CN114398546A - Dish recommending method and device, storage medium and electronic device - Google Patents
Dish recommending method and device, storage medium and electronic device Download PDFInfo
- Publication number
- CN114398546A CN114398546A CN202210010248.0A CN202210010248A CN114398546A CN 114398546 A CN114398546 A CN 114398546A CN 202210010248 A CN202210010248 A CN 202210010248A CN 114398546 A CN114398546 A CN 114398546A
- Authority
- CN
- China
- Prior art keywords
- dish
- recommendation
- target
- order
- recommending
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 230000015654 memory Effects 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 description 9
- 235000012054 meals Nutrition 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 230000004931 aggregating effect Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000036528 appetite Effects 0.000 description 1
- 235000019789 appetite Nutrition 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 208000013409 limited attention Diseases 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- 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)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a dish recommending method and device, a storage medium and an electronic device. Wherein, the method comprises the following steps: acquiring a current delivery address of a target account and a first dish in a historical order from a target platform, wherein the historical order is an order of the target account on the target platform, and the target account is an account used on the target platform; obtaining a first recommendation result matched with the first dish and the current distribution address by using a knowledge graph, wherein the knowledge graph is used for representing the relation among the user, the merchant and the dish on the target platform; and recommending a second dish to the target account based on the first recommendation result. The method and the device solve the technical problem that dish recommendation in the related art is inaccurate.
Description
Technical Field
The application relates to the field of data recommendation, in particular to a dish recommendation method and device, a storage medium and an electronic device.
Background
The appearance and popularization of the internet bring great convenience while meeting the requirements of users, and meanwhile, the mass commodities and information also bring trouble to users with limited attention. An effective method for solving the information overload problem is recommendation technology, which can recommend the commodity or information which may be interested to the user according to the needs and interests of the user, and the recommendation technology has become one of the most concerned research problems in academia and industry.
When the online meal ordering platform faces a large number of users, how to accurately recommend interested merchants or dishes with good appetite at specific time and place is an important problem worth exploring for a long time, so that the user can conveniently solve the meal demand and improve the meal satisfaction of the user. Compared with common e-commerce recommendation, the take-out recommendation has the characteristics of multidimensional user attributes, short decision time of a user, periodicity of user interests and the like, and more challenges are brought to the technical research of the take-out recommendation, so that inaccurate recommendation is caused.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the application provides a dish recommending method and device, a storage medium and an electronic device, and aims to at least solve the technical problem of inaccurate dish recommendation in the related art.
According to an aspect of an embodiment of the present application, there is provided a dish recommendation method including: acquiring a current delivery address of a target account and a first dish in a historical order from a target platform, wherein the historical order is an order of the target account on the target platform, and the target account is an account used on the target platform; obtaining a first recommendation result matched with the first dish and the current distribution address by using a knowledge graph, wherein the knowledge graph is used for representing the relation among the user, the merchant and the dish on the target platform; and recommending a second dish to the target account based on the first recommendation result.
Optionally, before recommending the second dish to the target account based on the first recommendation result, the method further comprises: obtaining second recommendation results matched with the first dishes and the current distribution address by using n recommendation schemes, wherein each second recommendation result is obtained by using one of the n recommendation schemes, and n is a positive integer greater than 1; recommending a second dish to the target account based on the first recommendation result, wherein the recommending comprises: and recommending second dishes to the target account according to the first recommendation result and the n second recommendation results.
Optionally, recommending a second dish to the target account according to the first recommendation result and the n second recommendation results, including: acquiring a recommended dish in the first recommendation result and a first matching degree p0 between the recommended dish and the target account, and acquiring a recommended dish in the ith second recommendation result and a second matching degree pi between the recommended dish and the target account, wherein i is a positive integer with the value of 1-n; determining the final matching degree between the same recommended dish and the target account according to the first matching degree p0 of the same recommended dish, the second matching degree pi in the ith second recommended result, the weight k0 distributed to the first matching degree and the weight ki distributed to the second matching degree in the ith second recommended result
Recommending a second dish in all recommended dishes according to the final matching degree, wherein the final matching degree of the second dish is not lower than the final matching degree of the rest dishes in all recommended dishes.
Optionally, before obtaining the first recommendation result matching the first dish and the current delivery address by using the knowledge graph, the method further comprises the following steps: and establishing map nodes by taking the user, the merchant, the order and the dish as map node types, and establishing the relationship among the map nodes by taking the user order, the order dish, the order merchant and the dish of the merchant as map relationship types.
