CN112328845B - Dish pushing method and device based on cooking equipment and cooking equipment - Google Patents
Dish pushing method and device based on cooking equipment and cooking equipment Download PDFInfo
- Publication number
- CN112328845B CN112328845B CN202011259689.1A CN202011259689A CN112328845B CN 112328845 B CN112328845 B CN 112328845B CN 202011259689 A CN202011259689 A CN 202011259689A CN 112328845 B CN112328845 B CN 112328845B
- Authority
- CN
- China
- Prior art keywords
- user
- dish
- feature
- characteristic
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- 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
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
Abstract
The application relates to a cooking equipment-based dish pushing method and device and the cooking equipment. The method comprises the following steps: acquiring historical behavior data of a user of the cooking equipment, and generating a corresponding user characteristic value according to the historical behavior data of the user; dividing users according to the relevance of each user characteristic value to generate user characteristic clusters; acquiring grouped user characteristics corresponding to each user characteristic group; acquiring a dish basic characteristic value generated according to dish attribute information; and determining the dishes to be recommended according to the basic characteristic values of the dishes and the characteristics of the grouped users. By combining the existing dish attribute information, the dish to be recommended which is acceptable by each user in the same group with higher association degree is determined, the dish is not limited to the recommendation of popular dishes or novel dishes, the dish recommending method provides dishes to be recommended which are more reasonable and selective for the users in the same group, and further improves the dish recommending rationality of the cooking equipment.
Description
Technical Field
The application relates to the technical field of electric appliances, in particular to a dish pushing method and device based on cooking equipment and the cooking equipment.
Background
With the development of electrical appliance technology and the wide application of various cooking devices in daily life of people, in order to better meet the increasingly diversified demands of users, an integrated cooking device integrating various cooking modes or setting different application functions appears, for example, an integrated steaming and baking machine integrating steaming and baking modes is provided with various functions of menu viewing, menu video teaching or dish pushing and the like.
The existing steaming and baking integrated machine has the function of pushing dishes, and corresponding recommended dishes are obtained by acquiring networking data, determining hot dishes within a period of time or newly taking out dishes according to the acquired networking data.
Because the basis that the conventional steaming and baking integrated machine generates recommended dishes is single, the recommended dishes are easy to appear and do not meet the requirements of users using the steaming and baking integrated machine, and the dish recommendation rationality is low.
Disclosure of Invention
Based on this, it is necessary to provide a cooking device-based dish pushing method and apparatus and a cooking device, which can improve the dish recommendation rationality of the cooking device, in view of the above technical problems.
A dish pushing method based on a cooking device, the method comprising:
acquiring historical user behavior data of the cooking equipment, and generating a corresponding user characteristic value according to the historical user behavior data;
dividing users according to the relevance of each user characteristic value to generate user characteristic clusters;
obtaining the grouped user characteristics corresponding to each user characteristic group;
acquiring a dish basic characteristic value generated according to dish attribute information;
and determining the dishes to be recommended according to the dish basic characteristic value and the group user characteristics.
In one embodiment, the determining the dish to be recommended according to the dish basic characteristic value and the grouped user characteristic includes:
carrying out user feature similarity quantization processing on the user grouping features to generate user similarity weight scores of the user feature groupings;
and determining the dishes to be recommended according to the similarity weight and the dish basic characteristic value.
In one embodiment, the performing the user feature similarity quantization processing on the user clustering features to generate the user similarity weight scores of the user feature clusters includes:
acquiring user characteristic values of any two users in the user characteristic cluster;
determining a first public intersection feature of any two selected users according to the user feature values of the any two selected users;
determining a first minimum feature weight ratio according to the feature weight ratio of the user feature value corresponding to the first public intersection feature;
and summing the first minimum feature weight ratios to generate a user similarity weight score of each user in the user feature cluster.
In one embodiment, the method further comprises:
generating a push general menu according to the dishes to be recommended;
acquiring historical behavior data of a target pushing user;
and determining a target recommendation menu corresponding to each target push user according to the historical behavior data and the push total menu.
