CN112561669A - Catering information recommendation system based on data analysis - Google Patents
Catering information recommendation system based on data analysis Download PDFInfo
- Publication number
- CN112561669A CN112561669A CN202110222719.XA CN202110222719A CN112561669A CN 112561669 A CN112561669 A CN 112561669A CN 202110222719 A CN202110222719 A CN 202110222719A CN 112561669 A CN112561669 A CN 112561669A
- Authority
- CN
- China
- Prior art keywords
- unit
- dish
- dishes
- data
- support degree
- 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.)
- Granted
Links
- 238000007405 data analysis Methods 0.000 title claims abstract description 19
- 238000012216 screening Methods 0.000 claims abstract description 67
- 238000004458 analytical method Methods 0.000 claims abstract description 46
- 238000013523 data management Methods 0.000 claims abstract description 37
- 238000012937 correction Methods 0.000 claims abstract description 33
- 238000013461 design Methods 0.000 claims abstract description 22
- 238000000034 method Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000001228 spectrum Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 3
- 238000007873 sieving Methods 0.000 claims description 2
- 230000001932 seasonal effect Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000019640 taste Nutrition 0.000 description 1
Images
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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- 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
- 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
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a catering information recommendation system based on data analysis, which comprises: the system comprises a consumption record acquisition unit, a personal information acquisition unit, a sales amount statistics unit, a data management platform, a data calling unit, a client classification unit, a support degree analysis unit, a correction similarity analysis unit, a recommended dish screening unit, an electronic menu design unit and a client, wherein the personal information acquisition unit confirms whether a client is a non-member or a member, collects order records of the member through the consumption record acquisition unit, and the support degree analysis unit analyzes the support degrees of single dishes and combined dishes according to the order records of the member client and recommends the combined dishes to the non-member client from large to small according to the support degrees; the sales amount weight of the dishes in each month is counted through the sales amount counting unit, and the dishes are recommended to member customers according to the correction similarity degree from large to small by combining the correction similarity degree analyzing unit, so that the requirements of different customers are met, and the sales amount of the restaurant dishes is increased.
Description
Technical Field
The invention relates to the technical field of big data, in particular to a catering information recommendation system based on data analysis.
Background
Along with the continuous development of social and economic levels, electronic commerce websites are rapidly developed along with the continuous development of the social and economic levels, data mining technology is greatly improved, recommendation systems are widely applied, the recommendation systems can be convenient for consumers to quickly position commodities needed by the consumers in complex and changeable commodity information, the experience of the users can be improved, the loss of the clients is avoided, the application of the catering information recommendation systems can attract the eyes of a large number of clients, the convenience and the experience of ordering and dining of the users are improved, because the identities of the clients in restaurants are different, some clients are members, some clients possibly are clients ordering for the first time, the unified recommendation of the catering information is too monotonous, ordered dishes also can not accord with the tastes of the clients, the loss condition of the clients can be caused, different recommendation modes are designed for member clients and non-member clients, and the requirements of different clients can be met, the sales volume of dishes can also be increased.
Therefore, a catering information recommendation system based on data analysis is needed to solve the above problems.
Disclosure of Invention
The invention aims to provide a catering information recommendation system based on data analysis, and aims to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: the catering information recommendation system based on data analysis is characterized in that: the method comprises the following steps: the system comprises a consumption record acquisition unit, a personal information acquisition unit, a sales statistic unit, a data management platform, a data calling unit, a customer classification unit, a support degree analysis unit, a correction similarity analysis unit, a recommended dish screening unit, an electronic menu design unit and a client;
the output ends of the consumption record acquisition unit, the personal information acquisition unit and the sales statistic unit are connected with the input end of the data management platform, the output end of the data management platform is connected with the input end of the data retrieval unit, the output end of the data retrieval unit is connected with the input end of the customer classification unit, the output end of the customer classification unit is connected with the input ends of the support degree analysis unit and the correction similarity analysis unit, the output ends of the support degree analysis unit and the correction similarity analysis unit are connected with the input end of the recommended dish screening unit, the output end of the recommended dish screening unit is connected with the input ends of the electronic dish spectrum design unit and the support degree analysis unit, and the output end of the electronic dish spectrum screening unit is connected with the input end of the client;
the consumption record acquisition unit acquires order records of restaurant members and inputs the order records into the data management platform, the personal information acquisition unit acquires personal information of different customers and inputs the personal information into the data management platform, the data calling unit calls the personal information and the order record data in the data management platform to the customer classification unit, and the customer classification unit classifies the customers into two batches by analyzing the personal information and the order record data of the customers: the support degree analysis unit analyzes and confirms the support degree of dishes according to the order details in the called member order record, and transmits the support degree data to the recommended dish screening unit, and the recommended dish screening unit recommends the screened dish combination for the non-member customers according to the support degree data;
sales statistics unit reaches the dish sales data transmission of every month in nearly one year data management platform, data management platform statistics sales weight data, through revising similarity analysis unit and combining the order quantity and the sales weight analysis of every dish its similarity, through data calling unit calls sales weight data in the data management platform will revise similarity data transmission to in recommending the dish screening unit, recommend the dish screening unit and recommend the dish of sieving for the member customer according to similarity data.
