1 (en) | Recommendation System With Dual Collaborative Filter Usage Matrix | |
| WO2018086401A1 (en) | Cluster processing method and device for questions in automatic question and answering system | |
| US20200327190A1 (en) | Personalized book-to-movie adaptation recommendation | |
| US11928985B2 (en) | Content pre-personalization using biometric data | |
| US11126682B1 (en) | Hyperlink based multimedia processing | |
| CN110196904A (en) | A kind of method, apparatus and computer readable storage medium obtaining recommendation information | |
| CN111914176A (en) | Method and device for recommending subjects | |
| US11042576B2 (en) | Identifying and prioritizing candidate answer gaps within a corpus | |
| CN113011126B (en) | Text processing method, text processing device, electronic equipment and computer readable storage medium | |
| CN113326440B (en) | Artificial intelligence based recommendation method and device and electronic equipment | |
| CN108304381B (en) | Entity edge establishing method, device and equipment based on artificial intelligence and storage medium | |
| CN115858886B (en) | Data processing method, device, equipment and readable storage medium | |
| CN113656589B (en) | Object attribute determining method, device, computer equipment and storage medium | |
| CN113495962A (en) | Content optimization method based on intelligent medical big data and cloud computing service system | |
| CN116468096B (en) | Model training method, device, equipment and readable storage medium | |
| CN115935049A (en) | Recommendation processing method and device based on artificial intelligence and electronic equipment | |
| CN109635004A (en) | A kind of object factory providing method, device and the equipment of database | |
| CN113254786B (en) | Big data-based diet information pushing method and system and cloud platform | |
| CN115017200B (en) | Method and device for sorting search results, electronic equipment and storage medium | |
| Elahi | Empirical evaluation of active learning strategies in collaborative filtering | |
| CN113282839B (en) | Internet data push processing method and system | |
| CN114461822A (en) | Resource processing method, device, equipment and storage medium | |
| CN111091198B (en) | Data processing method and device | |
| CN113987239A (en) | Image pushing method and device, computer equipment, storage medium and product |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210917 |