Optionally, obtaining a first recommendation result matching the first dish and the current distribution address by using a knowledge graph, including: searching a target node which is associated with the first dish and corresponds to the dish in a distribution range of the current distribution address in the knowledge graph; a first recommendation is determined based on the target node associated with the first dish.
Optionally, searching for a target node, which is associated with the first dish and corresponding to the dish located in the distribution range of the current distribution address, in the knowledge graph includes: searching a target node where a second order with the same dish is located through a first-degree relation between the first order and the first order where the first dish is located in the knowledge graph; searching a target node of a second merchant with the same dish in the knowledge graph according to the first-degree relation with the first merchant of the first dish; and searching a target node where a second user purchasing the same dish is located in the knowledge graph through a second-degree relation with a first user purchasing a first dish.
Optionally, determining the first recommendation result according to the target node associated with the first dish includes: and generating a first recommendation result according to the occurrence times of the recommended dishes on all the target nodes.
According to another aspect of the embodiments of the present application, there is also provided a dish recommending apparatus, including: the acquisition unit is used for acquiring a current delivery address of a target account and a first dish in a historical order from the target platform, wherein the historical order is an order of the target account on the target platform, and the target account is an account used on the target platform; the system comprises a searching unit, a first recommending unit and a second recommending unit, wherein the searching unit is used for obtaining a first recommending result matched with a first dish and a current distribution address by using a knowledge map, and the knowledge map is used for representing the relation among users, merchants and dishes on a target platform; and the recommending unit is used for recommending the second dish to the target account based on the first recommending result.
Optionally, the recommending unit is further configured to: before recommending second dishes to the target account based on the first recommendation result, obtaining second recommendation results matched with the first dishes and the current distribution address by using n recommendation schemes, wherein each second recommendation result is obtained by using one of the n recommendation schemes, and n is a positive integer greater than 1; and recommending second dishes to the target account according to the first recommendation result and the n second recommendation results.
Optionally, the recommending unit is further configured to: obtaining a push in a first recommendationRecommending dishes, a first matching degree p0 between the recommended dishes and the target account, and acquiring a second matching degree pi between the recommended dishes and the target account in the ith second recommendation result, wherein i is a positive integer with the value of 1-n; determining the final matching degree between the same recommended dish and the target account according to the first matching degree p0 of the same recommended dish, the second matching degree pi in the ith second recommended result, the weight k0 distributed to the first matching degree and the weight ki distributed to the second matching degree in the ith second recommended result
Recommending a second dish in all recommended dishes according to the final matching degree, wherein the final matching degree of the second dish is not lower than the final matching degree of the rest dishes in all recommended dishes.
Optionally, the lookup unit is further configured to: before a first recommendation result matched with the first dish and the current distribution address is obtained by using the knowledge graph, the knowledge graph is created according to the following modes: and establishing map nodes by taking the user, the merchant, the order and the dish as map node types, and establishing the relationship among the map nodes by taking the user order, the order dish, the order merchant and the dish of the merchant as map relationship types.
Optionally, the lookup unit is further configured to: searching a target node which is associated with the first dish and corresponds to the dish in a distribution range of the current distribution address in the knowledge graph; a first recommendation is determined based on the target node associated with the first dish.
Optionally, the lookup unit is further configured to: searching a target node where a second order with the same dish is located through a first-degree relation between the first order and the first order where the first dish is located in the knowledge graph; searching a target node of a second merchant with the same dish in the knowledge graph according to the first-degree relation with the first merchant of the first dish; and searching a target node where a second user purchasing the same dish is located in the knowledge graph through a second-degree relation with a first user purchasing a first dish.
Optionally, the lookup unit is further configured to: and generating a first recommendation result according to the occurrence times of the recommended dishes on all the target nodes.
According to another aspect of the embodiments of the present application, there is also provided a storage medium including a stored program which, when executed, performs the above-described method.
According to another aspect of the embodiments of the present application, there is also provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the above method through the computer program.
According to an aspect of the application, a computer program product or computer program is provided, comprising computer instructions, the computer instructions being stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the steps of any of the embodiments of the method described above.
