CN117829880B - Restaurant data intelligent supervision system and method based on artificial intelligence - Google Patents
Restaurant data intelligent supervision system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN117829880B CN117829880B CN202410083246.3A CN202410083246A CN117829880B CN 117829880 B CN117829880 B CN 117829880B CN 202410083246 A CN202410083246 A CN 202410083246A CN 117829880 B CN117829880 B CN 117829880B
- Authority
- CN
- China
- Prior art keywords
- operation behavior
- behavior information
- user portrait
- tag
- service platform
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 15
- 230000008569 process Effects 0.000 claims description 28
- 238000012544 monitoring process Methods 0.000 claims description 17
- 230000003993 interaction Effects 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 10
- 230000005856 abnormality Effects 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000001939 inductive effect Effects 0.000 claims description 2
- 230000006399 behavior Effects 0.000 description 169
- 230000009471 action Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Classifications
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- 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]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/12—Hotels or restaurants
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Primary Health Care (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of intelligent supervision of large dining data, in particular to an intelligent supervision system and an intelligent supervision method of dining data based on artificial intelligence.
Description
Technical Field
The invention relates to the technical field of intelligent supervision of big dining data, in particular to an intelligent supervision system and an intelligent supervision method of dining data based on artificial intelligence.
Background
Along with the rapid development of science and technology and the coming of digital age, big data are gradually becoming new pets in the catering industry, and the catering industry is taken as an industry closely related to daily life of people, and huge consumption data contain huge business opportunities. With the continuous development of internet technology, an online catering service platform has become an indispensable part of life of people, and through application of big data, catering industry can more accurately know demands of consumers, optimize operation and promote user experience. The online catering service platform is a platform for realizing online ordering, takeout distribution and other services through the Internet and artificial intelligence technology.
The application of the big data in the catering industry covers a plurality of aspects, firstly, the big data analysis can help catering enterprises to better know the taste preference and the consumption habit of consumers, and the catering enterprises can acquire precious market information by collecting and analyzing ordering data, consumption behaviors, evaluation comments and the like of the consumers, so that the product pricing can be accurately positioned, new dishes meeting the demands of the consumers can be pushed out, and personalized recommendation and service can be provided; however, when analyzing and processing data, big data is often affected by problems such as sample deviation and data quality, so that some analysis results may be deviated and misled.
Disclosure of Invention
The invention aims to provide an intelligent catering data supervision system and method based on artificial intelligence so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: an intelligent catering data supervision method based on artificial intelligence comprises the following steps:
Step S1: collecting operation behavior information generated by the online catering service platform on the basis of a preset user portrait rule according to the display interaction page of the grasping user on the online catering service platform, and generating all historical user portrait labels for the user;
Step S2: judging whether operation behavior information grabbing anomalies exist in the process of generating each historical user portrait label by the online catering service platform according to the quantity change distribution situation of catering service transaction orders presented by users under different historical user portrait labels, and dividing the corresponding historical user portrait labels into a first feature label and a second feature label based on the anomaly judgment result;
step S3: judging and identifying first characteristic operation behavior information which can induce the online catering service platform to generate an inaccurate user portrait tag according to similar clustering distribution conditions of the operation behavior information set when the online catering service platform generates the user portrait tag belonging to the first characteristic tag for the user;
Step S4: when the online catering service platform generates a user portrait tag belonging to a second characteristic tag for a user, screening out the second characteristic operation behavior information which can induce the online catering service platform to generate an accurate user portrait tag according to the operation behavior information set and the characteristic operation behavior information;
Step S5: the online catering service platform monitors the characteristic similarity distribution condition between the operation behavior information and the first characteristic operation behavior information or the second characteristic operation behavior information in real time for forming a new user portrait tag, the operation behavior information obtained by capturing is used for sorting the characteristic similarity distribution condition between the operation behavior information and the first characteristic operation behavior information or the second characteristic operation behavior information according to the operation behavior information set to be formed into the new user portrait tag, and the platform management terminal is used for assisting in adjusting the reference value weight of each operation behavior information in the operation behavior information set in the process of forming the new user portrait tag.
Preferably, when each history user portrait tag is generated for a user, the online catering service platform is required to grab the obtained operation behavior information set for the user according to a preset user portrait rule; each item of operation behavior information contained in the operation behavior information set is information obtained by capturing when a user performs information interaction with a display interaction page of the online catering service platform; wherein, the operation behavior information comprises an operation behavior and behavior attribute information corresponding to the operation behavior.
