CN117453992A - Dish recommending method and device, medium and electronic equipment - Google Patents
Dish recommending method and device, medium and electronic equipment Download PDFInfo
- Publication number
- CN117453992A CN117453992A CN202311265317.3A CN202311265317A CN117453992A CN 117453992 A CN117453992 A CN 117453992A CN 202311265317 A CN202311265317 A CN 202311265317A CN 117453992 A CN117453992 A CN 117453992A
- Authority
- CN
- China
- Prior art keywords
- dish
- dishes
- information
- user
- preference
- 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 44
- 239000011159 matrix material Substances 0.000 claims abstract description 63
- 230000006399 behavior Effects 0.000 claims description 23
- 238000011156 evaluation Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 12
- 241000287828 Gallus gallus Species 0.000 description 11
- 238000010586 diagram Methods 0.000 description 5
- 230000005236 sound signal Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 235000015278 beef Nutrition 0.000 description 3
- 235000012054 meals Nutrition 0.000 description 3
- 235000019640 taste Nutrition 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 235000013527 bean curd Nutrition 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 235000011888 snacks Nutrition 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/12—Hotels or restaurants
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical 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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure relates to the technical field of dish recommendation, and relates to a dish recommendation method, a device, a medium and electronic equipment, comprising: acquiring identity information of a target user; determining whether preference information matched with the identity information exists in a database; if preference information matched with the identity information exists in the database, determining first recommended dish information according to the preference information and a pre-constructed dish similarity matrix; and displaying the first recommended dish information on a user page, so that the accuracy and reliability of dish recommendation are improved.
Description
Technical Field
The disclosure relates to the technical field of dish recommendation, in particular to a dish recommendation method, a device, a medium and electronic equipment.
Background
In the ordering process, the user often recommends dishes or new dishes with good sales to the user, and because of different tastes of each client, the user may not find favorite dishes on the dish recommending page, so that the recommending efficiency is low, or when the user orders dishes in a general menu, the user often has difficulty in selecting due to various dishes, and the user needs to check each category for one time to find favorite dishes for ordering, so that effective dish recommendation cannot be obtained.
Disclosure of Invention
In order to overcome the problems in the related art, the present disclosure provides a dish recommendation method, a device, a medium and an electronic apparatus.
According to a first aspect of embodiments of the present disclosure, there is provided a dish recommendation method, including:
acquiring identity information of a target user;
under the condition that preference information matched with the identity information exists in a database, determining first recommended dish information according to the preference information and a pre-constructed dish similarity matrix;
and displaying the first recommended menu information on a user page.
Optionally, the preference information includes dish evaluation information and user behavior information, and determining the first recommended dish information according to the preference information and a pre-constructed dish similarity matrix includes:
according to the dish evaluation information, determining a plurality of target recommended dishes by inquiring the dish similarity matrix;
according to the user behavior information and the dish similarity matrix, determining an interest value of the target user for each target recommended dish;
and arranging the target recommended dishes according to the interest values corresponding to the target recommended dishes from large to small, and determining the target recommended dishes corresponding to the interest values of the preset number as the first recommended dish information.
Optionally, the determining, according to the dish evaluation information, a plurality of target recommended dishes by querying the dish similarity matrix includes:
determining a plurality of historical preference dishes with scores greater than a preset score threshold according to the dish evaluation information;
inquiring a pre-constructed dish similarity matrix, and determining a plurality of similarity dishes corresponding to each history preference dish;
and removing repeated dishes in the similar dishes and the historical preference dishes, and determining a plurality of target recommended dishes.
Optionally, the determining, according to the user behavior information and the dish similarity matrix, the interest value of the target user for each target recommended dish includes:
according to the user behavior information, determining interest values of the target user on each historical preference dish;
and carrying out weighted summation on the similarity of each target recommended dish and each history preference dish and the interest value of each history preference dish of the target user, and determining the interest value of the target user on each target recommended dish.