In the recommendation algorithm of the embodiment of the application, a current delivery address of a target account and a first dish in a historical order are obtained from a target platform, the historical order is an order of the target account on the target platform, and the target account is an account used on the target platform; obtaining a first recommendation result matched with the first dish and the current distribution address by using a knowledge graph, wherein the knowledge graph is used for representing the relation among the user, the merchant and the dish on the target platform; and recommending a second dish to the target account based on the first recommendation result. According to the scheme, the knowledge graph is constructed based on the dish information, the business district information and data which can be acquired around the order information and other various channels, dish recommendation is enhanced based on the knowledge graph, and the technical problem that dish recommendation is inaccurate in the related technology can be solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a schematic diagram of a hardware environment of a dish recommendation method according to an embodiment of the present application;
FIG. 2 is a flow chart of an alternative dish recommendation method according to an embodiment of the present application;
FIG. 3 is a schematic illustration of alternative order data according to an embodiment of the present application;
FIG. 4 is a schematic diagram of alternative user data according to an embodiment of the present application;
FIG. 5 is a schematic diagram of alternative merchant data according to an embodiment of the present application;
FIG. 6 is a schematic illustration of alternative dish data according to an embodiment of the present application;
FIG. 7 is a schematic illustration of an alternative knowledge-graph according to embodiments of the present application;
FIG. 8 is a schematic illustration of an alternative dish recommendation in accordance with embodiments of the present application;
FIG. 9 is a schematic illustration of an alternative dish recommendation in accordance with embodiments of the present application;
FIG. 10 is a schematic illustration of an alternative dish recommendation in accordance with an embodiment of the present application;
FIG. 11 is a schematic view of an alternative dish recommendation device according to an embodiment of the present application; and the number of the first and second groups,
fig. 12 is a block diagram of a terminal according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the ordering platform, the following schemes can be adopted for recommendation: 1) constructing a click matrix of the dishes of the user through behavior data in the dish order, and then completing recommendation based on a collaborative filtering method; 2) performing characteristic engineering processing on the attribute of the dish, performing characteristic engineering processing on the user, combining click matrix data, and completing recommendation based on an FM algorithm; 3) the recommendation is done using a method of deep learning.
The method has the advantages that the methods can perform well under the characteristics of the data and the scenes which are suitable for the methods, and the methods perform not well under the specific scenes in other fields, wherein the main reasons are that the current data acquisition mode is more and more diversified, the relation between the data is more and more complex, and the learning of all the characteristics is difficult to complete through a single method and a single model.
According to an aspect of embodiments of the present application, there is provided a method embodiment of a method for recommending dishes. The background situation of the scheme is that dishes are recommended in the meal ordering platform, relevant multi-dimensional attributes in the dishes and order surrounding relations are fully applied, a knowledge graph is suitable for being constructed, and then the dishes are recommended through a recommendation algorithm based on knowledge graph enhancement and integration of various methods.
Alternatively, in the present embodiment, the dish recommending method may be applied to a hardware environment formed by the terminal 101 and the server 103 as shown in fig. 1. As shown in fig. 1, a server 103 is connected to a terminal 101 through a network, which may be used to provide services (such as takeout services, fresh services, etc.) for the terminal or a client installed on the terminal, and a database 105 may be provided on the server or separately from the server, and is used to provide data storage services for the server 103, where the network includes but is not limited to: the terminal 101 is not limited to a PC, a mobile phone, a tablet computer, and the like.
The dish recommending method according to the embodiment of the present application may be executed by the server 103, or may be executed by both the server 103 and the terminal 101. Fig. 2 is a flowchart of an alternative dish recommending method according to an embodiment of the present application, and as shown in fig. 2, the method may include the following steps:
step S202, a current delivery address of a target account and a first dish in a historical order are obtained from the target platform, the historical order is an order of the target account on the target platform, and the target account is an account used on the target platform.
The target platform is a platform for the user to order dishes, such as a take-out platform, a fresh platform, a supermarket platform and the like, and the target account is any account of the user who receives the recommendation, such as a mobile phone number, a user ID and the like, on the platform.
And step S204, obtaining a first recommendation result matched with the first dish and the current distribution address by using a knowledge graph, wherein the knowledge graph is used for representing the relation among the user, the merchant and the dish on the target platform.
Step S2042, creating a knowledge graph as follows:
and establishing map nodes by taking the user, the merchant, the order and the dish as map node types, and establishing the relationship among the map nodes by taking the user order, the order dish, the order merchant and the dish of the merchant as map relationship types.
Step S2044, searching a target node which is associated with the first dish and corresponds to the dish and is located in the distribution range of the current distribution address in the knowledge graph, and determining a first recommendation result according to the target node associated with the first dish.
Optionally, when a target node which is associated with the first dish and corresponds to the dish within the distribution range of the current distribution address is searched in the knowledge graph, a target node where a second order with the same dish is located is searched in the knowledge graph through a first-degree relationship with a first order where the first dish is located; searching a target node of a second merchant with the same dish in the knowledge graph according to the first-degree relation with the first merchant of the first dish; and searching a target node where a second user purchasing the same dish is located in the knowledge graph through a second-degree relation with a first user purchasing a first dish.