Furthermore, the consumption record acquisition unit acquires n groups of order dish sets of the member customers, and the different dish sets in the dish sets are A = { A =1,A2,...AiWherein i representsCounting the total number of different dishes until the frequency set of the corresponding dishes appearing in the n groups of order dish sets is m = { m = }1,m2,...,miAnd transmitting the acquired data to the data management platform for the data calling unit to call to the support degree analysis unit.
Further, in the support degree analysis unit: calculating the minimum support of the dish according to the following formula:
The times of occurrence of different dishes in the n groups of order dish sets andin comparison, ifThe too few dish points are indicated, and the support degree is too low; if it isThe support degree of the dish is higher than the minimum support degree, the comparison result is transmitted to the recommended dish screening unit, the times of dishes ordered by member customers are different, the minimum support degree is calculated to compare the times of the dishes appearing in the order with the minimum support degree, the recommended dish screening unit is favorable for preliminarily screening the popular dishes, the average value of the times of the dishes is used as the minimum support degree, and the popular degree of the dishes is reflected accurately.
Further, the recommended dish screening unit screens out the dish recommended by the recommended dish screening unit according to the comparison result, wherein the support degree is greater than the minimum support degreeThe dish set A’={A1 ’,A2 ’,...,Aj ’The frequency set of the corresponding dishes in the n groups of order dish sets is m = { m = }1 ’,m2 ’,...,mj ’Where j denotes that the support degree is larger than the minimum support degreeTotal number of dishes j<i, randomly combining j dishes in pairs, adding the occurrence times of a group of dishes, and sharingEach combination, the total occurrence frequency of all combined dishes and the sum of the occurrence frequency of all combined dishes are mGroup of={mGroup 1,mGroup 2,...,mGroup jTransmitting the combined dish information to the support degree analysis unit, and calculating the minimum support degree of the combined dish according to the following formula:
The occurrence frequency of the combined dish is compared withComparing, screening out the occurrence frequency greater than the minimum support degree by using the recommended dish screening unitThe combined dishes are arranged from large to small according to the support degree, the combined dish information is sent to the client side to be recommended to the non-member customers, the minimum support degree of the combined dishes is calculated to secondarily screen popular combined dishes through the recommended dish screening unit, the combined dishes are recommended to the non-member customers instead of single dishes, the experience of the customers is improved, and the sales volume of the dishes is increased.
Further, the sales amount statistic unit collects the sales amountCollecting monthly sales data of all dishes in the restaurant in the last year, transmitting the sales data to the data management platform, and screening out the monthly sales set with the highest sales in the year of all dishes as W = { W = (the average sales per month) by using the data management platform1,W2,...,WiThe sales amount of each month in one year of one dish is w = { w = }1,w2,...,w12The method comprises the following steps of (1) calculating the sales weight Q of each month of the dishes according to the following formula:
the calculation mode of the monthly sales weight of the other i-1 dishes is the same as the formula, the sales weight data is transmitted to the correction similarity analysis unit through the data retrieval unit, the dishes interested by the customers can change under the influence of time and seasons, the ratio of the sales of each month in one year of a dish to the sales of the month with the highest sales volume in one year is calculated to confirm the time period with better sales volume in one year of the dish, and the sales weight is used as the sales weight, so that the welcome condition and time of the dishes ordered by the customers can be accurately reflected.