Optionally, the dish similarity matrix is constructed by:
determining a preference co-occurrence matrix corresponding to each user according to preference information of each user in the database;
superposing preference co-occurrence matrixes corresponding to a plurality of users, and determining a dish co-occurrence matrix, wherein the dish co-occurrence matrix is used for representing the number of target users who prefer any two dishes at the same time;
for any two dishes, determining the similarity between the any two dishes according to the dish co-occurrence matrix and the target user quantity of the two dishes which are preferred in the database respectively;
normalizing the similarity between any two dishes according to preset parameters, and determining the target similarity between any two dishes;
and constructing the dish similarity matrix according to the target similarity between any two dishes.
Optionally, the method further comprises:
under the condition that preference information matched with the identity information exists in the database, inputting the preference information into a pre-trained dish recommendation model to obtain second recommended dish information, wherein the dish recommendation model is obtained by training according to sample preference information of other users with the same preference as the target user;
and displaying the second recommended dish information on the user page.
Optionally, the method further comprises:
and displaying preset special dishes and hot-sell products on the user page under the condition that preference information matched with the identity information does not exist in the database.
According to a second aspect of embodiments of the present disclosure, there is provided a dish recommendation device, including:
the acquisition module is configured to acquire the identity information of the target user;
the determining module is configured to determine first recommended dish information according to the preference information and a pre-constructed dish similarity matrix under the condition that preference information matched with the identity information does not exist in the database;
and the display module is configured to display the first recommended menu information on a user page.
According to a third aspect of embodiments of the present disclosure, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the steps of the method of the first aspect of the present disclosure.
According to a fourth aspect of embodiments of the present disclosure, there is provided an electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the method of the first aspect of the disclosure.
Through the technical scheme, the method has the following technical effects:
by recommending dishes similar to the preferred dishes of the user to the user, accuracy and reliability of dish recommendation are improved, the dishes recommended to the user are more personalized, the user can directly see the recommended dishes through the display page, and further the user can find the favorite dishes without browsing the whole menu.
Additional features and advantages of the present disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings are included to provide a further understanding of the disclosure, and are incorporated in and constitute a part of this specification, illustrate the disclosure and together with the description serve to explain, but do not limit the disclosure. In the drawings:
fig. 1 is a flowchart illustrating a dish recommendation method according to an exemplary embodiment.
FIG. 2 is a flowchart illustrating one construction of a dish similarity matrix, according to an example embodiment.
FIG. 3 is a block diagram illustrating a dish recommendation device, according to an example embodiment.
Fig. 4 is a block diagram of an electronic device, according to an example embodiment.
Fig. 5 is a block diagram of another electronic device, shown in accordance with an exemplary embodiment.
Detailed Description
Specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the disclosure, are not intended to limit the disclosure.
It should be noted that, all actions for acquiring signals, information or data in the present disclosure are performed under the condition of conforming to the corresponding data protection rule policy of the country of the location and obtaining the authorization given by the owner of the corresponding device.
Before introducing the dish recommendation method, device, medium and electronic equipment of the disclosure, an application scenario of the disclosure is first introduced.
In the process of ordering, the user often recommends dishes with good sales or new dishes to the user, and because of different tastes of each client, the user may not find favorite dishes on the dish recommending page, so that the recommending efficiency is low, or when the user orders dishes in a general menu, the user often can be difficult to select because of various dishes, and the existing solution is to display all dishes according to the dishes types in a classified manner, for example: snack, steamed dish, fried dish, vegetables and the like, and a user needs to check each classification for one time to find favorite dishes for ordering, so that effective dish recommendation cannot be obtained.
In view of this, in order to improve the efficiency and effectiveness of dish recommendation, the present disclosure provides a dish recommendation method, and fig. 1 is a flowchart of a dish recommendation method according to an exemplary embodiment, as shown in fig. 1, including the following steps.
In step S1, identity information of a target user is acquired.
In one embodiment, a user may use a mobile terminal to scan a two-dimensional code on a dining table to order, wherein the user is required to perform an authorized login ordering program after scanning the two-dimensional code, so as to determine identity information of the user.
In another embodiment, the user can log in the ordering website or applet of the restaurant online to conduct the selling order, and after the user logs in, the identity information of the user is determined.