Optionally, when the first recommendation result is determined according to the target node associated with the first dish, the first recommendation result is generated according to the number of occurrences of the recommended dish on all target nodes, for example, the first recommendation result includes a plurality of dishes and the number of occurrences of each dish (the number of occurrences here is equivalent to the matching degree, and the number of occurrences may also be normalized to be the matching degree).
Step S2046, using n recommendation schemes, obtaining second recommendation results matched with the first dishes and the current distribution address, wherein each second recommendation result is obtained by using one of the n recommendation schemes, and n is a positive integer greater than 1.
For example, the collaborative filtering and the FM algorithm are used to respectively perform an algorithm of collaborative filtering on log data of dishes clicked by the user to mine recommended dishes and matching degrees obtained based on the collaborative filtering of the user.
And step S206, recommending a second dish to the target account based on the first recommendation result.
Optionally, the second dishes may be recommended to the target account according to the first recommendation result and the n second recommendation results as follows:
1) acquiring a recommended dish in the first recommendation result and a first matching degree p0 between the recommended dish and the target account, and acquiring a recommended dish in the ith second recommendation result and a second matching degree pi between the recommended dish and the target account, wherein i is a positive integer with the value from 1 to n;
2) determining the final matching degree between the same recommended dish and the target account according to the first matching degree p0 of the same recommended dish, the second matching degree pi in the ith second recommended result, the weight k0 distributed to the first matching degree and the weight ki distributed to the second matching degree in the ith second recommended result
3) Recommending a second dish in all recommended dishes according to the final matching degree, wherein the final matching degree of the second dish is not lower than the final matching degree of the rest dishes in all recommended dishes.
Through the steps, the current delivery address of the target account and a first dish in a historical order are obtained from the target platform, the historical order is an order of the target account on the target platform, and the target account is an account used on the target platform; obtaining a first recommendation result matched with the first dish and the current distribution address by using a knowledge graph, wherein the knowledge graph is used for representing the relation among the user, the merchant and the dish on the target platform; and recommending a second dish to the target account based on the first recommendation result. According to the scheme, the knowledge graph is constructed based on the dish information, the business district information and data which can be acquired around the order information and other various channels, dish recommendation is enhanced based on the knowledge graph, and the technical problem that dish recommendation is inaccurate in the related technology can be solved.
In the dish recommendation of the scheme, dish recommendation can be effectively enhanced by designing a recommendation overall flow architecture and integrating by means of various methods and by using a knowledge map enhancement mode. The key point of the scheme is that a knowledge map is constructed for data provided in an online meal ordering system, then the recommendation process is enhanced by a knowledge map-based method, a framework integrating various recommendation algorithms and business rules is integrally used, and dish click rate indexes are improved in practical application. As an alternative example, the following detailed description is provided to further describe the technical solution of the present application in conjunction with the following specific embodiments:
And 2, constructing a knowledge graph.
The above data was constructed into atlas data, as shown in fig. 7, surrounding: the user, the merchant, the order and the dish are used as the node types of the map; and taking the user order, the order dishes, the order merchant and the merchant dishes as the map relation types. The specific construction is shown in the following figure.
And step 3, recommending dishes. As shown in fig. 8, the present solution completes dish recalls based on geographical locations, then integrates based on multiple recommendation methods, completes scoring operations on recalled dishes, and completes TopN filtering by comparing scores.
And 3.1, recalling the dish to be recommended.
The ordering requirement has an important recall characteristic, namely that the recommendation is completed based on the geographic position, the selection of the merchant is performed based on the geographic position range, and then the recall of the dishes in the merchant is completed based on the recalled merchant, as shown in fig. 9, the dish of the merchant within 5 kilometers is recalled by default.
And 3.2, sorting dishes.
According to the first scheme, on the basis of statistical rules, takeaway recommendations used in an online ordering system have the characteristics of multidimensional user attributes, short user decision time, periodicity of user interests and the like, so statistics is firstly carried out on the basis of some basic business rules in processing, and recalled data are sequenced through statistical indexes.
And secondly, completing recommendation based on a traditional recommendation algorithm, as shown in fig. 10, based on the traditional recommendation algorithm, the collaborative filtering and the FM algorithm are used in the scheme to respectively conduct a collaborative filtering algorithm on log data of the dishes clicked by the user to mine the recommended dishes obtained based on the collaborative filtering of the user, and the FM algorithm is used to learn the user attributes and browsing records of the user when the user places an order to obtain the recommended dishes.