Furthermore, the consumption record acquisition unit acquires the collection of the single time points of each month of one dish in one year of one member customer as q = { q = }1,q2,...,q12Randomly collecting the single number set of the dishes of each month of another member customer in one year to be q = { p1,p2,...,p12The single time number set of every month of another dish on the member customer order is q’={q1 ’,q2 ’,...,q12 ’Randomly collecting the single time number set of each month of another dish on another member customer order as p’={p1 ’,p2 ’,...,p12 ’Establishing a two-dimensional space, and combining the points corresponding to two dishes of the same customer once to form a vector coordinate set (q, q)’)={(q1,q1 ’),(q2,q2 ’),...,(q12,q12 ’) }, and (p, p)’)={(p1,p1 ’),(p2,p2 ’),...,(p12,p12 ’) Are corresponding to vectors of respectivelyAndand calculating the correction similarity F of the click lists among different users according to the following formula:
wherein,the method comprises the steps of representing an included angle of correction similarity, transmitting obtained correction similarity data to a recommended dish screening unit, enabling a traditional similarity algorithm not to reflect interest change of member customers to dishes along with seasonal change, adding sales weight data on the premise of the traditional similarity algorithm to fully consider seasonal change of popularity of dishes, enabling calculation of the correction similarity to solve the defect that the traditional similarity algorithm cannot reflect interest change of the member customers, enabling the recommended dish screening unit to screen proper dishes for the member customers according to the correction similarity, improving flow of the member customers, improving experience of the member customers and further improving sales volume of the dishes.
Further, after receiving the corrected similarity data, the recommended dish screening unit sets the lowest similarity K, compares the corrected similarity F with the corrected similarity K, and if F is the corrected similarity F, compares the corrected similarity F with the corrected similarity K<K, the difference of the selected dishes of the customer is very large; if FK, showing that the difference of the selected dishes of the customers is very small, and screening out FAnd arranging the orders of the K customers according to the descending order, recommending dishes on the corresponding orders mutually, and sending the recommended dish information to the client side for recommending to the member customers.
Further, the dish information recommended for the non-member customers is transmitted to the electronic menu design unit through the recommended dish screening unit, and the electronic menu design unit is used for designing menus for the non-member customers: the function of recommending dishes is applied to the link that before the order of the non-member customer is selected and completed and the order is about to be placed, the non-member customer selects dishes in the order list, corresponding text prompt is carried out in an interface, and if the non-member customer is interested, the information of the recommended dishes is browsed.
Further, the dish information recommended to the member customers is transmitted to the electronic menu design unit through the recommended dish screening unit, and the electronic menu design unit is used for designing menus for the member customers: before the recommending function is used, a member customer firstly logs in through a login interface, a member recommending module is displayed after logging in, the login interface is popped up, and the member customer inputs an account and a password and can browse dish information recommended by the system after verification is passed.
Furthermore, different menu pages designed for member customers and non-member customers by the electronic menu design unit are transmitted to the client, customers can select to browse different menu pages according to different identities to order, and experience and satisfaction of the customers in ordering are improved by designing different electronic menus according to different customers.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention collects n groups of order dish sets of member customers through the consumption record collection unit, counts the times of different dishes appearing in the n groups of order dish sets, and analyzes and calculates the dishes through the support degree analysis unitMinimum support ofThe frequency and the frequency of different dishes appearing in the n groups of order dish setsComparing, screening out the support degree larger than the minimum support degree by the recommended dish screening unitThe selected dishes are randomly combined pairwise, the times of the appearance of a group of dishes are added to obtain a total set of the times of the appearance of all the combined dishes, and the times of the appearance larger than the minimum support degree are selected again according to the comparison with the minimum support degreeThe combined dishes are recommended to the non-member customers from large to small according to the support degree, the dishes are recommended to the non-member customers according to the dining information of the members, and the conditions that the non-member customers do not have consumption records and cannot find bases for recommendation are considered, so that a most benign and optimal recommendation mode is provided for the non-member customers, the catering enterprise is helped to improve the dish ordering efficiency, and the experience of the non-member customers is improved;