By way of example, user a is a registered user using a dining hall application. Each time he logs in, the system records his user name or user ID (Identity Document, identification number). Meanwhile, if the a user is willing to share, other information of the a user, such as age, gender, geographic location, etc., may be obtained.
It should be noted that, after the user logs in, if the identity information of the user is not found in the database, the user is regarded as a new user, and the identity information of the user is registered in the database, where the identity information may be a mobile phone number, a user name or a user ID of the user.
In step S2, if there is preference information matching with the identity information in the database, determining first recommended dish information according to the preference information and a pre-constructed dish similarity matrix.
It is worth to say that, the database stores the identity information of the user authorized to log in the ordering program or the ordering website and the preference information associated with the identity information of the user, and in addition, the dish similarity matrix is used for representing the similarity relation between any two dishes.
In one embodiment, preference information matched with identity information of a target user in a database is obtained, a preferred dish of the target user is determined according to the preference information, a plurality of similar dishes corresponding to the preferred dish of the user are determined by querying a dish similarity matrix, and the plurality of similar dishes are determined as first recommended dish information.
In step S3, the first recommended menu information is displayed on the user page.
In one embodiment, first, in response to an authorized login operation of the A user to the restaurant ordering program, the identity information of the A user is obtained, and the system queries a background database to determine that preference information of the A user has been stored. Assuming that during the past several months, user a will get a "chicken in a box" every five night, it can be inferred that he may like spicy and like eating dishes for chicken. Then, it was determined that the A user may like to eat spicy chicken dishes. Therefore, dishes similar to the "chicken in palace" can be searched in the dish similarity matrix. If the dish similarity matrix shows that the spicy chicken and the chicken in the wok have high similarity, the spicy chicken can be used as a dish recommended to the user A. Finally, when the a user opens the application again and browses the menu, the "spicy chicken" dish will be displayed at the top of his recommendation list, possibly even with a prompt like "according to your history order, possibly like the dish". Thus, the user A can directly click the dish to order food without spending time browsing the whole menu.
Through the technical scheme, the method has the following technical effects:
by recommending dishes similar to the preferred dishes of the user to the user, accuracy and reliability of dish recommendation are improved, the dishes recommended to the user are more personalized, the user can directly see the recommended dishes through the display page, and further the user can find the favorite dishes without browsing the whole menu.
Optionally, the preference information includes dish evaluation information and user behavior information, and determining the first recommended dish information according to the preference information and a pre-constructed dish similarity matrix includes:
firstly, according to the dish evaluation information, determining a plurality of target recommended dishes by inquiring the dish similarity matrix.
Wherein the preference information of the user includes at least one of dish evaluation information, user behavior information, and history ordering information.
It is worth to say that, the dish evaluation information is used for representing the score of one or more dishes by the user, if the user does not score each dish of a meal individually, but scores a plurality of dishes uniformly, the uniform score is corrected according to a preset correction coefficient and then is used as the individual score of each dish, the score standard is 0 to 5, the higher the score, the user's evaluation, the user has ordered three dishes in the restaurant, the individual evaluation is not performed on each dish after the meal is completed, but the uniform score of all dishes is 4.5, and the individual score of each dish in the dish of the meal of the user is considered to be 4.
In one embodiment, according to the dish evaluation information, dishes that are purchased by the target user for the history and have a score of greater than or equal to 4 are determined as the user history preference dishes, similar dishes of each history preference dish are sequentially queried in the dish similarity matrix, and the similar dishes are determined as the target recommended dishes.
And then, according to the user behavior information and the dish similarity matrix, determining the interest value of the target user for each target recommended dish.
Wherein the user behavior information comprises the purchase times of the dish ordered by the user or the click times of the dish page, and it is easy to understand that the user behavior information can be used for representing the preference degree of the user on the purchased dish.
In one embodiment, user a purchases dish a 3 times and dish b 2 times, indicating that user a has a greater preference for dish a than dish b, and in another example, there is no ordering record for user a in the database, but there is user a clicking on the "chicken in palace" dish page 5 times on the ordering page, and determining that user a has a greater preference for chicken in palace than other non-clicked dishes.