And a third scheme, based on a knowledge graph enhanced recommendation algorithm, based on knowledge graph enhanced recommendation, by constructing knowledge graphs of dishes, orders, merchants and users, and based on the knowledge graphs, enhancing a recommendation result, specifically using the following steps:
1) finding a specific dish;
2) the same dish is found by the first degree relationship with the order (order 1: a, b, c; order 2: a, e, c);
3) aggregating the times of dishes with the same order (dish a with the order twice [ order 1 and order 2], and b with the order once), and then sequencing in a reverse order based on the times of dishes with the same order;
4) finding the same dish through the first-degree relation with the merchant (the same order);
5) aggregating the times of dishes of the same merchant (the same order);
6) finding the same dish (the same order) through the second degree relation with the user;
7) aggregating the times of dishes of the same user (the same order);
8) integrating the candidate dishes and the aggregation number;
9) and combining all the aggregation numbers, and then carrying out reverse ordering to give a recommended result.
And 3.3, integrating the scoring results of all the plurality of recommended algorithms and reordering.
Through the steps, the recommendation scoring of the recalled dishes is realized based on three methods, integration is performed based on the recommendation scoring, the scheme uses a weighted average method to finish the final scoring of the dishes, and the final filtering of the dishes TopN is finished to serve as the final recommendation result.
The overall process recommendation provided by the scheme is used for recommending dishes of the online ordering system, the overall scheme fully focuses on the dishes, merchants and information in orders, and the relevance of various information is also considered by mainly using the characteristics of multi-aspect data and integrating a knowledge map; and on the other hand, the time-end distribution of the specific ordering of the user ordering period is counted and applied to rule-based scoring. The online meal ordering system integrally covers the characteristics provided by all online meal ordering systems, is good in performance in actual recommendation application, and has 11% effect improvement (dish click rate index).
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present application.
According to another aspect of the embodiment of the application, a dish recommending device for implementing the dish recommending method is further provided. Fig. 11 is a schematic view of an alternative dish recommending apparatus according to an embodiment of the present application, and as shown in fig. 11, the apparatus may include:
an obtaining unit 1101, configured to obtain, from a target platform, a current delivery address of a target account and a first dish in a historical order, where the historical order is an order of the target account on the target platform, and the target account is an account used on the target platform;
a searching unit 1103, configured to obtain, by using a knowledge graph, a first recommendation result that matches the first dish and the current distribution address, where the knowledge graph is used to represent a relationship between a user, a merchant, and a dish on the target platform;
a recommending unit 1105, configured to recommend a second dish to the target account based on the first recommending result.
It should be noted here that the modules described above are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure of the above embodiments. It should be noted that the modules described above as a part of the apparatus may operate in a hardware environment as shown in fig. 1, and may be implemented by software or hardware.
Through the module, a current delivery address of a target account and a first dish in a historical order are obtained from a target platform, wherein the historical order is an order of the target account on the target platform, and the target account is an account used on the target platform; obtaining a first recommendation result matched with the first dish and the current distribution address by using a knowledge graph, wherein the knowledge graph is used for expressing the relation among the user, the merchant and the dish on the target platform; and recommending a second dish to the target account based on the first recommendation result. According to the scheme, the knowledge graph is constructed based on the dish information, the business district information and data which can be acquired around the order information and other various channels, dish recommendation is enhanced based on the knowledge graph, and the technical problem that dish recommendation is inaccurate in the related technology can be solved.
Optionally, the recommending unit is further configured to: before recommending second dishes to the target account based on the first recommendation result, obtaining second recommendation results matched with the first dishes and the current distribution address by using n recommendation schemes, wherein each second recommendation result is obtained by using one of the n recommendation schemes, and n is a positive integer greater than 1; and recommending the second dishes to the target account according to the first recommendation result and the n second recommendation results.
Optionally, the recommending unit is further configured to: acquiring a recommended dish in the first recommendation result, a first matching degree p0 between the recommended dish and the target account, and acquiring a second matching degree pi between the recommended dish in the ith second recommendation result and the target account, wherein i is a positive integer with a value of 1 to n; determining the final matching degree between the same recommended dish and the target account according to the first matching degree p0 of the same recommended dish, the second matching degree pi in the ith second recommended result, the weight k0 distributed to the first matching degree and the weight ki distributed to the second matching degree in the ith second recommended result
Recommending the second dish in all recommended dishes according to the final matching degree, wherein the final matching degree of the second dish is not lower than the final matching degree of the rest dishes in all recommended dishes.