2. the invention collects the monthly sales data of all dishes in the restaurant in the last year through the sales statistics unit, screens out the monthly sales of the highest sales volume in the year of all dishes and the monthly sales of the year of the dishes, calculates the sales weight of each month of the dishes, analyzes the similarity of ordering lists of different member customers by using the correction similarity analysis unit, obtains the correction similarity of the ordering lists of the member customers by combining the sales weights, carries out mutual recommendation on the dishes ordered by the member customers with high correction similarity, recommends the corresponding dish information to the member customers, introduces the sales weight into the traditional similarity calculation method, the influence of time factors on dish sales is fully considered, the defect that the traditional similarity algorithm cannot reflect the interest change of member customers is overcome, the flow of the member customers is improved, the experience of the member customers is improved, and the dish sales volume is further improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a block diagram of a food and beverage information recommendation system based on data analysis according to the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Referring to fig. 1, the present invention provides a technical solution: the catering information recommendation system based on data analysis is characterized in that: the method comprises the following steps: the system comprises a consumption record acquisition unit, a personal information acquisition unit, a sales statistic unit, a data management platform, a data calling unit, a customer classification unit, a support degree analysis unit, a correction similarity analysis unit, a recommended dish screening unit, an electronic menu design unit and a client;
the output ends of the consumption record acquisition unit, the personal information acquisition unit and the sales statistic unit are connected with the input end of the data management platform, the output end of the data management platform is connected with the input end of the data calling unit, the output end of the data calling unit is connected with the input end of the client classification unit, the output end of the client classification unit is connected with the input ends of the support analysis unit and the correction similarity analysis unit, the output ends of the support analysis unit and the correction similarity analysis unit are connected with the input end of the recommended dish screening unit, the output end of the recommended dish screening unit is connected with the input ends of the electronic dish spectrum design unit and the support analysis unit, and the output end of the electronic dish spectrum screening unit is connected with the input end of the client;
the consumption record acquisition unit acquires order records of restaurant members and inputs the order records into the data management platform, the personal information acquisition unit acquires personal information of different customers and inputs the personal information into the data management platform, the data calling unit calls the personal information and the order record data in the data management platform to the customer classification unit, and the customer classification unit classifies the customers into two batches by analyzing the personal information and the order record data of the customers: the support degree analysis unit analyzes and confirms the support degree of dishes according to the order details in the called member order record, transmits the support degree data to the recommended dish screening unit, and the recommended dish screening unit recommends the screened dish combination for the non-member customers according to the support degree data;
the sales amount counting unit transmits dish sales data of each month in the last year to the data management platform, the data management platform counts sales weight data, the correction similarity analysis unit analyzes the similarity of the dishes in combination with the order number and the sales weight of each dish, the data calling unit calls the sales weight data in the data management platform and transmits the correction similarity data to the recommended dish screening unit, and the recommended dish screening unit recommends screened dishes for member customers according to the similarity data.
The consumption record acquisition unit acquires n groups of order dish sets of member customers, and the different dish sets in the dish sets are A = { A = (A) }1,A2,...AiAnd f, wherein i represents the total number of different dishes, and the number of times of occurrence of the corresponding dishes in the n groups of order dish sets is counted to be m = { m = }1,m2,...,miAnd transmitting the acquired data to a data management platform for the data calling unit to call to the support degree analysis unit.
In the support degree analysis unit: calculating the minimum support of the dish according to the following formula:
The times of occurrence of different dishes in the n groups of order dish sets andin comparison, ifThe too few dish points are indicated, and the support degree is too low; if it isThe support degree of the dishes is higher than the minimum support degree, the comparison result is transmitted to the recommended dish screening unit, the times of dishes ordered by member customers are different, the minimum support degree is calculated to compare the times of the dishes appearing in the order with the minimum support degree, the recommended dish screening unit can conveniently and primarily screen popular dishes, the average value of the times of the dishes is used as the minimum support degree, and the popularity of the dishes can be accurately reflected.
The recommended dish screening unit screens out the support degree larger than the minimum support degree according to the comparison resultThe dish set A’={A1 ’,A2 ’,...,Aj ’The frequency set of the corresponding dishes in the n groups of order dish sets is m = { m = }1 ’,m2 ’,...,mj ’Where j denotes that the support degree is larger than the minimum support degreeTotal number of dishes j<i, randomly combining j dishes in pairs, adding the occurrence times of a group of dishes, and sharingEach combination, the total occurrence frequency of all combined dishes and the sum of the occurrence frequency of all combined dishes are mGroup of={mGroup 1,mGroup 2,...,mGroup jTransmitting the combined dish information to a support degree analysis unit, and calculating the minimum support degree of the combined dish according to the following formula:
The occurrence frequency of the combined dish is compared withComparing, screening out the appearance times larger than the minimum support degree by using the recommended dish screening unitThe combined dishes are arranged from large to small according to the support degree, the combined dish information is sent to the client side to be recommended to the non-member customers, the minimum support degree of the combined dishes is calculated to secondarily screen popular combined dishes through the recommended dish screening unit, the combined dishes are recommended to the non-member customers instead of single dishes, the experience of the customers can be improved, and the sales volume of the dishes is further improved.
