CN112235596B - Live webcast-based food recommendation method and device - Google Patents
Live webcast-based food recommendation method and device Download PDFInfo
- Publication number
- CN112235596B CN112235596B CN202011431442.3A CN202011431442A CN112235596B CN 112235596 B CN112235596 B CN 112235596B CN 202011431442 A CN202011431442 A CN 202011431442A CN 112235596 B CN112235596 B CN 112235596B
- Authority
- CN
- China
- Prior art keywords
- information
- obtaining
- food
- video
- scoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
- H04N21/4756—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for rating content, e.g. scoring a recommended movie
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/482—End-user interface for program selection
- H04N21/4826—End-user interface for program selection using recommendation lists, e.g. of programs or channels sorted out according to their score
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Human Computer Interaction (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Economics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a food recommendation method and device based on live webcasting, wherein the method comprises the following steps: obtaining first video information; according to the first video information, obtaining the first online redplay information and the characteristic information of the first food; according to the oral sowing information and the characteristic information of the first food, obtaining the scoring information of the first food by the first net red; obtaining real scoring information of the first food product; obtaining first difference information of the two grading information; judging whether the first difference information exceeds the preset difference threshold value or not so as to determine whether first hot broadcast information is obtained or not; and increasing the recommendation times of the first video information according to the first hot broadcast information. The recommendation information is accurately evaluated and intelligently screened, and therefore the technical purpose of comprehensively meeting the requirements of consumers is achieved.
Description
Technical Field
The invention relates to the field of network live broadcast information processing, in particular to a food recommendation method and device based on network live broadcast.
Background
The network information processing process comprises information collection, information transmission, information processing and information storage. The live broadcast delivery means a novel service mode of carrying out short-distance commodity display, consultation response and shopping guide on users by a main broadcast through some internet platforms. People acquire information through a network live broadcast platform, and then various consumption requirements of the people are met. The method for recommending the restaurants through the live webcast is a novel mode, and consumers can select satisfactory restaurants according to the demands without going out.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
too much false information results in complicated information screening and filtering for the consumer, and thus the consumer's requirement cannot be met in all directions.
Disclosure of Invention
The embodiment of the application provides a live webcast-based food recommendation method and device, solves the technical problems that in the prior art, too much false information exists, information screening and filtering of consumers are complex, and the requirements of the consumers cannot be met in all directions, and achieves the technical purposes of accurately evaluating and intelligently screening recommendation information and meeting the requirements of the consumers in all directions.
The embodiment of the application provides a live webcast-based food recommendation method, wherein the method comprises the following steps: obtaining first video information, wherein the first video information is video recommendation information of first lipstick on first food; acquiring the first online redcasting information according to the first video information; according to the first video information, obtaining characteristic information of the first food; obtaining first scoring information according to the oral sowing information and the characteristic information of the first food, wherein the first scoring information is the scoring information of the first food by the first net red; obtaining second scoring information, wherein the second scoring information is real scoring information of the first food; obtaining a predetermined differential threshold; obtaining first score information according to the first score information and the second score information; judging whether the first differential information exceeds the preset differential threshold value or not, and obtaining a first judgment result; determining whether first hot broadcast information is obtained or not according to the first judgment result; and increasing the recommendation times of the first video information according to the first hot broadcast information.
On the other hand, this application still provides a live food recommendation device based on network, wherein, the device includes: the first obtaining unit is used for obtaining first video information, and the first video information is video recommendation information of first lipstick on first food; a second obtaining unit, configured to obtain, according to the first video information, the first online redcasting interface information; a third obtaining unit, configured to obtain feature information of the first food according to the first video information; a fourth obtaining unit, configured to obtain first scoring information according to the oral sowing information and the feature information of the first food, where the first scoring information is scoring information of the first food by the first lipstick; a fifth obtaining unit, configured to obtain second scoring information, where the second scoring information is real scoring information of the first food; a sixth obtaining unit configured to obtain a predetermined differential threshold; a seventh obtaining unit, configured to obtain first score information according to the first score information and the second score information; the first judging unit is used for judging whether the first differential information exceeds the preset differential threshold value or not and obtaining a first judging result; a second judging unit, configured to determine whether to obtain first hot broadcast information according to the first judgment result; the first execution unit is used for increasing the recommendation times of the first video information according to the first hot broadcast information.