In one embodiment, the determining, according to the historical behavior data and the total push menu, a target recommendation menu corresponding to each of the target push users includes:
according to the user similarity weight score, extracting similar users corresponding to the target pushing user from the user feature cluster;
determining a first dish list with a first dish basic characteristic according to the historical behavior data and the push general menu; the first dish basic feature is the same dish basic feature of the target pushing user and similar users thereof;
determining a second dish list with second dish basic characteristics according to the historical behavior data and the push total menu; the second dish basic feature is a dish basic feature that the target pushing user does not have and the similar user does have;
and generating a target recommendation menu corresponding to each target pushing user according to the first dish list and the second dish list.
In one embodiment, the determining a first dish list having a first dish base characteristic according to the historical behavior data and the push global menu includes:
determining user characteristic values of the target pushing user and similar users thereof according to the historical behavior data;
acquiring dish basic characteristic values of all dishes of the push general menu;
determining a second public intersection feature of the target pushing user and the similar users thereof and the pushing general menu according to the user feature values of the target pushing user and the similar users thereof and the dish basic feature value;
determining a second minimum feature weight ratio according to the feature weight ratio of the dish basic feature value corresponding to the second public intersection feature;
summing the second minimum feature weight ratios to generate a first dish similarity weight score of the target pushing user and similar users thereof;
and sequencing the push general menu according to the first dish similarity weight to generate a first dish list with first dish basic characteristics.
In one embodiment, the determining a second dish list having a second dish base characteristic according to the historical behavior data and the push global menu includes:
deleting the first user characteristic value corresponding to the target push user from the second user characteristic value of the similar user to obtain a third user characteristic value;
determining a third public intersection feature of the similar user and the push total menu according to the third user feature value and the dish basic feature value;
determining a third minimum feature weight ratio according to the feature weight ratio of the dish basic feature value corresponding to the third public intersection feature;
summing the third minimum feature weight ratios to generate a second dish similarity weight score of the similar user;
and sorting the push general menu according to the second dish similarity weight to generate a second dish list with second dish basic characteristics.
In one embodiment, before the performing user partition according to the relevance of each user feature value to generate a user feature cluster, the method further includes:
carrying out quantization processing on the user characteristic value to generate a user characteristic attribute table;
determining the characteristic weight ratio of each user characteristic value of the corresponding user according to the user characteristic attribute table;
and determining the association degree of each user characteristic value according to the user characteristic attribute table and the characteristic weight ratio.
In one embodiment, the method further comprises:
displaying the target recommendation menu;
acquiring operation behavior data aiming at the target recommendation menu;
and adjusting the dish characteristic weight of the target recommendation menu according to the operation behavior data.
A cooking device based dish pushing device, the device comprising:
the user characteristic value generating module is used for acquiring historical user behavior data of the cooking equipment and generating a corresponding user characteristic value according to the historical user behavior data;
the user characteristic clustering generation module is used for carrying out user division according to the relevance of each user characteristic value to generate user characteristic clustering;
the grouping user characteristic acquisition module is used for acquiring the grouping user characteristics corresponding to each user characteristic grouping;
the dish basic characteristic value generating module is used for acquiring dish basic characteristic values generated according to the dish attribute information;
and the dish to be recommended determining module is used for determining the dish to be recommended according to the dish basic characteristic value and the grouped user characteristics.
A cooking device comprises a cooking device body, a display screen, a memory and a processor, wherein the display screen, the memory and the processor are arranged on the cooking device body; the memory stores a computer program which when executed by the processor performs the steps of:
acquiring historical user behavior data of cooking equipment, and generating a corresponding user characteristic value according to the historical user behavior data;
dividing users according to the relevance of each user characteristic value to generate user characteristic clusters;
obtaining the grouped user characteristics corresponding to each user characteristic group;
acquiring a dish basic characteristic value generated according to dish attribute information;
and determining the dishes to be recommended according to the dish basic characteristic value and the group user characteristics.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring historical user behavior data of the cooking equipment, and generating a corresponding user characteristic value according to the historical user behavior data;
dividing users according to the relevance of each user characteristic value to generate user characteristic clusters;
obtaining the grouped user characteristics corresponding to each user characteristic group;
acquiring a dish basic characteristic value generated according to dish attribute information;
and determining the dishes to be recommended according to the dish basic characteristic value and the group user characteristics.