The sales statistics unit is used for collecting monthly sales data of all dishes in the restaurant in the last year, the sales data are transmitted to the data management platform, and the data management platform is used for screening the sales set of the highest sales month in the last year of all the dishes as W = { W = }1,W2,...,WiThe sales amount of each month in one year of one dish is w = { w = }1,w2,...,w12The method comprises the following steps of (1) calculating the sales weight Q of each month of the dishes according to the following formula:
the calculation mode of the monthly sales weight of the other i-1 dishes is the same as the formula, the sales weight data is transmitted to the correction similarity analysis unit through the data retrieval unit, the dishes interested by customers can change under the influence of time and seasons, and the calculation of the ratio of the sales of each month in one year of a dish to the sales of the month with the highest sales in one year is used for confirming the time period with better sales in one year of the dish and is used as the sales weight so as to more accurately reflect the welcome condition and time of the dish ordered by the customers.
The consumption record acquisition unit acquires the point single time number set of one dish per month in one year of one member customer as q = { q }1,q2,...,q12Randomly collecting the single number set of the dishes of each month of another member customer in one year to be q = { p1,p2,...,p12The single time number set of every month of another dish on the member customer order is q’={q1 ’,q2 ’,...,q12 ’Randomly collecting the single time number set of each month of another dish on another member customer order as p’={p1 ’,p2 ’,...,p12 ’Establishing a two-dimensional space, and combining the points corresponding to two dishes of the same customer once to form a vector coordinate set (q, q)’)={(q1,q1 ’),(q2,q2 ’),...,(q12,q12 ’) }, and (p, p)’)={(p1,p1 ’),(p2,p2 ’),...,(p12,p12 ’) Are corresponding to vectors of respectivelyAndand calculating the correction similarity F of the click lists among different users according to the following formula:
wherein,the method comprises the steps of representing an included angle of correction similarity, transmitting obtained correction similarity data to a recommended dish screening unit, enabling a traditional similarity algorithm not to reflect interest change of member customers to dishes along with seasonal change, adding sales weight data on the premise of the traditional similarity algorithm to fully consider seasonal change of popularity of dishes, enabling calculation of the correction similarity to solve the defect that the traditional similarity algorithm cannot reflect interest change of the member customers, enabling the recommended dish screening unit to screen proper dishes for the member customers according to the correction similarity, improving flow of the member customers, improving experience of the member customers and further improving sales of the dishes.
After the recommended dish screening unit receives the corrected similarity data, the lowest similarity K is set, the corrected similarities F and K are compared, and if F is the corrected similarity F, the corrected similarity K is compared with K<K, the difference of the selected dishes of the customer is very large; if FK, showing that the difference of the selected dishes of the customers is very small, and screening out FAnd arranging the orders of the K customers according to the descending order, recommending dishes on the corresponding orders mutually, and sending the recommended dish information to the client side for recommending to the member customers.
The method comprises the following steps of transmitting dish information recommended for non-member customers to an electronic menu design unit through a recommended dish screening unit, and designing menus for the non-member customers by using the electronic menu design unit: the function of recommending dishes is applied to the link that before the order of the non-member customer is selected and completed and the order is about to be placed, the non-member customer selects dishes in the order list, corresponding text prompt is carried out in an interface, and if the non-member customer is interested, the information of the recommended dishes is browsed.
The method comprises the following steps of transmitting dish information recommended for member customers to an electronic menu design unit through a recommended dish screening unit, and designing menus for the member customers by using the electronic menu design unit: before the recommending function is used, a member customer firstly logs in through a login interface, a member recommending module is displayed after logging in, the login interface is popped up, and the member customer inputs an account and a password and can browse dish information recommended by the system after verification is passed.
Different menu pages designed for member customers and non-member customers by the electronic menu design unit are transmitted to the client, customers can select to browse different menu pages according to different identities to order, and experience and satisfaction of the customers in ordering can be improved by designing different electronic menus according to different customers.