On the other hand, an embodiment of the present application further provides a live webcast-based food recommendation device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the method according to the first aspect when executing the program.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
the method comprises the steps of identifying the oral broadcasting information of first food in the first net red live broadcasting through a semantic identification technology, so that the grading information of the first net red on the first food is obtained, judging the real effectiveness of the recommendation information of the first net red through obtaining the real grading information of the first food, and then determining the recommendation quantity of the video information of the first net red. The method and the device achieve the technical purpose of accurately evaluating the recommended information, thereby ensuring the authenticity of the live broadcast information and meeting the requirements of users.
The foregoing is a summary of the present disclosure, and embodiments of the present disclosure are described below to make the technical means of the present disclosure more clearly understood.
Drawings
Fig. 1 is a schematic flowchart of a live webcast-based food recommendation method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a live webcast-based food recommendation device according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of reference numerals: a first obtaining unit 11, a second obtaining unit 12, a third obtaining unit 13, a fourth obtaining unit 14, a fifth obtaining unit 15, a sixth obtaining unit 16, a seventh obtaining unit 17, a first judging unit 18, a second judging unit 19, a first executing unit 20, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, and a bus interface 306.
Detailed Description
The embodiment of the application provides a live webcast-based food recommendation method and device, solves the technical problems that in the prior art, too much false information exists, information screening and filtering of consumers are complex, and the requirements of the consumers cannot be met in all directions, and achieves the technical purposes of accurately evaluating and intelligently screening recommendation information and meeting the requirements of the consumers in all directions. Hereinafter, example embodiments of the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are merely some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.
Summary of the application
The live broadcast delivery means a novel service mode of carrying out short-distance commodity display, consultation response and shopping guide on users by a main broadcast through some internet platforms. The online live broadcast restaurant recommendation method is a novel method, and a consumer can select a satisfactory restaurant according to the demand without going out. The prior art has the technical problems that the false information is too much, the information screening and filtering of a consumer is complex, and the requirement of the consumer cannot be met in all directions.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the embodiment of the application provides a live webcast-based food recommendation method, wherein the method comprises the following steps: obtaining first video information, wherein the first video information is video recommendation information of first lipstick on first food; acquiring the first online redcasting information according to the first video information; according to the first video information, obtaining characteristic information of the first food; obtaining first scoring information according to the oral sowing information and the characteristic information of the first food, wherein the first scoring information is the scoring information of the first food by the first net red; obtaining second scoring information, wherein the second scoring information is real scoring information of the first food; obtaining a predetermined differential threshold; obtaining first score information according to the first score information and the second score information; judging whether the first differential information exceeds the preset differential threshold value or not, and obtaining a first judgment result; determining whether first hot broadcast information is obtained or not according to the first judgment result; and increasing the recommendation times of the first video information according to the first hot broadcast information.
Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
As shown in fig. 1, an embodiment of the present application provides a live webcast-based food recommendation method, where the method includes:
step S100: obtaining first video information, wherein the first video information is video recommendation information of first lipstick on first food;
step S200: acquiring the first online redcasting information according to the first video information;
specifically, the first video information is video recommendation information of first food by first net red acquired by a first direct broadcasting platform, and the first video information includes detailed information of restaurants, foods and the like recommended by the first net red. The first multicast information is information such as specific introduction, trial experience and recommendation reason of the first food by the first net red, and a foundation is laid for subsequent information evaluation by automatically acquiring the first video information.
Step S300: according to the first video information, obtaining characteristic information of the first food;
specifically, the characteristic information of the first food is obtained by filtering the first lipstick from the oral broadcasting information recommending the first food in the first video information based on a semantic recognition technology, and includes specific information such as the name, materials, category, cooking manner, taste and the like of the first food, and the user obtains the required food information by filtering the characteristic information of the first food. The method lays a foundation for subsequently obtaining the scoring information of the first net red on the first food.