In another embodiment, if the user behavior information indicates that the target user has preset behavior on the dish, for example, the number of repeated purchases of a certain dish is greater than a first preset number of times threshold, or the number of clicks on a certain dish page is greater than a second preset number of times threshold, the interest value of the dish is determined to be "1", otherwise, the interest value of the dish is determined to be "0".
In one embodiment, the dish similarity matrix may determine a plurality of target recommended dishes similar to the history preferred dishes, and then calculate the purchase times or click times of the user on each history preferred dish according to the user behavior information of the target user, further determine the interest value of the target user on each history preferred dish, and then perform weighted summation on the interest value of each history preferred dish and the similarity of the corresponding similar dishes, to determine the interest value of the target user on the history preferred dishes, wherein the more the user purchases or clicks times of the user on the history preferred dishes, the greater the interest value of the user on the similar dishes corresponding to the history preferred dishes.
And finally, arranging the target recommended dishes according to the interest values corresponding to the target recommended dishes from large to small, and determining the target recommended dishes corresponding to the interest values of the preset number as the first recommended dish information.
In an embodiment, the first 3 of the target recommended dishes are sent to the user as first recommended dish information, and the target recommended dishes are displayed on the user page from large to small according to the corresponding interest values, so that the user can see the dishes which are most interested in the first time, and further dish recommending efficiency is improved.
Optionally, the determining, according to the dish evaluation information, a plurality of target recommended dishes by querying the dish similarity matrix includes:
first, according to the dish evaluation information, a plurality of historical preference dishes with scores larger than a preset score threshold are determined.
In one embodiment, the score is 0 to 5, the higher the score, the better the score, and the preset score threshold is 3.5, which indicates that if the score for a dish is greater than 3.5, the dish is determined to be a historically preferred dish for the user.
And secondly, inquiring a pre-constructed dish similarity matrix, and determining a plurality of similarity dishes corresponding to each history preference dish.
For example, the history preference dishes of the user a are a dish and b dish, and the similarity dishes corresponding to the dish a are b dish, c dish and d dish, and the similarity dishes corresponding to the dish b are a dish, d dish and e dish, which are determined by querying the dish similarity matrix.
And thirdly, removing repeated dishes in the similar dishes and the historical preference dishes, and determining a plurality of target recommended dishes.
Continuing with the description with the above example, the a-and b-dishes of the A-preference and the repeatedly occurring dishes are removed, and the target recommended dishes are determined to be the c-dish, the d-dish, and the e-dish.
By the method, influence of different scores on judgment of the historical preferred dishes of the user is avoided, accuracy in positioning the dishes preferred by the user is further improved, and when the target recommended dishes are determined, favorite dishes and repeatedly occurring dishes of the user are removed, so that repeated recommendation to the user is avoided.
Optionally, the determining, according to the user behavior information and the dish similarity matrix, the interest value of the target user for each target recommended dish includes:
and according to the user behavior information, determining the interest value of the target user for each history preference dish.
In one embodiment, if the user behavior information shows that the target user has preset behaviors on the history preferred dishes, for example, the repeated purchasing frequency of a certain history preferred dish is greater than a first preset frequency threshold value, or the clicking frequency of a certain history preferred dish page is greater than a second preset frequency threshold value, the interest value of the history preferred dish is determined to be "1", otherwise, the interest value of the history preferred dish is determined to be "0".
And carrying out weighted summation on the similarity of each target recommended dish and each history preference dish and the interest value of each history preference dish of the target user, and determining the interest value of the target user on each target recommended dish.
In one embodiment, the target user's interest value p for each target recommended dish is determined by the following formula:
wherein j is the target recommended dish, i is the history preference dish, S (j, K) is a set of K dishes similar to the target recommended dish j, W ij For the similarity of the target recommended dishes j and the history preferred dishes i, N (x) is a set of the history preferred dishes of the user, R xi For the interest value of the user x on the history preference dish i, if the user x has purchasing or clicking actions on the dish i, R xi =1, if user x has no purchase or click action on i dishes, R xi ＝0。
Optionally, fig. 2 is a flowchart illustrating a method of constructing a dish similarity matrix according to an exemplary embodiment, see fig. 2, including the following steps.