According to the dish pushing method and device based on the cooking equipment and the cooking equipment, the user historical behavior data of the cooking equipment is obtained, and the corresponding user characteristic value is generated according to the user historical behavior data. And carrying out user division according to the association degree of each user characteristic value, generating user characteristic clusters, and acquiring the cluster user characteristics corresponding to each user characteristic cluster. And determining the dish to be recommended according to the dish basic characteristic value generated according to the dish attribute information and the dish basic characteristic value and the grouped user characteristics. Because the user characteristic groups with similar user characteristic values are obtained according to the historical behavior data of the users, the users under each user characteristic group have the same or similar user characteristic values, the association degree between the users is high, and the dishes to be recommended, which are acceptable by the users under the same group with the high association degree, are determined by combining the existing dish attribute information, so that the method is not limited to the recommendation of hot dishes or new dishes, provides more reasonable and selective dishes to be recommended for the users under the same group, and further improves the dish recommendation rationality of the cooking equipment.
Drawings
Fig. 1 is an application environment diagram of a dish pushing method based on a cooking device in an embodiment;
fig. 2 is a schematic flow chart of a dish pushing method based on a cooking device in one embodiment;
fig. 3 is a schematic flow chart of a dish pushing method based on a cooking device in another embodiment;
FIG. 4 is a block diagram of a dish pushing device based on a cooking device in one embodiment;
fig. 5 is an internal structure view of a cooking apparatus in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The dish pushing method based on the cooking device can be applied to an application environment shown in fig. 1. Wherein the cooking appliance 102 communicates with the server 104 over a network. The server 104 generates user characteristic groups by acquiring the user historical behavior data of the cooking device 102 and generating corresponding user characteristic values according to the user historical behavior data, and further performing user division according to the relevance of each user characteristic value. The method comprises the steps of obtaining group user characteristics corresponding to each user characteristic group, obtaining dish basic characteristic values generated according to dish attribute information, and determining dishes to be recommended according to the dish basic characteristic values and the group user characteristics. The dishes to be recommended are displayed on the cooking device 102 or on a mobile terminal device connected to the cooking device 102. The cooking device 102 may be, but not limited to, a steaming and baking all-in-one machine, an oven, a steam box, an electric cooker, an automatic cooker, and the like, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a cooking device based dish pushing method is provided, which is described by taking the method as an example of being applied to the server in fig. 1, and includes the following steps:
step 202, obtaining historical behavior data of a user of the cooking device, and generating a corresponding user characteristic value according to the historical behavior data of the user.
The historical user behavior data of the cooking equipment comprises historical use data of the cooking equipment by a user, wherein the historical use data comprises use data of different use modes such as dish cooking, dish checking, dish tutorial checking and the like. The dish cooking method aims at dish cooking aspects and comprises dishes cooked by a user, food raw materials, cooking modes, cooking time periods, a dish family to which the dishes belong, dish components, cooking times and cooking cycles/frequencies of the same dishes and the like. And aiming at dish checking and dish course checking, the checking times of each dish browsed by a user and the checking times, the checking duration and the like of each dish course are included.
Specifically, historical user data of the cooking equipment, including historical use data of different use modes such as dish cooking, dish checking and dish course checking, are obtained, and corresponding user characteristic values are generated according to the historical user behavior data. The user characteristic value may include a favorite style of the user for dishes, including food materials, a dish system, a cooking mode, and the like.
Furthermore, the user characteristic value of the user is updated by acquiring the behavior data of the user in real time. When a certain user characteristic value of the user reaches an effective condition, namely the occurrence frequency of the user characteristic value reaches a threshold value of a corresponding user characteristic value, or the proportion of the occurrence frequency of the user characteristic value to the threshold value of the total user behavior is equal, the corresponding user characteristic value is added to the user. The method for obtaining the effective conditions is to set the effective condition default threshold of each characteristic value according to the user data by analyzing the user data.