Preferably, step S2 includes:
step S2-1: according to the time sequence, all the historical user portrait labels generated by the online catering service platform for the user are collected to obtain a historical user portrait label sequence of the user; respectively gathering all the catering service transaction orders generated by the user under the online catering service platform in each historical user portrait label to obtain a catering service transaction order set corresponding to each historical user portrait label;
step S2-2: obtaining the number of the catering service trade orders contained in each catering service trade order set, calculating to obtain the total number M of the catering service trade orders generated based on all the historical user portrait labels, obtaining the total number N of the historical user portrait labels generated by an online catering service platform for users, and calculating the average catering service trade order number K=M/N;
Step S2-3: performing information traversal on the restaurant service transaction order set of each historical user portrait tag in the historical user portrait tag sequence; setting the restaurant service transaction order set of a certain historical user portrait tag a as A, setting the restaurant service transaction order set of a certain historical user portrait tag B which is adjacent to a certain historical user portrait tag a and is positioned in front of the certain historical user portrait tag a as B;
Step S2-4: when the card (A) is more than or equal to K or the card (A) is more than or equal to K and the card (A) is less than or equal to B, judging that the online catering service platform has abnormal grabbing of operation behavior information in the process of generating a certain historical user portrait tag a, and setting the certain historical user portrait tag a as a first characteristic tag; when the card (A) is more than or equal to K and the card (A) is more than or equal to card (B), judging that the online catering service platform has no operation behavior information grabbing abnormality in the process of generating a certain historical user portrait tag a, and setting the certain historical user portrait tag a as a second feature tag;
If the user portrait tag appears, the number of the catering service transaction orders contained in the corresponding catering service transaction order set is smaller than the average catering service transaction order number, and the online catering service platform is explained that the catering service data browse page intelligently recommended to the user does not prompt the user to maintain the past standard on the number of the catering service transaction orders generated on the online catering service platform based on the user portrait tag; if the number of the catering service trade orders contained in the corresponding catering service trade order set is smaller than the average catering service trade order number and the number of the catering service trade orders contained in the corresponding catering service trade order set is smaller than the number of the catering service trade orders contained in the catering service trade order set corresponding to the previous historical user portrait label, the online catering service platform is stated that the number of the catering service trade orders generated on the online catering service platform by the user is not promoted to be increased by the intelligently recommended catering data browse page for the user based on the user portrait label.
Preferably, step S3 includes:
Step S3-1: extracting an operation behavior information set according to which the online catering service platform generates each historical user portrait tag for a user; acquiring the feature classification of each historical user portrait tag in the historical user portrait tag sequence;
Step S3-2: setting the interval generation time between any first feature label and the next adjacent historical user portrait label as the feature reference time of any first feature label, extracting an operation behavior information set according to which the online catering service platform generates the first feature label with the largest corresponding feature reference time, and setting the operation behavior information set as a feature information set; setting an operation behavior information set according to which the online catering service platform generates other first characteristic labels as a target information set;
if the online catering service platform generates a first feature tag for the user, the catering data pushed to the user by the online catering service platform is mainly based on the catering data matched with the first feature tag in the maintenance period of the first feature tag, namely the catering data pushed by the user is mainly based on the catering data with deviation from the catering data really interested by the user; if the longer the first feature tag is switched to the next user portrait tag, the larger the continuous influence of the first feature tag on the user is, namely, the smaller the deviation between the dining data pushed by the user and the dining data really interested by the user is based on the first feature tag, the certain interference degree is brought to the user in the process of applying for the dining service trade order, for example, the screening and comparing process is increased;
Step S3-3: taking each item of operation behavior information in the characteristic information set as a clustering center; dividing each item of operation behavior information contained in each target information set into cluster centers with maximum similarity with each item of operation behavior information; and accumulating the total number of the operation behavior information contained in each clustering center, and judging the operation behavior information as the first characteristic operation behavior information which can induce the online catering service platform to generate an inaccurate user portrait tag if the total number of the operation behavior information contained in the clustering center is larger than a total number threshold value as one of the operation behavior information in the characteristic information set.
Preferably, step S4 includes:
Step S4-1: collecting all operation behavior information sets which are used for generating user portrait labels belonging to second feature labels for users by an online catering service platform to obtain a set Q, and removing operation behavior information with information similarity larger than a similarity threshold value from the set Q to obtain a set Q';
step S4-2: and judging each item of operation behavior information contained in the set Q' as second characteristic operation behavior information which can induce the online catering service platform to generate accurate user portrait tags.