The first embodiment is as follows: collecting 5 groups of order dish sets of member customers, wherein the different dish sets in the dish sets are A = { A = }1,A2,A3,A4,A5The frequency set of the corresponding dishes in the 5 groups of order dish sets is m = {6, 2, 10, 5, 1}, and the frequency set is according to a formulaCalculating the minimum support of dishes=4.8, the recommended dish screening unit screens out that the support degree is larger than the minimum support degree according to the comparison resultThe dish is A1、A3And A4Combining 3 dishes randomly in pairs, adding the times of occurrence of a group of dishes to obtain 3 combinations, and combining the times of occurrence of all the combined dishes into mGroup of= 16, 11, 15, according to formulaCalculating the minimum support degree of the combined dishes=14, number of occurrences of combined dish andcomparing, screening out the occurrence frequency greater than the minimum support degreeThe combined dish A1And A3、A3And A4The combined dish A1And A3Preferentially to non-member customers, and secondly A3And A4。
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The catering information recommendation system based on data analysis is characterized in that: the method comprises the following steps: the system comprises a consumption record acquisition unit, a personal information acquisition unit, a sales statistic unit, a data management platform, a data calling unit, a customer classification unit, a support degree analysis unit, a correction similarity analysis unit, a recommended dish screening unit, an electronic menu design unit and a client;
the output ends of the consumption record acquisition unit, the personal information acquisition unit and the sales statistic unit are connected with the input end of the data management platform, the output end of the data management platform is connected with the input end of the data retrieval unit, the output end of the data retrieval unit is connected with the input end of the customer classification unit, the output end of the customer classification unit is connected with the input ends of the support degree analysis unit and the correction similarity analysis unit, the output ends of the support degree analysis unit and the correction similarity analysis unit are connected with the input end of the recommended dish screening unit, the output end of the recommended dish screening unit is connected with the input ends of the electronic dish spectrum design unit and the support degree analysis unit, and the output end of the electronic dish spectrum screening unit is connected with the input end of the client;
the consumption record acquisition unit acquires order records of restaurant members and inputs the order records into the data management platform, the personal information acquisition unit acquires personal information of different customers and inputs the personal information into the data management platform, the data calling unit calls the personal information and the order record data in the data management platform to the customer classification unit, and the customer classification unit classifies the customers into two batches by analyzing the personal information and the order record data of the customers: the support degree analysis unit analyzes and confirms the support degree of dishes according to the order details in the called member order record, and transmits the support degree data to the recommended dish screening unit, and the recommended dish screening unit recommends the screened dish combination for the non-member customers according to the support degree data;
sales statistics unit reaches the dish sales data transmission of every month in nearly one year data management platform, data management platform statistics sales weight data, through revising similarity analysis unit and combining the order quantity and the sales weight analysis of every dish its similarity, through data calling unit calls sales weight data in the data management platform will revise similarity data transmission to in recommending the dish screening unit, recommend the dish screening unit and recommend the dish of sieving for the member customer according to similarity data.
2. The catering information recommendation system based on data analysis as claimed in claim 1, wherein: the consumption record acquisition unit acquires n groups of order dish sets of member customers and different dishes in the dish setsThe product set is A = { A = { [ A ]1,A2,...AiAnd f, wherein i represents the total number of different dishes, and the number of times of occurrence of the corresponding dishes in the n groups of order dish sets is counted to be m = { m = }1,m2,...,miAnd transmitting the acquired data to the data management platform for the data calling unit to call to the support degree analysis unit.
3. The catering information recommendation system based on data analysis as claimed in claim 2, wherein: in the support degree analysis unit: calculating the minimum support of the dish according to the following formula:
The times of occurrence of different dishes in the n groups of order dish sets andin comparison, ifThe too few dish points are indicated, and the support degree is too low; if it isAnd the support degree of the dish is higher than the minimum support degree, and the comparison result is transmitted to the recommended dish screening unit.