And 204, dividing the users according to the relevance of each user characteristic value to generate user characteristic clusters.
Specifically, a user characteristic attribute table is generated by performing quantization processing on the user characteristic values, and the characteristic weight ratio of each user characteristic value corresponding to the user is determined according to the user characteristic attribute table. And determining the association degree of each user characteristic value according to the user characteristic attribute table and the characteristic weight ratio, and further performing user division according to the determined association degree of each user characteristic value to generate user characteristic clusters.
The relevance of the user characteristic values is used for determining the similarity among the users, and the users with the similarity higher than a preset similarity threshold are divided into the same user characteristic grouping. The preset similarity threshold value can be preset with a default value or adjusted according to actual application conditions.
Further, a Boolean value quantization mode is adopted for quantization processing, wherein:
the total characteristic Boolean value is T General assembly ＝{T 1 ，T 2 ……T max }，T 1 ……T max Each T value in (1) is 0 or 1. The total feature weight table is P General assembly ＝{P 1 ，P 2 ……P max }，P 1 ……P max Each P value is 0 to 100.
The user characteristic table obtained is T user ＝{T 1 ，T 2 ……T max }，T 1 ……T max Each T value in (1) is 0 or 1. Wherein if T of user exists x Characteristic, then T x 1, otherwise T x 0. The user characteristic weight table is P user ＝{P 1 ，P 2 ……P max }，P 1 ……P max Each P value in (1) is 0 to 100. Wherein if T of user exists x Characteristic, then P user P of x Is P General assembly P in (1) x Otherwise, it is 0.
Wherein, the weight ratio is used for reflecting the relevance weight ratio of the characteristic on each dish/user. Because the weight ratio of the same characteristic on different dishes is different, the attribute of each dish can be quantized through the weight ratio. Similarly, the user feature weight ratio is also the weight of the feature on the user, and the user weight ratio is updated in real time according to each user behavior. For example, if the user clicks push, and determines that the user likes the push, a plurality of characteristics corresponding to the pushed dishes will increase the weight ratio of the characteristics of the corresponding users. The higher the weight ratio, the higher the relevance representing the feature, and the lower the weight ratio, the lower the relevance representing the feature.
In one embodiment, the following user feature groups and corresponding dish pushing can be obtained by dividing according to the user feature values:
1) and (4) grouping the characteristics of the user who never uses the steaming oven, and pushing the dishes for the first time.
2) And grouping the user characteristics with fewer times of using the steam oven to push simple dishes.
3) And (4) clustering the user characteristics of the frequent frequency times after 10:00 night, and correspondingly pushing the users at night.
4) Like a certain class of food materials (e.g.: fruits, vegetables, meat, etc.), and pushing the type of dishes which are uncooked but have more cooking times of other users in the network data under the user characteristic grouping.
5) And (4) grouping the user characteristics with more complicated cooking degree, and pushing dishes with higher cooking difficulty.
6) And (4) continuously cooking user characteristics of a large amount of dishes, grouping and pushing household special dishes.
7) And (4) grouping the user characteristics with stable cooking period, and pushing uncooked dishes which are normally hot at home.
8) And (4) grouping the user characteristics with small food cooking amount, and pushing a small-amount single package.
9) Grouping the user characteristics of the same food material cooking modes, and performing corresponding cooking modes (such as: baking and steaming).
And step 206, acquiring the grouped user characteristics corresponding to each user characteristic group.
Specifically, the group user characteristics are obtained by obtaining user characteristic values of all users in each user characteristic group. The user characteristics of the groups can be obtained by historical use data of different use modes such as dish cooking, dish checking, dish course checking and the like.
And step 208, acquiring a dish basic characteristic value generated according to the dish attribute information.
Specifically, corresponding dish basic characteristic values are generated by acquiring dish attribute information stored in a local storage of the cooking equipment and stored in a cloud of the server. The dish attribute information comprises known basic operation interface information, menus, menu content attribute labels, cooking time and region information.