Step S400: obtaining first scoring information according to the oral sowing information and the characteristic information of the first food, wherein the first scoring information is the scoring information of the first food by the first net red;
specifically, supervised learning is automatically performed on the oral broadcasting information and the characteristic information of the first food based on a machine learning model, so that the first scoring information is accurately obtained. The first grading information is the grading information of the first food by the first net red, and a foundation is laid for further evaluation of the first food subsequently by obtaining the first grading information.
Step S500: obtaining second scoring information, wherein the second scoring information is real scoring information of the first food;
specifically, the second scoring information is real scoring information of the first food, and is automatically obtained from information such as passenger flow volume, environment, geographical position, user comment and the like of the first restaurant based on a big data information processing technology. And integrating and processing the obtained information through information processing to obtain a comprehensive score, namely the second score information. And a foundation is laid for realizing the evaluation of the authenticity of the information by obtaining the second grading information.
Step S600: obtaining a predetermined differential threshold;
specifically, the preset score threshold is preset by a system, and threshold information of a difference value between the first score information and the second score information indicates that the difference value between the net red score and the real score of the first food is smaller and meets the authenticity of the information if the difference information is within the threshold; if the difference information is not within the threshold, the difference between the net red score and the real score of the first food is larger, and the authenticity of the information is poor. The technical aim of automatically evaluating the information so as to meet the requirements of consumers is fulfilled.
Step S700: obtaining first score information according to the first score information and the second score information;
step S800: judging whether the first differential information exceeds the preset differential threshold value or not, and obtaining a first judgment result;
specifically, the first difference information is difference information between the first score information and the second score information, the first multicast information of the first net red is evaluated by judging whether the first difference information exceeds the preset difference threshold, and if the difference information is within the preset difference threshold, the authenticity of the first multicast satisfaction information is represented; otherwise, it is not satisfied. The first judgment result is a judgment result used for judging whether the first grading information is real and effective. The technical purpose of guaranteeing the authenticity of the live broadcast information by effectively evaluating the food information is achieved.
Step S900: determining whether first hot broadcast information is obtained or not according to the first judgment result;
step S1000: and increasing the recommendation times of the first video information according to the first hot broadcast information.
Specifically, the first live information is information for automatically adding a hot degree to the first live video. If the first live webcast video information meets the information trueness and validity through information evaluation, first hot-cast information can be obtained, and the recommendation times of the first video information are automatically increased by the system, so that the heat is increased for the first video information. The technical purpose of reasonably recommending the live broadcast content through information evaluation so as to further meet the user requirements is achieved.
Further, in order to obtain the first score information, an embodiment S400 of the present application further includes:
step S401: taking the multicast information as first input information;
step S402: taking the characteristic information of the first food as second input information;
step S403: inputting the first input information and the second input information into a training model, wherein the training model is obtained by training a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises: the first input information, the second input information, and identification information for identifying a food score;
step S404: obtaining output information of the training model, wherein the output information comprises scoring information of the first food product.
Specifically, the machine model is obtained by training a plurality of sets of training data, and the process of training the neural network model by the training data is essentially a process of supervised learning. Each set of training data in the plurality of sets of training data comprises: the first input information, the second input information, and identification information for identifying a food score; under the condition of obtaining the first input information and the second input information, the machine learning model outputs identified food score information to verify the food score information output by the machine learning model, and if the output food score information is consistent with the identified food score information, the data supervised learning is finished, and then the next group of data supervised learning is carried out; and if the output food score information is inconsistent with the identified food score information, adjusting the machine learning model by the machine learning model, and performing supervised learning of the next group of data after the machine learning model reaches the expected accuracy. The machine learning model is continuously corrected and optimized through training data, the accuracy of the machine learning model for processing the data is improved through the process of supervised learning, and the food score information is more accurate. By accurately obtaining the food score information, a foundation is laid for the subsequent evaluation of the reality and the effectiveness of the live broadcast information.