Preferably, step S5 includes:
Step S5-1: accumulating the operation behavior information quantity H1 which is based on the operation behavior information set and has similarity larger than a similarity threshold value with any first characteristic operation behavior information and the operation behavior information quantity H2 which has similarity larger than a similarity threshold value with any second characteristic operation behavior information respectively when a new user portrait label is to be formed, monitoring the ratio G=H2 between H1 and H2 in real time, setting the lowest ratio F, deleting the first characteristic operation behavior information in the operation behavior information set when G is larger than or equal to F, and ensuring that G is maintained below F;
Step S5-2: the method comprises the steps that operation behavior information with similarity larger than a similarity threshold value between any first characteristic operation behavior information is used as a first type characteristic mark, and operation behavior information with similarity larger than a similarity threshold value between any second characteristic operation behavior information is used as a second type characteristic mark in an operation behavior information set according to which a new user portrait tag is to be formed;
And S5-3, feeding back the platform management terminal, wherein when a new user portrait tag is formed based on the operation behavior information set, the reference value weight which is set in the process of forming the new user portrait tag is set for the operation behavior information containing the first type of feature tag, the reference value weight is reduced on the basis of the original reference value weight, and the reference value weight which is set in the process of forming the new user portrait tag is set for the operation behavior information containing the second type of feature tag, and the reference value weight is increased on the basis of the original reference value weight.
In order to better realize the method, the intelligent monitoring system for the catering data is also provided, and comprises a user portrait tag arrangement module, a tag characteristic division management module, an operation behavior information judgment and identification module and an intelligent monitoring module;
the user portrait tag arrangement module is used for acquiring all history user portrait tags generated by the user on the basis of a preset user portrait rule by the online catering service platform according to operation behavior information generated by capturing the user on a display interaction page of the online catering service platform;
The tag feature division management module is used for judging whether the online catering service platform has operation behavior information grabbing abnormality in the process of generating each historical user portrait tag according to the quantity change distribution condition of catering service transaction orders presented by the online catering service platform by users under different historical user portrait tags, and dividing the corresponding historical user portrait tags into a first feature tag and a second feature tag based on the result of abnormality judgment;
the operation behavior information judging and identifying module is used for judging and identifying the first characteristic operation behavior information which can induce the online catering service platform to generate an inaccurate user portrait label according to the similar clustering distribution condition of the operation behavior information set when the online catering service platform generates the user portrait label belonging to the first characteristic label for the user; the operation behavior information set is used for screening out second characteristic operation behavior information which can induce the online catering service platform to generate accurate user portrait tags according to the characteristic operation behavior information when the online catering service platform generates the user portrait tags belonging to the second characteristic tags for the users;
The intelligent supervision module is used for monitoring the online catering service platform in real time to form a new user portrait tag, collecting all operation behavior information obtained by grabbing, sorting the characteristic similarity distribution situation between the operation behavior information and the first characteristic operation behavior information or the second characteristic operation behavior information according to the operation behavior information set which is about to form the new user portrait tag, and assisting the platform management terminal to adjust the reference value weight of all the operation behavior information in the operation behavior information set in the process of forming the new user portrait tag.
Preferably, the operation behavior information judgment and identification module comprises a first type judgment and identification management unit and a second type judgment and identification management unit;
The first-class judging and identifying management unit is used for judging and identifying the first characteristic operation behavior information which can induce the online catering service platform to generate an inaccurate user portrait label according to the similar clustering distribution condition of the operation behavior information set when the online catering service platform generates the user portrait label belonging to the first characteristic label for the user;
The second-class judging and identifying management unit is used for combing the operation behavior information set according to which the online catering service platform generates the user portrait tags belonging to the second feature tags for the users, and screening out the second feature operation behavior information which can induce the online catering service platform to generate the accurate user portrait tags by combining the feature operation behavior information.