S101, determining a preference co-occurrence matrix corresponding to each user according to preference information of each user in the database.
In one embodiment, a database is queried to know a plurality of historical preference dishes of each user, and the plurality of historical preference dishes are combined in pairs to construct a preference co-occurrence matrix corresponding to each user.
For example, if the historical preference dishes of the user a are the dish a, the dish b and the dish d respectively, the following preference co-occurrence matrix is constructed by combining two by two:
| a | b | d | |
| a | 0 | 1 | 1 |
| b | 1 | 0 | 0 |
| d | 1 | 0 | 0 |
optionally, C [ i ] [ j ] is defined as the number of users who like i dish and j dish at the same time, for illustration, see the preference co-occurrence matrix corresponding to user a, and C [ a ] [ b ] =1, representing that only user a is one user who like a dish and b dish at the same time.
S102, overlapping preference co-occurrence matrixes corresponding to a plurality of users, and determining a dish co-occurrence matrix, wherein the dish co-occurrence matrix is used for representing the number of target users who prefer any two dishes at the same time.
For example, if the historical preference dishes of the user a are the dishes a, the dishes b and the dishes d, the user who likes the dishes a and the dishes d simultaneously is one person, the historical preference dishes of the user E are the dishes a and the dishes d, the user who likes the dishes a and the dishes d simultaneously is one person, and after the preference co-occurrence matrixes of the user a and the user E are overlapped, the dishes co-occurrence matrixes display two people who likes the dishes a and the dishes d simultaneously.
S103, aiming at any two dishes, determining the similarity between the any two dishes according to the dish co-occurrence matrix and the target user quantity of the two dishes which are preferred in the database respectively.
In one embodiment, the similarity W between any two dishes is determined by the following formula:
wherein, C [ i ] [ j ] is the number of users who like i dishes and j dishes at the same time, N (i) is the number of users who like i dishes, and N (j) is the number of users who like j dishes.
And S104, normalizing the similarity between any two dishes according to preset parameters, and determining the target similarity between any two dishes.
In one embodiment, the preset parameter may be set to a maximum value of the similarity between any two dishes, and the similarity between the dishes may be normalized according to the preset parameter.
S105, constructing a dish similarity matrix according to the target similarity between any two dishes.
By constructing the dish similarity matrix through the method, dishes similar to the dishes which are historically preferred by the user can be recommended to the user by inquiring the target similarity between any two dishes, so that the accuracy and coverage rate of dish recommendation are improved.
Optionally, the method further comprises:
and under the condition that preference information matched with the identity information exists in the database, inputting the preference information into a pre-trained dish recommendation model to obtain second recommended dish information, wherein the dish recommendation model is trained according to sample preference information of other users with the same preference as the target user.
In one embodiment, in the database, the historical preference dishes of the user a are "spicy chicken" and "spicy bean curd", the user B has the same preference as the user a, and it can be determined that the tastes of the user a and the user B are similar, for example, the labels of the preference dishes of the user a and the user B may be "spicy", "Sichuan dish", the preference dishes of the user B also include "poached beef", and then the user a may also like "poached beef", and then it is determined that the second recommended dish is "poached beef".
And displaying the second recommended dish information on the user page.
In one embodiment, the first recommended dish information and the second recommended dish information can be displayed together on a user display page, the first recommended dish information can be "guessed like" by using a prompt, the second recommended dish can be "all like" by using the prompt, and by the adoption of the mode, the user can select dishes more conveniently, and the dish recommending efficiency is greatly improved.
Optionally, the method further comprises:
and if the preference information matched with the identity information does not exist in the database, displaying preset special dishes and hot-sell products on the user page.
If the preference information matched with the identity information of the target user does not exist in the database, the target user may be a new user just registered or a user who has no ordering record in a restaurant, and then the special dishes or hot-sell products can be recommended to the user, so that the recommendation efficiency is improved.
The present disclosure also provides a dish recommendation device 200, as shown in fig. 3, including:
the obtaining module 201 is configured to obtain identity information of the target user.