Further, in order to obtain the second score information, step S500 in this embodiment of the present application further includes:
step S501: obtaining a first lens switching instruction;
step S502: obtaining second video information according to the first lens switching instruction, wherein the second video information comprises wide-angle video information of a first restaurant to which the first food belongs;
step S503: obtaining environment information of the first restaurant according to the second video information;
step S504: obtaining the number information of the diners in the first dining room according to the second video information;
step S505: and obtaining second scoring information according to the environment information of the first restaurant and the number of the diners.
Specifically, the first lens switching instruction is to automatically acquire the use permission of a rear image capturing device of the first live online-red broadcast equipment so as to acquire the second video information, wherein the second video information comprises wide-angle video information of a first restaurant to which the first food belongs, then the video information is used to automatically capture and acquire environment information and diner number information of the first restaurant, and the information is analyzed and sorted so as to acquire second grading information. Accurate evaluation of the first dining room real scoring information is achieved.
Further, step S100 in the embodiment of the present application further includes:
step S101: obtaining schedule information of a first user;
step S102: obtaining a preset time length threshold value;
step S103: judging whether the first user has holiday arrangement within the preset time threshold according to the schedule information;
step S104: if the first user has a vacation schedule within the predetermined length threshold, obtaining vacation length information for the first user;
step S105: acquiring first recommended region range information according to the vacation duration information;
step S106: and obtaining the first video information according to the first recommended region range information, wherein the first food recommended in the first video information is located within the first recommended region range information.
Specifically, based on a big data technology, the schedule access authority set by the first user is obtained, so that the schedule of the first user is obtained. The preset duration threshold is a preset time range for acquiring schedule information of the first user, if the first user has vacation arrangement within the preset duration threshold, vacation duration information of the first user is acquired, recommendation area information is acquired based on the vacation duration, and then live video information corresponding to restaurants within the first recommendation area range is recommended for the first user. The technical purpose that the live broadcast information is intelligently screened and filtered is achieved, and the user requirements are further met.
Further, step S105 in the embodiment of the present application further includes:
step S1051: obtaining trip information for a first user;
step S1052: determining whether the first user has trip plan information within the vacation schedule based on the trip information of the first user;
step S1053: if the first user has tour schedule information in the vacation arrangement, obtaining peer personnel information;
step S1054: obtaining recommendation point information of the persons in the same row, wherein the recommendation point information comprises age information, taste information and health information;
step S1055: and acquiring the first video information according to the recommendation point information and the first recommendation region range information of the peer information.
Specifically, based on a big data technology, obtaining itinerary information of a first user by obtaining ticket booking record information in a bill of the first user, then judging whether the first user has a tour schedule in the first holiday duration, and if the first user has the tour schedule in the first holiday duration, obtaining account information of live broadcast platforms of other tourists at the same destination according to the itinerary information of the first user. And obtaining the restaurant recommendation information of the fellow staff to the destination through the account information of the fellow staff, wherein the restaurant recommendation information of the fellow staff comprises the preference age range information, the taste information and the health degree information of the restaurant recommended by the fellow staff, and the age information, the preference taste and the health degree preference information of the first user are obtained. And obtaining the first video information according to the recommendation point information of the peer personnel and the first recommendation region range information, wherein the first video information is restaurant live broadcast information which is screened and meets the first user requirement in the first recommendation region range. The technical purpose that the live broadcast information is intelligently screened and filtered is achieved, and the user requirements are further met.
Further, step S502 in the embodiment of the present application further includes:
step S5021: acquiring acquisition time information of the second video information;
step S5022: obtaining information of the peak time of a meal;
step S5023: acquiring time difference information between the acquisition time information and the dining peak period information according to the dining peak period information and the acquisition time information of the second video information;
step S5024: obtaining a first correction parameter according to the time difference information;
step S5025: and correcting the second grading information according to the first correction parameter.
Specifically, the acquisition time of the second video information is obtained, whether the acquisition time is in a preset peak dining period or not is judged, time difference information between the acquisition time information and the peak dining period information is obtained, and the obtained second scoring information is automatically corrected by the system according to the time difference information, so that the accuracy of obtaining the second scoring information is guaranteed. The technical purpose of accurately evaluating the live broadcast information is achieved.
Further, step S5025 in the embodiment of the present application further includes:
step S50251: obtaining a first floating range;
step S50252: and correcting the second grading information in the first floating range according to the first correction parameter.