Compared with the prior art, the invention has the following beneficial effects: according to the online dining service platform, the online dining service platform is combed to generate inaccurate and accurate user portrait tag operation behavior information unfolding occupation feature judgment and identification based on the change condition of the historical user portrait tag generated by the user based on the preset user portrait rule and the quantity change distribution condition of the dining service transaction orders presented by the user on the online dining service platform under different historical user portrait tags, portrait assessment of the online dining service platform on the user dining data is improved, accuracy of the online dining service platform on pushing the dining data by the user is effectively improved, user experience satisfaction of the user on the online dining service platform is effectively improved, and customer conversion rate and order transaction success rate of the online dining service platform are promoted.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic flow chart of an intelligent monitoring method for restaurant data based on artificial intelligence;
Fig. 2 is a schematic structural diagram of an intelligent catering data supervision system based on artificial intelligence.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, the present invention provides the following technical solutions: an intelligent catering data supervision method based on artificial intelligence comprises the following steps:
Step S1: collecting operation behavior information generated by the online catering service platform on the basis of a preset user portrait rule according to the display interaction page of the grasping user on the online catering service platform, and generating all historical user portrait labels for the user;
When each history user portrait tag is generated for a user, the online catering service platform is required to grab the obtained operation behavior information set for the user according to a preset user portrait rule; each item of operation behavior information contained in the operation behavior information set is information obtained by capturing when a user performs information interaction with a display interaction page of the online catering service platform; wherein, the operation behavior information comprises an operation behavior and behavior attribute information corresponding to the operation behavior;
For example, in a preset user portrait rule, it is specified that the clicking operation behavior of the user is an effective behavior to be grabbed when the user forms a user portrait tag, and because the behavior attribute information corresponding to the clicking operation behavior includes the frequency of the clicking operation behavior, the total number of clicking operation behaviors, that is, when judging whether the user is interested in a certain type of food, that is, when the user portrait tag, the frequency of clicking operation behaviors generated by the user on food information related to the type of food needs to be grabbed, the total number of clicking operation behaviors;
Step S2: judging whether operation behavior information grabbing anomalies exist in the process of generating each historical user portrait label by the online catering service platform according to the quantity change distribution situation of catering service transaction orders presented by users under different historical user portrait labels, and dividing the corresponding historical user portrait labels into a first feature label and a second feature label based on the anomaly judgment result;
wherein, step S2 includes:
step S2-1: according to the time sequence, all the historical user portrait labels generated by the online catering service platform for the user are collected to obtain a historical user portrait label sequence of the user; respectively gathering all the catering service transaction orders generated by the user under the online catering service platform in each historical user portrait label to obtain a catering service transaction order set corresponding to each historical user portrait label;
step S2-2: obtaining the number of the catering service trade orders contained in each catering service trade order set, calculating to obtain the total number M of the catering service trade orders generated based on all the historical user portrait labels, obtaining the total number N of the historical user portrait labels generated by an online catering service platform for users, and calculating the average catering service trade order number K=M/N;
Step S2-3: performing information traversal on the restaurant service transaction order set of each historical user portrait tag in the historical user portrait tag sequence; setting the restaurant service transaction order set of a certain historical user portrait tag a as A, setting the restaurant service transaction order set of a certain historical user portrait tag B which is adjacent to a certain historical user portrait tag a and is positioned in front of the certain historical user portrait tag a as B;
Step S2-4: when the card (A) is more than or equal to K or the card (A) is more than or equal to K and the card (A) is less than or equal to B, judging that the online catering service platform has abnormal grabbing of operation behavior information in the process of generating a certain historical user portrait tag a, and setting the certain historical user portrait tag a as a first characteristic tag; when the card (A) is more than or equal to K and the card (A) is more than or equal to card (B), judging that the online catering service platform has no operation behavior information grabbing abnormality in the process of generating a certain historical user portrait tag a, and setting the certain historical user portrait tag a as a second feature tag;
step S3: judging and identifying first characteristic operation behavior information which can induce the online catering service platform to generate an inaccurate user portrait tag according to similar clustering distribution conditions of the operation behavior information set when the online catering service platform generates the user portrait tag belonging to the first characteristic tag for the user;
wherein, step S3 includes:
Step S3-1: extracting an operation behavior information set according to which the online catering service platform generates each historical user portrait tag for a user; acquiring the feature classification of each historical user portrait tag in the historical user portrait tag sequence;
Step S3-2: setting the interval generation time between any first feature label and the next adjacent historical user portrait label as the feature reference time of any first feature label, extracting an operation behavior information set according to which the online catering service platform generates the first feature label with the largest corresponding feature reference time, and setting the operation behavior information set as a feature information set; setting an operation behavior information set according to which the online catering service platform generates other first characteristic labels as a target information set;
Step S3-3: taking each item of operation behavior information in the characteristic information set as a clustering center; dividing each item of operation behavior information contained in each target information set into cluster centers with maximum similarity with each item of operation behavior information; accumulating the total number of the operation behavior information contained in each clustering center, if one item of operation behavior information in the characteristic information set is used as the operation behavior information contained in the clustering center, and if the total number of the operation behavior information is larger than the total number threshold, judging the one item of operation behavior information as first characteristic operation behavior information capable of inducing the online catering service platform to generate an inaccurate user portrait label;