The determining module 202 determines the first recommended dish information according to the preference information and a pre-constructed dish similarity matrix when the preference information matched with the identity information exists in the database.
And the display module 203 is configured to display the first recommended dish information on a user page.
Optionally, the preference information includes dish evaluation information and user behavior information, and the determining module 202 is configured to:
and according to the dish evaluation information, determining a plurality of target recommended dishes by inquiring the dish similarity matrix.
And determining the interest value of the target user for each target recommended dish according to the user behavior information and the dish similarity matrix.
And arranging the target recommended dishes according to the interest values corresponding to the target recommended dishes from large to small, and determining the target recommended dishes corresponding to the interest values of the preset number as the first recommended dish information.
Optionally, the sub-module of the determination module 202 is configured to:
and determining a plurality of historical preference dishes with scores greater than a preset score threshold according to the dish evaluation information.
Inquiring a pre-constructed dish similarity matrix, and determining a plurality of similarity dishes corresponding to each history preference dish.
And removing repeated dishes in the similar dishes and the historical preference dishes, and determining a plurality of target recommended dishes.
Optionally, the sub-module of the determination module 202 is configured to:
and according to the user behavior information, determining the interest value of the target user for each history preference dish.
And carrying out weighted summation on the similarity of each target recommended dish and each history preference dish and the interest value of each history preference dish of the target user, and determining the interest value of the target user on each target recommended dish.
Optionally, the sub-module of the determination module 202 is configured to:
and determining a preference co-occurrence matrix corresponding to each user according to the preference information of each user in the database.
And superposing preference co-occurrence matrixes corresponding to the plurality of users to determine a dish co-occurrence matrix, wherein the dish co-occurrence matrix is used for representing the number of target users who prefer any two dishes at the same time.
And determining the similarity between any two dishes according to the dish co-occurrence matrix and the number of users who prefer the two dishes in the database respectively.
Normalizing the similarity between any two dishes according to preset parameters, and determining the target similarity between any two dishes.
And constructing a dish similarity matrix according to the target similarity between any two dishes.
Optionally, the determination module 202 is configured to:
and under the condition that preference information matched with the identity information exists in the database, inputting the preference information into a pre-trained dish recommendation model to obtain second recommended dish information, wherein the dish recommendation model is trained according to sample preference information of other users with the same preference as the target user.
And displaying the second recommended dish information on the user page.
Optionally, the display model 203 is configured to:
and if the preference information matched with the identity information does not exist in the database, displaying preset special dishes and hot-sell products on the user page.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
Fig. 4 is a block diagram of an electronic device 700, according to an example embodiment. As shown in fig. 4, the electronic device 700 may include: a processor 701, a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input/output (I/O) interface 704, and a communication component 705.
The processor 701 is configured to control the overall operation of the electronic device 700 to complete all or part of the steps in the dish recommendation method described above. The memory 702 is used to store various types of data to support operation on the electronic device 700, which may include, for example, instructions for any application or method operating on the electronic device 700, as well as application-related data, such as contact data, messages sent and received, pictures, audio, video, and so forth. The Memory 702 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM for short), electrically erasable programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM for short), programmable Read-Only Memory (Programmable Read-Only Memory, PROM for short), read-Only Memory (ROM for short), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia component 703 can include a screen and an audio component. Wherein the screen may be, for example, a touch screen, the audio component being for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 702 or transmitted through the communication component 705. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 704 provides an interface between the processor 701 and other interface modules, which may be a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, bluetooth, near field communication (Near Field Communication, NFC for short), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or one or a combination of more of them, is not limited herein. The corresponding communication component 705 may thus comprise: wi-Fi module, bluetooth module, NFC module, etc.
In an exemplary embodiment, the electronic device 700 may be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, abbreviated ASIC), digital signal processor (Digital Signal Processor, abbreviated DSP), digital signal processing device (Digital Signal Processing Device, abbreviated DSPD), programmable logic device (Programmable Logic Device, abbreviated PLD), field programmable gate array (Field Programmable Gate Array, abbreviated FPGA), controller, microcontroller, microprocessor, or other electronic components for performing the above-described dish recommendation method.