Specifically, the first floating range is a limit range for correcting the second scoring information according to the first correction parameter, and the second scoring information is corrected according to the first correction parameter within the first floating range. The correction range is limited, so that the correction error is reduced, and the technical purpose of obtaining more accurate second scoring information is achieved.
To sum up, the live webcast-based food recommendation method provided by the embodiment of the application has the following technical effects:
1. the method comprises the steps of identifying the oral broadcasting information of first food in the first net red live broadcasting through a semantic identification technology, so that the grading information of the first net red on the first food is obtained, judging the real effectiveness of the recommendation information of the first net red through obtaining the real grading information of the first food, and then determining the recommendation quantity of the video information of the first net red. The method and the device achieve the technical purpose of accurately evaluating the recommended information, thereby ensuring the authenticity of the live broadcast information and meeting the requirements of users.
2. Because the mode that the oral broadcasting information and the characteristic information of the first food are input into the training model and the food score is output by the training model is adopted, the obtained grading information of the first food is more accurate based on the characteristic that the training model can continuously optimize learning so as to obtain experience to process more accurate data, and the technical purpose of accurately evaluating the recommendation information is realized by accurately obtaining the grading information of the first food.
3. Due to the fact that the big data based technology is adopted, the schedule and journey information of the first user and the recommended place information of the same person are obtained, information such as restaurant positions and restaurant types required by the first user is analyzed, and then the first video information is intelligently recommended to the first user after the information is intelligently screened. The intelligent screening of the recommendation information is realized, and the technical purpose of comprehensively meeting the requirements of consumers is achieved.
Example two
Based on the same inventive concept as the live webcast-based food recommendation method in the foregoing embodiment, the present invention further provides a live webcast-based food recommendation device, as shown in fig. 2, the device includes:
the first obtaining unit 11 is configured to obtain first video information, where the first video information is video recommendation information of a first food for a first lipstick;
a second obtaining unit 12, where the second obtaining unit 12 is configured to obtain, according to the first video information, the first online redcasting information;
a third obtaining unit 13, where the third obtaining unit 13 is configured to obtain characteristic information of the first food according to the first video information;
a fourth obtaining unit 14, where the fourth obtaining unit 14 is configured to obtain first scoring information according to the oral sowing information and the feature information of the first food, and the first scoring information is scoring information of the first food by the first lipstick;
a fifth obtaining unit 15, where the fifth obtaining unit 15 is configured to obtain second scoring information, where the second scoring information is real scoring information of the first food;
a sixth obtaining unit 16, the sixth obtaining unit configured to obtain a predetermined differential threshold;
a seventh obtaining unit 17, where the seventh obtaining unit 17 is configured to obtain first difference information according to the first scoring information and the second scoring information;
a first judging unit 18, where the first judging unit 18 is configured to judge whether the first difference information exceeds the predetermined difference threshold, and obtain a first judgment result;
a second judging unit 19, where the second judging unit 19 is configured to determine whether to obtain first hot broadcast information according to the first judgment result;
a first executing unit 20, where the first executing unit 20 is configured to increase the recommendation times of the first video information according to the first hot-air information.
Further, the apparatus further comprises:
an eighth obtaining unit, configured to use the multicast information as first input information;
a ninth obtaining unit for taking the characteristic information of the first food as second input information;
a first input unit, configured to input the first input information and the second input information into a training model, where the training model is obtained by training multiple sets of training data, and each set of training data in the multiple sets of training data includes: the first input information, the second input information, and identification information for identifying a food score;
a tenth obtaining unit, configured to obtain output information of the training model, where the output information includes score information of the first food.
Further, the apparatus further comprises:
an eleventh obtaining unit configured to obtain a first lens switching instruction;
a twelfth obtaining unit, configured to obtain second video information according to the first lens switching instruction, where the second video information includes wide-angle video information of a first restaurant to which the first food belongs;
a thirteenth obtaining unit configured to obtain environment information of the first restaurant from the second video information;
a fourteenth obtaining unit, configured to obtain the number of people at the first dining room according to the second video information;
a fifteenth obtaining unit, configured to obtain first scoring information according to the environment information of the first restaurant and the number of people having meals.