Step S4: when the online catering service platform generates a user portrait tag belonging to a second characteristic tag for a user, screening out the second characteristic operation behavior information which can induce the online catering service platform to generate an accurate user portrait tag according to the operation behavior information set and the characteristic operation behavior information;
wherein, step S4 includes:
Step S4-1: collecting all operation behavior information sets which are used for generating user portrait labels belonging to second feature labels for users by an online catering service platform to obtain a set Q, and removing operation behavior information with information similarity larger than a similarity threshold value from the set Q to obtain a set Q';
Step S4-2: judging each item of operation behavior information contained in the set Q' as second characteristic operation behavior information which can induce the online catering service platform to generate accurate user portrait tags;
Step S5: the online catering service platform is used for monitoring the characteristic similarity distribution situation between the operation behavior information and the first characteristic operation behavior information or the second characteristic operation behavior information in real time, wherein the operation behavior information is collected according to the operation behavior information when the new user portrait label is to be formed, and the platform management terminal is used for assisting in adjusting the reference value weight of each operation behavior information in the operation behavior information collection in the process of forming the new user portrait label;
Wherein, step S5 includes:
Step S5-1: accumulating the operation behavior information quantity H1 which is based on the operation behavior information set and has similarity larger than a similarity threshold value with any first characteristic operation behavior information and the operation behavior information quantity H2 which has similarity larger than a similarity threshold value with any second characteristic operation behavior information respectively when a new user portrait label is to be formed, monitoring the ratio G=H2 between H1 and H2 in real time, setting the lowest ratio F, deleting the first characteristic operation behavior information in the operation behavior information set when G is larger than or equal to F, and ensuring that G is maintained below F;
Step S5-2: the method comprises the steps that operation behavior information with similarity larger than a similarity threshold value between any first characteristic operation behavior information is used as a first type characteristic mark, and operation behavior information with similarity larger than a similarity threshold value between any second characteristic operation behavior information is used as a second type characteristic mark in an operation behavior information set according to which a new user portrait tag is to be formed;
S5-3, feeding back the platform management terminal, wherein when a new user portrait tag is formed based on the operation behavior information set, the operation behavior information containing the first type of feature tag is set as the reference value weight set in the process of forming the new user portrait tag, the reference value weight is reduced on the basis of the original reference value weight, and the operation behavior information containing the second type of feature tag is set as the reference value weight set in the process of forming the new user portrait tag, and the reference value weight is increased on the basis of the original reference value weight;
for example, when judging whether a user is interested in a certain type of food, capturing click operation behaviors, browse operation behaviors and order transaction behaviors generated by the user on food information related to the food; according to the above scheme, the number of times of clicking operation on the food information related to a certain type of food is less than 10, and the number of times of clicking operation on the food information related to a certain type of food originally generated by the platform management terminal is less than 10, wherein the number of times of clicking operation on the food information related to a certain type of food is less than 10, and the set reference value weight is 0.8 when the interest degree of a user on a certain type of food is calculated, so that the platform management terminal can be fed back to adjust 0.8;
in order to better realize the method, the intelligent monitoring system for the catering data is also provided, and comprises a user portrait tag arrangement module, a tag characteristic division management module, an operation behavior information judgment and identification module and an intelligent monitoring module;
the user portrait tag arrangement module is used for acquiring all history user portrait tags generated by the user on the basis of a preset user portrait rule by the online catering service platform according to operation behavior information generated by capturing the user on a display interaction page of the online catering service platform;
The tag feature division management module is used for judging whether the online catering service platform has operation behavior information grabbing abnormality in the process of generating each historical user portrait tag according to the quantity change distribution condition of catering service transaction orders presented by the online catering service platform by users under different historical user portrait tags, and dividing the corresponding historical user portrait tags into a first feature tag and a second feature tag based on the result of abnormality judgment;
the operation behavior information judging and identifying module is used for judging and identifying the first characteristic operation behavior information which can induce the online catering service platform to generate an inaccurate user portrait label according to the similar clustering distribution condition of the operation behavior information set when the online catering service platform generates the user portrait label belonging to the first characteristic label for the user; the operation behavior information set is used for screening out second characteristic operation behavior information which can induce the online catering service platform to generate accurate user portrait tags according to the characteristic operation behavior information when the online catering service platform generates the user portrait tags belonging to the second characteristic tags for the users;
The intelligent supervision module is used for monitoring the online catering service platform in real time to form a new user portrait tag, collecting all operation behavior information obtained by grabbing, sorting the characteristic similarity distribution situation between the operation behavior information and the first characteristic operation behavior information or the second characteristic operation behavior information according to the operation behavior information set which is about to form the new user portrait tag, and assisting the platform management terminal to adjust the reference value weight of all the operation behavior information in the operation behavior information set in the process of forming the new user portrait tag.