Optionally, the lookup unit is further configured to: before a first recommendation result matched with the first dish and the current distribution address is obtained by using a knowledge graph, the knowledge graph is created according to the following mode: and establishing map nodes by taking the user, the merchant, the order and the dish as map node types, and establishing the relationship among the map nodes by taking the user order, the order dish, the order merchant and the dish of the merchant as map relationship types.
Optionally, the lookup unit is further configured to: searching a target node which is associated with the first dish and corresponds to the dish in a distribution range of the current distribution address in the knowledge graph; determining the first recommendation result according to the target node associated with the first dish.
Optionally, the lookup unit is further configured to: searching the target node where a second order with the same dish is located in the knowledge graph through the first-degree relation between the first order and the first order where the first dish is located; searching the target node where a second merchant with the same dish is located in the knowledge graph through the first-degree relation with a first merchant where the first dish is located; and searching the target node where a second user purchasing the same dish is located in the knowledge graph through a second-degree relation with a first user purchasing the first dish.
Optionally, the lookup unit is further configured to: and generating the first recommendation result according to the occurrence times of the recommended dishes on all the target nodes.
It should be noted here that the modules described above are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure of the above embodiments. It should be noted that the modules described above as a part of the apparatus may be operated in a hardware environment as shown in fig. 1, and may be implemented by software, or may be implemented by hardware, where the hardware environment includes a network environment.
According to another aspect of the embodiment of the application, a server or a terminal for implementing the dish recommending method is also provided.
Fig. 12 is a block diagram of a terminal according to an embodiment of the present application, and as shown in fig. 12, the terminal may include: one or more processors 1201 (only one of which is shown in fig. 12), a memory 1203, and a transmission 1205. as shown in fig. 12, the terminal may also include an input-output device 1207.
The memory 1203 may be used to store software programs and modules, such as program instructions/modules corresponding to the dish recommending method and apparatus in the embodiment of the present application, and the processor 1201 executes various functional applications and data processing by running the software programs and modules stored in the memory 1203, that is, implements the above dish recommending method. The memory 1203 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 1203 may further include memory located remotely from the processor 1201, which may be connected to the terminal through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The above-mentioned transmission means 1205 is used for receiving or sending data via a network, and may also be used for data transmission between the processor and the memory. Examples of the network may include a wired network and a wireless network. In one example, the transmission device 1205 includes a Network adapter (NIC) that can be connected to a router via a Network cable and other Network devices to communicate with the internet or a local area Network. In one example, the transmission device 1205 is a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.
Among them, the memory 1203 is specifically used for storing an application program.
The processor 1201 may invoke an application stored in the memory 1203 via the transmission 1205 to perform the following steps:
acquiring a current delivery address of a target account and a first dish in a historical order from a target platform, wherein the historical order is an order of the target account on the target platform, and the target account is an account used on the target platform;
obtaining a first recommendation result matched with the first dish and the current distribution address by using a knowledge graph, wherein the knowledge graph is used for expressing the relation among the user, the merchant and the dish on the target platform;
and recommending a second dish to the target account based on the first recommendation result.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment is not described herein again.
It can be understood by those skilled in the art that the structure shown in fig. 12 is only an illustration, and the terminal may be a terminal device such as a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, and a Mobile Internet Device (MID), a PAD, etc. Fig. 12 is a diagram illustrating a structure of the electronic device. For example, the terminal may also include more or fewer components (e.g., network interfaces, display devices, etc.) than shown in FIG. 12, or have a different configuration than shown in FIG. 12.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by a program instructing hardware associated with the terminal device, where the program may be stored in a computer-readable storage medium, and the storage medium may include: flash disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.
Embodiments of the present application also provide a storage medium. Alternatively, in this embodiment, the storage medium may be a program code for executing a method of recommending dishes.
Optionally, in this embodiment, the storage medium may be located on at least one of a plurality of network devices in a network shown in the above embodiment.
Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps:
acquiring a current delivery address of a target account and a first dish in a historical order from a target platform, wherein the historical order is an order of the target account on the target platform, and the target account is an account used on the target platform;
obtaining a first recommendation result matched with the first dish and the current distribution address by using a knowledge graph, wherein the knowledge graph is used for expressing the relation among the user, the merchant and the dish on the target platform;
and recommending a second dish to the target account based on the first recommendation result.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment is not described herein again.