Further, the apparatus further comprises:
a sixteenth obtaining unit configured to obtain schedule information of the first user;
a seventeenth obtaining unit, configured to obtain a predetermined duration threshold;
a third judging unit, configured to judge whether the first user has holiday arrangement within the predetermined time threshold according to the schedule information;
an eighteenth obtaining unit, configured to obtain vacation duration information of the first user if the first user has a vacation schedule within the predetermined duration threshold;
a nineteenth obtaining unit, configured to obtain first recommended region range information according to the vacation time length information;
a twentieth obtaining unit, configured to obtain the first video information according to the first recommended region range information, where the first food recommended in the first video information is located within the first recommended region range information.
Further, the apparatus further comprises:
a twenty-first obtaining unit for obtaining trip information of the first user;
a fourth determination unit configured to determine whether the first user has tour schedule information within the vacation schedule according to the trip information of the first user;
a twenty-second obtaining unit configured to obtain fellow person information if the first user has tour schedule information within the vacation schedule;
a twenty-third obtaining unit, configured to obtain recommendation point information of the peer information, where the recommendation point information includes age information, taste information, and health information;
a twenty-fourth obtaining unit, configured to obtain the first video information according to the recommendation point information of the peer information and the first recommendation region range information.
Further, the apparatus further comprises:
a twenty-fifth obtaining unit, configured to obtain acquisition time information of the second video information;
a twenty-sixth obtaining unit configured to obtain meal peak period information;
a twenty-seventh obtaining unit, configured to obtain time difference information between the collection time information and the peak meal time information according to the peak meal time information and the collection time information of the second video information;
a twenty-eighth obtaining unit, configured to obtain a first correction parameter according to the time difference information;
and the first correcting unit is used for correcting the second grading information according to the first correcting parameter.
Further, the apparatus further comprises:
a twenty-ninth obtaining unit to obtain a first floating range;
and the second correcting unit is used for correcting the second grading information in the first floating range according to the first correcting parameter.
Various changes and specific examples of the live webcast-based food recommendation method in the first embodiment of fig. 1 are also applicable to the live webcast-based food recommendation device in the present embodiment, and through the foregoing detailed description of the live webcast-based food recommendation method, those skilled in the art can clearly know the live webcast-based food recommendation device in the present embodiment, so for the sake of brevity of the description, detailed descriptions are not repeated here.
Exemplary electronic device
The electronic device of the embodiment of the present application is described below with reference to fig. 3.
Fig. 3 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of the live webcast-based food recommendation method in the foregoing embodiments, the present invention further provides a live webcast-based food recommendation apparatus, on which a computer program is stored, and when the computer program is executed by a processor, the steps of any one of the foregoing live webcast-based food recommendation methods are implemented.
Where in fig. 3 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 306 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. A live webcast-based food recommendation method comprises the following steps:
obtaining first video information, wherein the first video information is video recommendation information of first lipstick on first food;
acquiring the first online redcasting information according to the first video information;
according to the first video information, obtaining characteristic information of the first food;
obtaining first scoring information according to the oral sowing information and the characteristic information of the first food, wherein the first scoring information is the scoring information of the first food by the first net red;
obtaining second scoring information, wherein the second scoring information is real scoring information of the first food;
obtaining a predetermined differential threshold;
obtaining first score information according to the first score information and the second score information;
judging whether the first differential information exceeds the preset differential threshold value or not, and obtaining a first judgment result;
determining whether first hot broadcast information is obtained or not according to the first judgment result;
increasing the recommendation times of the first video information according to the first hot broadcast information;
wherein, judging whether the first difference information exceeds the preset difference threshold value to obtain a first judgment result, specifically:
when the first difference information does not exceed the preset difference threshold value, the first judgment result is that the first grading information is real and effective;
when the first difference information exceeds the preset difference threshold value, the first judgment result is that the first grading information is not true and effective;
determining whether to obtain first hot broadcast information according to the first judgment result, specifically:
and when the first judgment result shows that the first grading information is real and effective, determining to obtain the first hot broadcast information.