The operation behavior information judging and identifying module comprises a first type judging and identifying management unit and a second type judging and identifying management unit;
The first-class judgment and identification management unit is used for judging and identifying the first characteristic operation behavior information which can induce the online catering service platform to generate an inaccurate user portrait label according to the similar clustering distribution condition of the operation behavior information set when the online catering service platform generates the user portrait label belonging to the first characteristic label for the user
The second-class judging and identifying management unit is used for combing the operation behavior information set according to which the online catering service platform generates the user portrait tags belonging to the second feature tags for the users, and screening out the second feature operation behavior information which can induce the online catering service platform to generate the accurate user portrait tags by combining the feature operation behavior information.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. An intelligent catering data supervision method based on artificial intelligence, which is characterized by comprising the following steps:
Step S1: collecting operation behavior information generated by the online catering service platform on the basis of a preset user portrait rule according to the display interaction page of the grasping user on the online catering service platform, and generating all historical user portrait labels for the user;
Step S2: judging whether operation behavior information grabbing anomalies exist in the process of generating each historical user portrait label by the online catering service platform according to the quantity change distribution situation of catering service transaction orders presented by users under different historical user portrait labels, and dividing the corresponding historical user portrait labels into a first feature label and a second feature label based on the anomaly judgment result;
step S3: judging and identifying first characteristic operation behavior information which can induce the online catering service platform to generate an inaccurate user portrait tag according to similar clustering distribution conditions of the operation behavior information set when the online catering service platform generates the user portrait tag belonging to the first characteristic tag for the user;
Step S4: when the online catering service platform generates a user portrait tag belonging to a second characteristic tag for a user, screening out the second characteristic operation behavior information which can induce the online catering service platform to generate an accurate user portrait tag according to the operation behavior information set and the characteristic operation behavior information;
Step S5: the method comprises the steps that an online catering service platform is monitored in real time to form a new user portrait tag, all operation behavior information obtained through grabbing is arranged, feature similarity distribution conditions between operation behavior information and first feature operation behavior information or second feature operation behavior information in an operation behavior information set which is about to form the new user portrait tag are arranged, and a platform management terminal is used for assisting in adjusting reference value weights of all operation behavior information in the operation behavior information set in the process of forming the new user portrait tag;
The step S2 includes:
step S2-1: according to the time sequence, all the historical user portrait labels generated by the online catering service platform for the user are collected to obtain a historical user portrait label sequence of the user; respectively gathering all the catering service transaction orders generated by the user under the online catering service platform in each historical user portrait label to obtain a catering service transaction order set corresponding to each historical user portrait label;
step S2-2: obtaining the number of the catering service trade orders contained in each catering service trade order set, calculating to obtain the total number M of the catering service trade orders generated based on all the historical user portrait labels, obtaining the total number N of the historical user portrait labels generated by an online catering service platform for users, and calculating the average catering service trade order number K=M/N;
Step S2-3: performing information traversal on the restaurant service transaction order set of each historical user portrait tag in the historical user portrait tag sequence; setting the restaurant service transaction order set of a certain historical user portrait tag a as A, setting the restaurant service transaction order set of a certain historical user portrait tag B which is adjacent to the certain historical user portrait tag a and is positioned in front of the certain historical user portrait tag a as B;
Step S2-4: when the card (A) is more than or equal to K or the card (A) is more than or equal to K and the card (A) is less than or equal to the card (B), judging that the online catering service platform has abnormal grabbing of operation behavior information in the process of generating the certain historical user portrait tag a, and setting the certain historical user portrait tag a as a first feature tag; when the card (A) is more than or equal to K and the card (A) is more than or equal to card (B), judging that the online catering service platform has no operation behavior information grabbing abnormality in the process of generating the certain historical user portrait tag a, and setting the certain historical user portrait tag a as a second characteristic tag;
the step S3 includes:
Step S3-1: extracting an operation behavior information set according to which the online catering service platform generates each historical user portrait tag for a user; acquiring the feature classification of each historical user portrait tag in the historical user portrait tag sequence;
Step S3-2: setting the interval generation time between any first feature label and the next adjacent historical user portrait label as the feature reference time of the any first feature label, extracting an operation behavior information set according to which the online catering service platform generates the first feature label with the largest corresponding feature reference time, and setting the operation behavior information set as a feature information set; setting an operation behavior information set according to which the online catering service platform generates other first characteristic labels as a target information set;
step S3-3: taking each item of operation behavior information in the characteristic information set as a clustering center; dividing each item of operation behavior information contained in each target information set into clustering centers with maximum similarity with each item of operation behavior information; and accumulating the total number of the operation behavior information contained in each clustering center, and judging that one item of operation behavior information contained in the clustering center is larger than a total number threshold value if one item of operation behavior information contained in the characteristic information set is used as the first characteristic operation behavior information capable of inducing the online catering service platform to generate an inaccurate user portrait tag.