Optionally, in this embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
The integrated unit in the above embodiments, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in the above computer-readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a storage medium, and including instructions for causing one or more computer devices (which may be personal computers, servers, network devices, or the like) to execute all or part of the steps of the method described in the embodiments of the present application.
In the above embodiments of the present application, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed client may be implemented in other manners. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.
Claims (10)
1. A method for recommending dishes, comprising:
acquiring a current delivery address of a target account and a first dish in a historical order from a target platform, wherein the historical order is an order of the target account on the target platform, and the target account is an account used on the target platform;
obtaining a first recommendation result matched with the first dish and the current distribution address by using a knowledge graph, wherein the knowledge graph is used for expressing the relation among the user, the merchant and the dish on the target platform;
and recommending a second dish to the target account based on the first recommendation result.
2. The method of claim 1,
before recommending a second dish to the target account based on the first recommendation result, the method further comprises: obtaining second recommendation results matched with the first dishes and the current distribution address by using n recommendation schemes, wherein each second recommendation result is obtained by using one of the n recommendation schemes, and n is a positive integer greater than 1;
recommending a second dish to the target account based on the first recommendation result, comprising: and recommending the second dishes to the target account according to the first recommendation result and the n second recommendation results.
3. The method of claim 2, wherein recommending the second dish to the target account according to the first recommendation and the n second recommendations comprises:
acquiring a recommended dish in the first recommendation result, a first matching degree p0 between the recommended dish and the target account, and acquiring a second matching degree pi between the recommended dish in the ith second recommendation result and the target account, wherein i is a positive integer with a value of 1 to n;
determining the final matching degree between the same recommended dish and the target account according to the first matching degree p0 of the same recommended dish, the second matching degree pi in the ith second recommended result, the weight k0 distributed to the first matching degree and the weight ki distributed to the second matching degree pi in the ith second recommended result
Recommending the second dish in all recommended dishes according to the final matching degree, wherein the final matching degree of the second dish is not lower than the final matching degree of the rest dishes in all recommended dishes.
4. The method of claim 1, wherein prior to using the knowledge-graph to arrive at the first recommendation that matches the first dish and the current distribution address, the method further comprises creating the knowledge-graph as follows:
and establishing map nodes by taking the user, the merchant, the order and the dish as map node types, and establishing the relationship among the map nodes by taking the user order, the order dish, the order merchant and the dish of the merchant as map relationship types.
5. The method of any of claims 1-4, wherein obtaining a first recommendation matching the first dish and the current delivery address using a knowledge-graph comprises:
searching a target node which is associated with the first dish and corresponds to the dish in a distribution range of the current distribution address in the knowledge graph;
determining the first recommendation result according to the target node associated with the first dish.
6. The method of claim 5, wherein searching the knowledge-graph for a target node associated with the first dish and corresponding to a dish within a delivery range of the current delivery address comprises:
searching the target node where a second order with the same dish is located in the knowledge graph through the first-degree relation between the first order and the first order where the first dish is located;
searching the target node where a second merchant with the same dish is located in the knowledge graph through the first-degree relation with a first merchant where the first dish is located;
and searching the target node where a second user purchasing the same dish is located in the knowledge graph through a second-degree relation with a first user purchasing the first dish.
7. The method of claim 5 or 6, wherein determining the first recommendation from the target node associated with the first dish comprises:
and generating the first recommendation result according to the occurrence times of the recommended dishes on all the target nodes.
8. A dish recommendation device, comprising:
the system comprises an acquisition unit, a storage unit and a processing unit, wherein the acquisition unit is used for acquiring a current delivery address of a target account and a first dish in a historical order from a target platform, the historical order is an order of the target account on the target platform, and the target account is an account used on the target platform;
the searching unit is used for obtaining a first recommendation result matched with the first dish and the current distribution address by using a knowledge graph, wherein the knowledge graph is used for representing the relation among the user, the merchant and the dish on the target platform;
and the recommending unit is used for recommending a second dish to the target account based on the first recommending result.