2. The method of claim 1, wherein said obtaining first scoring information based on said oral information and characteristic information of said first food product comprises:
taking the multicast information as first input information;
taking the characteristic information of the first food as second input information;
inputting the first input information and the second input information into a training model, wherein the training model is obtained by training a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises: the first input information, the second input information, and identification information for identifying a food score;
obtaining output information of the training model, wherein the output information comprises scoring information of the first food product.
3. The method of claim 1, wherein said obtaining second scoring information comprises:
obtaining a first lens switching instruction;
obtaining second video information according to the first lens switching instruction, wherein the second video information comprises wide-angle video information of a first restaurant to which the first food belongs;
obtaining environment information of the first restaurant according to the second video information;
obtaining the number information of the diners in the first dining room according to the second video information;
and obtaining second scoring information according to the environment information of the first restaurant and the number of the diners.
4. The method of claim 1, wherein said obtaining first video information comprises:
obtaining schedule information of a first user;
obtaining a preset time length threshold value;
judging whether the first user has holiday arrangement within the preset time threshold according to the schedule information;
if the first user has a vacation schedule within the predetermined length threshold, obtaining vacation length information for the first user;
acquiring first recommended region range information according to the vacation duration information;
and obtaining the first video information according to the first recommended region range information, wherein the first food recommended in the first video information is located within the first recommended region range information.
5. The method of claim 4, wherein the method comprises:
obtaining trip information for a first user;
determining whether the first user has trip plan information within the vacation schedule based on the trip information of the first user;
if the first user has tour schedule information in the vacation arrangement, obtaining peer personnel information;
obtaining recommendation point information of the persons in the same row, wherein the recommendation point information comprises age information, taste information and health information;
and acquiring the first video information according to the recommendation point information and the first recommendation region range information of the peer information.
6. The method of claim 3, wherein the method comprises:
acquiring acquisition time information of the second video information;
obtaining information of the peak time of a meal;
acquiring the acquisition time information according to the dining peak time information and the acquisition time information of the second video information
Time difference information between the rest and the rush hour information;
obtaining a first correction parameter according to the time difference information;
and correcting the second grading information according to the first correction parameter.
7. The method of claim 6, wherein the method comprises:
obtaining a first floating range;
and correcting the second grading information in the first floating range according to the first correction parameter.
8. A live webcast-based food recommendation device, wherein the device comprises:
the first obtaining unit is used for obtaining first video information, and the first video information is video recommendation information of first lipstick on first food;
a second obtaining unit, configured to obtain, according to the first video information, the first online redcasting interface information;
a third obtaining unit, configured to obtain feature information of the first food according to the first video information;
a fourth obtaining unit, configured to obtain first scoring information according to the oral sowing information and the feature information of the first food, where the first scoring information is scoring information of the first food by the first lipstick;
a fifth obtaining unit, configured to obtain second scoring information, where the second scoring information is real scoring information of the first food;
a sixth obtaining unit configured to obtain a predetermined differential threshold;
a seventh obtaining unit, configured to obtain first score information according to the first score information and the second score information;
the first judging unit is used for judging whether the first differential information exceeds the preset differential threshold value or not and obtaining a first judging result;
a second judging unit, configured to determine whether to obtain first hot broadcast information according to the first judgment result;
the first execution unit is used for increasing the recommendation times of the first video information according to the first hot broadcast information;
wherein, judging whether the first difference information exceeds the preset difference threshold value to obtain a first judgment result, specifically:
when the first difference information does not exceed the preset difference threshold value, the first judgment result is that the first grading information is real and effective;
when the first difference information exceeds the preset difference threshold value, the first judgment result is that the first grading information is not true and effective;
determining whether to obtain first hot broadcast information according to the first judgment result, specifically:
and when the first judgment result shows that the first grading information is real and effective, determining to obtain the first hot broadcast information.