2. The intelligent monitoring method for restaurant data based on artificial intelligence according to claim 1, wherein the online restaurant service platform captures the operation behavior information set obtained by capturing the user according to the user portrait rules based on the preset rules when generating each history user portrait label for the user; each item of operation behavior information contained in the operation behavior information set is information obtained by capturing when a user performs information interaction with a display interaction page of the online catering service platform; wherein, the operation behavior information comprises an operation behavior and behavior attribute information corresponding to the operation behavior.
3. An intelligent supervision method for restaurant data based on artificial intelligence according to claim 1, wherein the step S4 includes:
Step S4-1: collecting all operation behavior information sets which are used for generating user portrait labels belonging to second feature labels for users by an online catering service platform to obtain a set Q, and removing operation behavior information with information similarity larger than a similarity threshold value from the set Q to obtain a set Q';
step S4-2: and judging each item of operation behavior information contained in the set Q' as second characteristic operation behavior information which can induce the online catering service platform to generate accurate user portrait tags.
4. An intelligent monitoring method for restaurant data based on artificial intelligence according to claim 3, wherein said step S5 comprises:
Step S5-1: accumulating the operation behavior information quantity H1 which is based on the operation behavior information set and has similarity larger than a similarity threshold value with any first characteristic operation behavior information and the operation behavior information quantity H2 which has similarity larger than a similarity threshold value with any second characteristic operation behavior information respectively when a new user portrait label is to be formed, monitoring the ratio G=H2 between H1 and H2 in real time, setting the lowest ratio F, and deleting the first characteristic operation behavior information in the operation behavior information set when G is larger than or equal to F, so as to ensure that G is maintained below F;
Step S5-2: the method comprises the steps that operation behavior information with similarity larger than a similarity threshold value between any first characteristic operation behavior information is used as a first type characteristic mark, and operation behavior information with similarity larger than a similarity threshold value between any second characteristic operation behavior information is used as a second type characteristic mark in an operation behavior information set according to which a new user portrait tag is to be formed;
Step S5-3: the feedback platform management terminal is used for setting the reference value weight which is set in the process of forming the new user portrait tag for the operation behavior information containing the first type of feature tag when the new user portrait tag is formed based on the operation behavior information set, setting down the reference value weight based on the original reference value weight, and setting up the reference value weight which is set in the process of forming the new user portrait tag for the operation behavior information containing the second type of feature tag based on the original reference value weight.
5. An intelligent monitoring system for restaurant data for executing the intelligent monitoring method for restaurant data based on artificial intelligence as claimed in any one of claims 1-4, characterized in that the system comprises a user portrait tag arrangement module, a tag feature division management module, an operation behavior information judgment and identification module and an intelligent monitoring module;
The user portrait tag arrangement module is used for collecting all historical user portrait tags generated by the user according to operation behavior information generated by capturing the user on a display interaction page of the online catering service platform based on a preset user portrait rule;
The tag feature division management module is used for judging whether the online catering service platform has operation behavior information grabbing abnormality in the process of generating each historical user portrait tag according to the quantity change distribution condition of catering service transaction orders presented by the online catering service platform by users under different historical user portrait tags, and dividing the corresponding historical user portrait tags into a first feature tag and a second feature tag based on the result of abnormality judgment;
the operation behavior information judging and identifying module is used for judging and identifying the first characteristic operation behavior information which can induce the online catering service platform to generate an inaccurate user portrait label according to the similar clustering distribution condition of the operation behavior information set when the online catering service platform generates the user portrait label belonging to the first characteristic label for the user; the operation behavior information set is used for screening out second characteristic operation behavior information which can induce the online catering service platform to generate accurate user portrait tags according to the characteristic operation behavior information when the online catering service platform generates the user portrait tags belonging to the second characteristic tags for the users;
The intelligent supervision module is used for monitoring the online catering service platform in real time to form a new user portrait tag, acquiring various operation behavior information, sorting characteristic similar distribution conditions between operation behavior information and first characteristic operation behavior information or second characteristic operation behavior information according to the operation behavior information set to be formed into the new user portrait tag, and assisting the platform management terminal to adjust reference value weights of the operation behavior information in the operation behavior information set in the process of forming the new user portrait tag.