9. A storage medium, characterized in that the storage medium comprises a stored program, wherein the program when executed performs the method of any of the preceding claims 1 to 7.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the method of any of the preceding claims 1 to 7 by means of the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210010248.0A CN114398546A (en) | 2022-01-06 | 2022-01-06 | Dish recommending method and device, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210010248.0A CN114398546A (en) | 2022-01-06 | 2022-01-06 | Dish recommending method and device, storage medium and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114398546A true CN114398546A (en) | 2022-04-26 |
Family
ID=81229304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210010248.0A Pending CN114398546A (en) | 2022-01-06 | 2022-01-06 | Dish recommending method and device, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114398546A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115757816A (en) * | 2022-11-07 | 2023-03-07 | 北京交通大学 | Multi-source heterogeneous information channel coupling method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150169758A1 (en) * | 2013-12-17 | 2015-06-18 | Luigi ASSOM | Multi-partite graph database |
| CN110400193A (en) * | 2019-06-13 | 2019-11-01 | 拉扎斯网络科技（上海）有限公司 | Vegetable recommended method and device, electronic equipment and storage medium |
| CN110837552A (en) * | 2019-09-30 | 2020-02-25 | 口口相传(北京)网络技术有限公司 | Diet information recommendation method and device |
| CN112100513A (en) * | 2020-08-27 | 2020-12-18 | 北京明略昭辉科技有限公司 | Knowledge graph-based recommendation method, device, equipment and computer readable medium |
| US20220198300A1 (en) * | 2020-05-29 | 2022-06-23 | Boe Technology Group Co., Ltd. | Question recommendation method, device and system, electronic device, and readable storage medium |
-
2022
- 2022-01-06 CN CN202210010248.0A patent/CN114398546A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150169758A1 (en) * | 2013-12-17 | 2015-06-18 | Luigi ASSOM | Multi-partite graph database |
| CN110400193A (en) * | 2019-06-13 | 2019-11-01 | 拉扎斯网络科技（上海）有限公司 | Vegetable recommended method and device, electronic equipment and storage medium |
| CN110837552A (en) * | 2019-09-30 | 2020-02-25 | 口口相传(北京)网络技术有限公司 | Diet information recommendation method and device |
| US20220198300A1 (en) * | 2020-05-29 | 2022-06-23 | Boe Technology Group Co., Ltd. | Question recommendation method, device and system, electronic device, and readable storage medium |
| CN112100513A (en) * | 2020-08-27 | 2020-12-18 | 北京明略昭辉科技有限公司 | Knowledge graph-based recommendation method, device, equipment and computer readable medium |
Non-Patent Citations (1)
| Title |
|---|
| 乔秀珍;: "基于智能推荐的图书馆管理系统设计", 微型电脑应用, no. 12, 19 December 2018 (2018-12-19) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115757816A (en) * | 2022-11-07 | 2023-03-07 | 北京交通大学 | Multi-source heterogeneous information channel coupling method |
| CN115757816B (en) * | 2022-11-07 | 2023-12-08 | 北京交通大学 | Multi-source heterogeneous information channel coupling method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110162693B (en) | Information recommendation method and server | |
| CN101324948B (en) | A kind of method of information recommendation and device | |
| CN103106285B (en) | Recommendation algorithm based on information security professional social network platform | |
| CN108763314A (en) | A kind of interest recommends method, apparatus, server and storage medium | |
| CN109325182B (en) | Information pushing method and device based on session, computer equipment and storage medium | |
| KR102042047B1 (en) | System and method of marketing service using formal and informal big data | |
| CN103116639A (en) | Item recommendation method and system based on user-item bipartite model | |
| CN105159910A (en) | Information recommendation method and device | |
| CN105335409A (en) | Target user determination method and device and network server | |
| CN109241451B (en) | Content combination recommendation method and device and readable storage medium | |
| CN105677787B (en) | Information retrieval device and information search method | |
| Mashal et al. | Analysis of recommendation algorithms for Internet of Things | |
| CN110570279A (en) | Strategic recommendation method and device based on real-time user behavior | |
| CN113850649A (en) | Customized recommendation method and recommendation system based on multi-platform user data | |
| CN111611499A (en) | Collaborative filtering method, collaborative filtering device and collaborative filtering system | |
| CN112380299A (en) | Relational network construction method, device and storage medium | |
| CN114371946B (en) | Information push method and information push server based on cloud computing and big data | |
| CN114398546A (en) | Dish recommending method and device, storage medium and electronic device | |
| CN105426392A (en) | Collaborative filtering recommendation method and system | |
| CN113342994B (en) | Recommendation system based on non-sampling cooperative knowledge graph network | |
| CN108416645B (en) | Recommendation method, device, storage medium and equipment for user | |
| CN111652451B (en) | Social relationship obtaining method and device and storage medium | |
| CN111461826A (en) | Information pushing method and device, storage medium and electronic device | |
| CN112784025A (en) | Method and device for determining target event | |
| CN104504134A (en) | Promotion information attribute data acquiring method and device |
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 |