9. A webcast-based food recommendation device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of claims 1-7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011431442.3A CN112235596B (en) | 2020-12-10 | 2020-12-10 | Live webcast-based food recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011431442.3A CN112235596B (en) | 2020-12-10 | 2020-12-10 | Live webcast-based food recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112235596A CN112235596A (en) | 2021-01-15 |
| CN112235596B true CN112235596B (en) | 2021-03-19 |
Family
ID=74123985
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011431442.3A Active CN112235596B (en) | 2020-12-10 | 2020-12-10 | Live webcast-based food recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112235596B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107205178A (en) * | 2017-04-25 | 2017-09-26 | 北京潘达互娱科技有限公司 | Direct broadcasting room recommends method and device |
| CN109344696A (en) * | 2018-08-14 | 2019-02-15 | 上海常仁信息科技有限公司 | A kind of points-scoring system and method based on vegetable identification |
| WO2019143714A1 (en) * | 2018-01-16 | 2019-07-25 | Habi, Inc. | Methods and systems for pet wellness platform |
| CN110475155A (en) * | 2019-08-19 | 2019-11-19 | 北京字节跳动网络技术有限公司 | Live video temperature state identification method, device, equipment and readable medium |
| CN111797756A (en) * | 2020-06-30 | 2020-10-20 | 平安国际智慧城市科技股份有限公司 | Video analysis method, device and medium based on artificial intelligence |
-
2020
- 2020-12-10 CN CN202011431442.3A patent/CN112235596B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107205178A (en) * | 2017-04-25 | 2017-09-26 | 北京潘达互娱科技有限公司 | Direct broadcasting room recommends method and device |
| WO2019143714A1 (en) * | 2018-01-16 | 2019-07-25 | Habi, Inc. | Methods and systems for pet wellness platform |
| CN109344696A (en) * | 2018-08-14 | 2019-02-15 | 上海常仁信息科技有限公司 | A kind of points-scoring system and method based on vegetable identification |
| CN110475155A (en) * | 2019-08-19 | 2019-11-19 | 北京字节跳动网络技术有限公司 | Live video temperature state identification method, device, equipment and readable medium |
| CN111797756A (en) * | 2020-06-30 | 2020-10-20 | 平安国际智慧城市科技股份有限公司 | Video analysis method, device and medium based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112235596A (en) | 2021-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20010039506A1 (en) | Process for automated real estate valuation | |
| Eschker* et al. | The NBA and the influx of international basketball players | |
| CN103647800A (en) | Method and system of recommending application resources | |
| US20160055418A1 (en) | Information processing apparatus, information processing method, and program | |
| CN107291672A (en) | The treating method and apparatus of tables of data | |
| CN107122386B (en) | Data screening method and device | |
| CN109767270A (en) | The old information recommendation method of housing support and system are deposited based on artificial intelligence | |
| Alencar et al. | A model for selecting project team members using multicriteria group decision making | |
| CN106127594A (en) | User room interest-degree computational methods based on principal component analysis and system | |
| Inoa et al. | Effect of an accessibility measure in a model for choice of residential location, workplace, and type of employment | |
| CN108053271A (en) | A kind of smart card certificate applied to commercial circle recommends the System and method for distribution | |
| CN107924544A (en) | Information processing system and information processing method | |
| CN110322114A (en) | Cell recommended method, device, equipment and storage medium based on big data | |
| KR20150113644A (en) | Method for selecting recommendation type in product recommeding system | |
| US20160306937A1 (en) | Smart health management service and system by using automation platform installed in smart phones | |
| CN110020152A (en) | Using recommended method and device | |
| JP2024097895A (en) | Image processing system, image processing method, and program | |
| JP6021223B2 (en) | Matching server | |
| CN112235596B (en) | Live webcast-based food recommendation method and device | |
| CN105719084A (en) | Catering service evaluation management method and catering service evaluation management device | |
| Alencar et al. | Multicriteria decision group model for the selection of suppliers | |
| CN101180879A (en) | Communication device, communication method, communication program, its recording medium, and integrated circuit | |
| JP5823332B2 (en) | Personal behavior preference analysis system and personal behavior preference analysis method | |
| CN110209916A (en) | A kind of point of interest image recommendation method and device | |
| Jankalová | Service quality-object of Business excellence measuring |
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 |