6. The intelligent catering data supervision system according to claim 5, wherein the operation behavior information judgment and identification module comprises a first type judgment and identification management unit and a second type judgment and identification management unit;
the first type judgment and identification management unit is used for judging and identifying first characteristic operation behavior information which can induce the online catering service platform to generate an inaccurate user portrait label according to similar clustering distribution conditions of the operation behavior information set when the online catering service platform generates the user portrait label belonging to the first characteristic label for the user;
The second-class judging and identifying management unit is used for combing the operation behavior information set according to which the online catering service platform generates the user portrait tags belonging to the second feature tags for the users, and screening out the second feature operation behavior information which can induce the online catering service platform to generate the accurate user portrait tags by combining the feature operation behavior information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410083246.3A CN117829880B (en) | 2024-01-19 | 2024-01-19 | Restaurant data intelligent supervision system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410083246.3A CN117829880B (en) | 2024-01-19 | 2024-01-19 | Restaurant data intelligent supervision system and method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117829880A CN117829880A (en) | 2024-04-05 |
| CN117829880B true CN117829880B (en) | 2024-07-12 |
Family
ID=90522870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410083246.3A Active CN117829880B (en) | 2024-01-19 | 2024-01-19 | Restaurant data intelligent supervision system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117829880B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111159551A (en) * | 2019-12-30 | 2020-05-15 | 汉海信息技术(上海)有限公司 | Display method and device of user-generated content and computer equipment |
| WO2020232615A1 (en) * | 2019-05-20 | 2020-11-26 | 深圳市欢太科技有限公司 | Information recommendation method and apparatus, and electronic device and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105468630A (en) * | 2014-09-04 | 2016-04-06 | 口碑控股有限公司 | Method and apparatus for providing user information |
| CN113127723B (en) * | 2019-12-31 | 2023-07-14 | Oppo（重庆）智能科技有限公司 | User portrait processing method, device, server and storage medium |
| CN114331486A (en) * | 2020-10-12 | 2022-04-12 | 腾讯科技（北京）有限公司 | User portrait updating method, device, equipment and medium |
| CN115687786A (en) * | 2022-11-18 | 2023-02-03 | 广东大比特网络科技有限公司 | Personalized recommendation method, system and storage medium |
| CN117271884A (en) * | 2023-08-18 | 2023-12-22 | 百度时代网络技术（北京）有限公司 | Method, device, electronic equipment and storage medium for determining recommended content |
-
2024
- 2024-01-19 CN CN202410083246.3A patent/CN117829880B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020232615A1 (en) * | 2019-05-20 | 2020-11-26 | 深圳市欢太科技有限公司 | Information recommendation method and apparatus, and electronic device and storage medium |
| CN111159551A (en) * | 2019-12-30 | 2020-05-15 | 汉海信息技术(上海)有限公司 | Display method and device of user-generated content and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117829880A (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109685631B (en) | Personalized recommendation method based on big data user behavior analysis | |
| CN105589905B (en) | The analysis of user interest data and collection system and its method | |
| WO2009116198A1 (en) | Advertisement medium determination device and advertisement medium determination method | |
| TWI793412B (en) | Consumption prediction system and consumption prediction method | |
| CN117829914B (en) | Digital media advertisement effect evaluation system | |
| CN105956883A (en) | Electronic commerce data processing system | |
| CN113159881B (en) | Data clustering and B2B platform customer preference obtaining method and system | |
| CN116862592B (en) | Automatic push method for SOP private marketing information based on user behavior | |
| CN112184484B (en) | Differentiated service method and system for power users | |
| CN111984873A (en) | Service recommendation system and method | |
| WO2022036894A1 (en) | Commodity recommendation system based on mining of high-utility negative sequential rule for decision-making, and working method of commodity recommendation system | |
| WO2020171066A1 (en) | Image search device and training data extraction method | |
| CN111737338A (en) | Big data portrait-based closed-loop marketing data analysis method | |
| CN111401973A (en) | Commodity demand prediction information prediction system and method under multiple influence factors | |
| CN115983952A (en) | Custom garment design recommendation system | |
| CN117726412A (en) | AI recommendation system and method based on big data | |
| CN116468460A (en) | Consumer finance customer image recognition system and method based on artificial intelligence | |
| CN117557299A (en) | Marketing planning method and system based on computer assistance | |
| CN116320626A (en) | Method and system for calculating live broadcast heat of electronic commerce | |
| CN116228319A (en) | Intelligent advertisement putting method and system based on buried points | |
| CN117829880B (en) | Restaurant data intelligent supervision system and method based on artificial intelligence | |
| CN104331395A (en) | Method and device for identifying Chinese product name from text | |
| Chakraborty et al. | Clustering of web sessions by FOGSAA | |
| CN117746546A (en) | Service business handling method and system based on number calling device | |
| CN117372056A (en) | User behavior analysis system based on machine learning |
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 |