4. The catering information recommendation system based on data analysis as claimed in claim 3, wherein: the recommended dish screening unit screens out the support degree larger than the minimum support degree according to the comparison resultThe dish set A’={A1 ’,A2 ’,...,Aj ’The frequency set of the corresponding dishes in the n groups of order dish sets is m = { m = }1 ’,m2 ’,...,mj ’Where j denotes that the support degree is larger than the minimum support degreeTotal number of dishes j<i, randomly combining j dishes in pairs, adding the occurrence times of a group of dishes, and sharingEach combination, the total occurrence frequency of all combined dishes and the sum of the occurrence frequency of all combined dishes are mGroup of={mGroup 1,mGroup 2,...,mGroup jTransmitting the combined dish information to the support degree analysis unit, and calculating the minimum support degree of the combined dish according to the following formula:
The occurrence frequency of the combined dish is compared withComparing, screening out the occurrence frequency greater than the minimum support degree by using the recommended dish screening unitThe combined dishes are arranged from large to small according to the support degree, and the combined dish information is sent to the client side and recommended to the non-member customers.
5. The catering information recommendation system based on data analysis as claimed in claim 1, wherein: the sales statistics unit is used for collecting monthly sales data of all dishes in the restaurant in the last year, the sales data are transmitted to the data management platform, and the data management platform is used for screening the sales set of the month with the highest sales in the last year of all the dishes as W = { W =1,W2,...,WiThe sales amount of each month in one year of one dish is w = { w = }1,w2,...,w12The method comprises the following steps of (1) calculating the sales weight Q of each month of the dishes according to the following formula:
the calculation mode of the monthly sales weight of the other i-1 dishes is the same as that of the formula, and the sales weight data are transmitted to the correction similarity analysis unit through the data retrieval unit.
6. The catering information recommendation system based on data analysis as claimed in claim 5, wherein: the consumption record acquisition unit acquires the point single time number set of one dish per month in one year of one member customer as q = { q }1,q2,...,q12Randomly collecting the single number set of the dishes of each month of another member customer in one year to be q = { p1,p2,...,p12The single time number set of every month of another dish on the member customer order is q’={q1 ’,q2 ’,...,q12 ’Randomly collecting the single time number set of each month of another dish on another member customer order as p’={p1 ’,p2 ’,...,p12 ’Establishing a two-dimensional space, and combining the points corresponding to two dishes of the same customer once to form a vector coordinate set (q, q)’)={(q1,q1 ’),(q2,q2 ’),...,(q12,q12 ’) }, and (p, p)’)={(p1,p1 ’),(p2,p2 ’),...,(p12,p12 ’) Are corresponding to vectors of respectivelyAndand calculating the correction similarity F of the click lists among different users according to the following formula:
7. The catering information recommendation system based on data analysis as claimed in claim 6, wherein: after the recommended dish screening unit receives the corrected similarity data, the lowest similarity K is set, the corrected similarities F and K are compared, and if F is found, the corrected similarities F and K are compared<K, the difference of the selected dishes of the customer is very large; if FK, showing that the difference of the selected dishes of the customers is very small, and screening out FK, arranging the orders of the customers in the descending order, and mutually arranging the dishes on the corresponding ordersAnd (5) recommending, and sending the information of the recommended dishes to the client to recommend to the member customer.
8. The catering information recommendation system based on data analysis as claimed in claim 4, wherein: dish information recommended for non-member customers is transmitted to the electronic menu design unit through the recommended dish screening unit, and a menu is designed for the non-member customers by the electronic menu design unit: the function of recommending dishes is applied to the link that before the order of the non-member customer is selected and completed and the order is about to be placed, the non-member customer selects dishes in the order list, corresponding text prompt is carried out in an interface, and if the non-member customer is interested, the information of the recommended dishes is browsed.
9. The catering information recommendation system based on data analysis as claimed in claim 7, wherein: dish information recommended for the member customers is transmitted to the electronic menu design unit through the recommended dish screening unit, and a menu is designed for the member customers by the electronic menu design unit: before the recommending function is used, a member customer firstly logs in through a login interface, a member recommending module is displayed after logging in, the login interface is popped up, and the member customer inputs an account and a password and can browse dish information recommended by the system after verification is passed.