In another exemplary embodiment, a computer readable storage medium is also provided, comprising program instructions which, when executed by a processor, implement the steps of the dish recommendation method described above. For example, the computer readable storage medium may be the memory 702 including program instructions described above, which are executable by the processor 701 of the electronic device 700 to perform the dish recommendation method described above.
Fig. 5 is a block diagram illustrating an electronic device 1900 according to an example embodiment. For example, electronic device 1900 may be provided as a server. Referring to fig. 5, the electronic device 1900 includes a processor 1922, which may be one or more in number, and a memory 1932 for storing computer programs executable by the processor 1922. The computer program stored in memory 1932 may include one or more modules each corresponding to a set of instructions. Further, the processor 1922 may be configured to execute the computer program to perform the dish recommendation method described above.
In addition, the electronic device 1900 may further include a power component 1926 and a communication component 1950, the power component 1926 may be configured to perform power management of the electronic device 1900, and the communication component 1950 may be configured to enable communication of the electronic device 1900, e.g., wired or wireless communication. In addition, the electronic device 1900 may also include an input/output (I/O) interface 1958. Electronic device 1900 may operate based on an operating system stored in memory 1932.
In another exemplary embodiment, a computer readable storage medium is also provided, comprising program instructions which, when executed by a processor, implement the steps of the dish recommendation method described above. For example, the non-transitory computer readable storage medium may be the memory 1932 including program instructions described above that are executable by the processor 1922 of the electronic device 1900 to perform the dish recommendation method described above.
In another exemplary embodiment, a computer program product is also provided, comprising a computer program executable by a programmable apparatus, the computer program having code portions for performing the above-described dish recommendation method when executed by the programmable apparatus.
The preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings, but the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solutions of the present disclosure within the scope of the technical concept of the present disclosure, and all the simple modifications belong to the protection scope of the present disclosure.
In addition, the specific features described in the foregoing embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, the present disclosure does not further describe various possible combinations.
Moreover, any combination between the various embodiments of the present disclosure is possible as long as it does not depart from the spirit of the present disclosure, which should also be construed as the disclosure of the present disclosure.
Claims (10)
1. A dish recommendation method, comprising:
acquiring identity information of a target user;
under the condition that preference information matched with the identity information exists in a database, determining first recommended dish information according to the preference information and a pre-constructed dish similarity matrix;
and displaying the first recommended menu information on a user page.
2. The method of claim 1, wherein the preference information includes dish rating information and user behavior information, and wherein determining the first recommended dish information based on the preference information and a pre-constructed dish similarity matrix comprises:
according to the dish evaluation information, determining a plurality of target recommended dishes by inquiring the dish similarity matrix;
according to the user behavior information and the dish similarity matrix, determining an interest value of the target user for each target recommended dish;
and arranging the target recommended dishes according to the interest values corresponding to the target recommended dishes from large to small, and determining the target recommended dishes corresponding to the interest values of the preset number as the first recommended dish information.
3. The method of claim 2, wherein the determining a plurality of target recommended dishes by querying the dish similarity matrix according to the dish evaluation information comprises:
determining a plurality of historical preference dishes with scores greater than a preset score threshold according to the dish evaluation information;
inquiring a pre-constructed dish similarity matrix, and determining a plurality of similarity dishes corresponding to each history preference dish;
and removing repeated dishes in the similar dishes and the historical preference dishes, and determining a plurality of target recommended dishes.
4. The method of claim 2, wherein the determining the interest value of the target user for each of the target recommended dishes based on the user behavior information and the dish similarity matrix comprises:
according to the user behavior information, determining an interest value of the target user for each history preference dish;
and carrying out weighted summation on the similarity of each target recommended dish and each history preference dish and the interest value of each history preference dish of the target user, and determining the interest value of the target user on each target recommended dish.
5. The method of any one of claims 1-4, wherein the dish similarity matrix is constructed by:
determining a preference co-occurrence matrix corresponding to each user according to preference information of each user in the database;
superposing preference co-occurrence matrixes corresponding to a plurality of users, and determining a dish co-occurrence matrix, wherein the dish co-occurrence matrix is used for representing the number of target users who prefer any two dishes at the same time;
for any two dishes, determining the similarity between the any two dishes according to the dish co-occurrence matrix and the number of users who prefer the two dishes in the database respectively;
normalizing the similarity between any two dishes according to preset parameters, and determining the target similarity between any two dishes;
and constructing the dish similarity matrix according to the target similarity between any two dishes.
6. The method according to claim 1, wherein the method further comprises:
under the condition that preference information matched with the identity information exists in the database, inputting the preference information into a pre-trained dish recommendation model to obtain second recommended dish information, wherein the dish recommendation model is obtained by training according to sample preference information of other users with the same preference as the target user;
and displaying the second recommended dish information on the user page.
7. The method according to claim 1, wherein the method further comprises:
and if the preference information matched with the identity information does not exist in the database, displaying preset special dishes and hot-sell products on the user page.
8. A dish recommendation device, comprising:
the acquisition module is configured to acquire the identity information of the target user;
the determining module is configured to determine first recommended dish information according to the preference information and a pre-constructed dish similarity matrix under the condition that preference information matched with the identity information exists in a database;
and the display module is configured to display the first recommended menu information on a user page.
9. A non-transitory computer readable storage medium having stored thereon a computer program, characterized in that the program when executed by a processor realizes the steps of the method according to any of claims 1-7.
10. An electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311265317.3A CN117453992A (en) | 2023-09-26 | 2023-09-26 | Dish recommending method and device, medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311265317.3A CN117453992A (en) | 2023-09-26 | 2023-09-26 | Dish recommending method and device, medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117453992A true CN117453992A (en) | 2024-01-26 |
Family
ID=89590017
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311265317.3A Pending CN117453992A (en) | 2023-09-26 | 2023-09-26 | Dish recommending method and device, medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117453992A (en) |
-
2023
- 2023-09-26 CN CN202311265317.3A patent/CN117453992A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10467267B2 (en) | Iterative image search algorithm informed by continuous human-machine input feedback | |
| CN107835231B (en) | Feedback information processing method and terminal equipment | |
| CN110473040B (en) | Product recommendation method and device and electronic equipment | |
| US9812022B2 (en) | Method and apparatus for providing healthier food purchase suggestions to a shopper | |
| CN107220852A (en) | Method, device and server for determining target recommended user | |
| JP5422084B1 (en) | Cooking recipe information providing apparatus, cooking recipe information providing method, program, and information recording medium | |
| CN102934113B (en) | Information providing system, information providing method, information providing apparatus | |
| CN108648058B (en) | Product sorting method and device, electronic equipment and storage medium | |
| CN110674391B (en) | Product data pushing method and system based on big data and computer equipment | |
| JP6957879B2 (en) | Food ordering system and food ordering method | |
| US20130110754A1 (en) | Factor-graph based matching systems and methods | |
| US20190325501A1 (en) | Meal-Kit Recommendation Engine | |
| JP5831204B2 (en) | Information providing system, information providing method, and program | |
| CN109886772A (en) | Products Show method, apparatus, computer equipment and storage medium | |
| CN108062692B (en) | Recording recommendation method, device, equipment and computer readable storage medium | |
| US20150254680A1 (en) | Utilizing product and service reviews | |
| JP2018156429A (en) | Information processing device, information processing method, and program | |
| CN106027585A (en) | Food recommending method and device | |
| US20160335683A1 (en) | Rating System and Method | |
| CN109741125A (en) | Recommend method and device, the storage medium, electronic device of vegetable | |
| JP5615464B1 (en) | Cooking recipe information providing apparatus, cooking recipe information providing method, program, and information recording medium | |
| CN110851702B (en) | Information pushing method, device, terminal and computer readable medium | |
| CN116228342B (en) | Commodity recommendation method and device and computer readable storage medium | |
| CN117453992A (en) | Dish recommending method and device, medium and electronic equipment | |
| CN111193598B (en) | Group chat session recommendation 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 |