10. The catering information recommendation system based on data analysis according to claim 8 or 9, wherein: and transmitting different menu pages designed for the member customers and the non-member customers by the electronic menu design unit to the client, wherein the customers can select to browse the different menu pages according to different identities to order.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110222719.XA CN112561669B (en) | 2021-03-01 | 2021-03-01 | Catering information recommendation system based on data analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110222719.XA CN112561669B (en) | 2021-03-01 | 2021-03-01 | Catering information recommendation system based on data analysis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112561669A true CN112561669A (en) | 2021-03-26 |
CN112561669B CN112561669B (en) | 2021-07-09 |
Family
ID=75034866
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110222719.XA Expired - Fee Related CN112561669B (en) | 2021-03-01 | 2021-03-01 | Catering information recommendation system based on data analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112561669B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113413610A (en) * | 2021-06-21 | 2021-09-21 | 网易(杭州)网络有限公司 | Game item recommendation method, equipment and computer-readable storage medium |
CN116308465A (en) * | 2023-05-15 | 2023-06-23 | 深圳易派支付科技有限公司 | Big data analysis system based on mobile payment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104021506A (en) * | 2014-06-24 | 2014-09-03 | 河海大学常州校区 | Intelligent restaurant ordering management system and intelligent restaurant ordering management method based on human face recognition technology |
CN104978697A (en) * | 2015-06-24 | 2015-10-14 | 西南石油大学 | Two-dimensional code-based cooperative intelligent ordering method and system |
CN106651524A (en) * | 2016-12-27 | 2017-05-10 | 杭州火小二科技有限公司 | Method for intelligently generating recommended menu |
-
2021
- 2021-03-01 CN CN202110222719.XA patent/CN112561669B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104021506A (en) * | 2014-06-24 | 2014-09-03 | 河海大学常州校区 | Intelligent restaurant ordering management system and intelligent restaurant ordering management method based on human face recognition technology |
CN104978697A (en) * | 2015-06-24 | 2015-10-14 | 西南石油大学 | Two-dimensional code-based cooperative intelligent ordering method and system |
CN106651524A (en) * | 2016-12-27 | 2017-05-10 | 杭州火小二科技有限公司 | Method for intelligently generating recommended menu |
Non-Patent Citations (1)
Title |
---|
张奥多 等: "基于关联规则的餐饮服务智能推荐系统究", 《广西科技大学学报》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113413610A (en) * | 2021-06-21 | 2021-09-21 | 网易(杭州)网络有限公司 | Game item recommendation method, equipment and computer-readable storage medium |
CN116308465A (en) * | 2023-05-15 | 2023-06-23 | 深圳易派支付科技有限公司 | Big data analysis system based on mobile payment |
CN116308465B (en) * | 2023-05-15 | 2023-09-01 | 深圳易派支付科技有限公司 | Big data analysis system based on mobile payment |
Also Published As
Publication number | Publication date |
---|---|
CN112561669B (en) | 2021-07-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9734258B2 (en) | Method and system of displaying cross-website information | |
WO2019148817A1 (en) | E-commerce commodity recommendation method and e-commerce platform server | |
CN101324948B (en) | A kind of method of information recommendation and device | |
CN104050187B (en) | Search result methods of exhibiting and system | |
CN112561669B (en) | Catering information recommendation system based on data analysis | |
CN107092647B (en) | Method and device for providing resource combination | |
CN103136683B (en) | Calculate method, device and product search method, the system of product reference price | |
CN107220852A (en) | Method, device and server for determining target recommended user | |
JP5831204B2 (en) | Information providing system, information providing method, and program | |
US9965526B1 (en) | Data mining for multiple item comparisons | |
CN110335123B (en) | Commodity recommendation method, system, computer readable medium and device based on social e-commerce platform | |
JP2019508756A (en) | Method and apparatus for selecting and recommending objects on an electronic delivery platform | |
CN107301592A (en) | The method and device excavated for commodity substitute | |
CN111899047A (en) | Resource recommendation method and device, computer equipment and computer-readable storage medium | |
CN110516163B (en) | Commodity ordering method and system based on user behavior data | |
WO2018213325A1 (en) | Distributed node cluster for establishing a digital touchpoint across multiple devices on a digital communications network | |
WO2016011406A1 (en) | Rating system and method | |
KR102442988B1 (en) | A taste network generation system based on user experience using CNN learning | |
CN111193598B (en) | Group chat session recommendation method and device | |
CN111125536A (en) | Information pushing method and device, computer equipment and storage medium | |
CN111784434A (en) | Dish information pushing method and device and electronic equipment | |
CN109840820A (en) | A kind of method and apparatus of determining user to object type preference | |
KR102619030B1 (en) | Server, system, method and program that provide matching service between apartment complexes and distributors | |
US8589244B2 (en) | Instant, accurate, and efficient product recommendations to client endpoint | |
Kumar et al. | Enhance the Quality of Recommendation System in E-Commerce Application |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210709 |