The known basic operation interface information may include a cooking mode selected on a display interface of the cooking device, and the number of times each cooking mode is selected, including different cooking modes such as a steaming mode, a steaming and baking mode, and a baking mode. The menu corresponds to an actual dish name, the content attribute labels of the menu comprise different information such as a cooking mode, food raw materials, a cuisine, cooking time, cooking taste and cooking difficulty, the cooking time represents cooking time periods including three-meal time periods in the morning, the noon and the evening, afternoon tea, night and the like, and the region information represents a preferred taste and a preferred food dish of an area where the cooking equipment is located.
Further, a Boolean value quantization mode is adopted to perform quantization processing on the dish attribute information, wherein:
the characteristic table of the dish is T item ＝{T 1 ，T 2 ……T max }，T 1 ……T max Wherein each T value is 0 or 1, if T is present in the dish x Characteristic, then T x 1, otherwise T x 0. The dish characteristic weight table is P item ＝{P 1 ，P 2 ……P max }，P 1 ……P max Each P value in the range of 0 to 100, T if present x Characteristic, then P item P of x Is P General assembly P in (1) x Otherwise, it is 0.
And step 210, determining the dishes to be recommended according to the basic characteristic values of the dishes and the characteristics of the grouped users.
Specifically, the user feature similarity quantization processing is carried out on the user grouping features to generate user similarity weight scores of the user feature groupings, and dishes to be recommended are determined according to the similarity weight scores and the dish basic feature values.
Further, the first public intersection feature of any two selected users is determined by obtaining the user feature values of any two users in the user feature cluster and according to the user feature values of any two selected users. And determining a first minimum feature weight ratio according to the feature weight ratio of the user feature value corresponding to the first public intersection feature, and summing the first minimum feature weight ratios to generate a user similarity weight score of each user in the user feature cluster.
Wherein the first minimum feature weight ratios are summed using the following formula:
wherein the content of the first and second substances,
i.e. from k 1 to k n, P mink And obtaining the user similarity weight score of each user in the user feature cluster.
According to the dish pushing method based on the cooking equipment, the historical behavior data of the user of the cooking equipment is obtained, and the corresponding user characteristic value is generated according to the historical behavior data of the user. And carrying out user division according to the association degree of each user characteristic value, generating user characteristic clusters, and acquiring the cluster user characteristics corresponding to each user characteristic cluster. And determining the dish to be recommended according to the dish basic characteristic value generated according to the dish attribute information and the dish basic characteristic value and the grouped user characteristics. Because the user characteristic groups with similar user characteristic values are obtained according to the historical behavior data of the users, the users under each user characteristic group have the same or similar user characteristic values, the association degree among the users is high, and the dishes to be recommended, which are acceptable by the users under the same group with the high association degree, are determined by combining the existing dish attribute information, so that the dish recommendation method is not limited to the recommendation of popular dishes or new dishes, provides more reasonable and selective dishes to be recommended for the users under the same group, and further improves the dish recommendation rationality of the cooking equipment.
In one embodiment, as shown in fig. 3, a cooking device based dish pushing method is provided, which specifically includes the following steps:
and step S302, generating a push total menu according to the dishes to be recommended.
Specifically, a general push menu corresponding to the user characteristic clustering is generated according to dishes to be recommended, wherein the general push menu is a group menu used as the user characteristic clustering, and for each target push user in the user clustering, the general push menu needs to be screened according to the historical behavior data of the target push user, so that the target recommendation menu corresponding to each target push user is determined.
Step S304, obtaining historical behavior data of the target push user.
Specifically, historical behavior data of a target pushing user is obtained and comprises historical use data of the user on cooking equipment, wherein the historical use data comprises use data of different use modes such as dish cooking, dish checking and dish tutorial checking. The dish cooking method aims at dish cooking aspects and comprises dishes cooked by a user, food raw materials, cooking modes, cooking time periods, a dish family to which the dishes belong, dish components, cooking times and cooking cycles/frequencies of the same dishes and the like. And aiming at dish checking and dish tutorial checking, the method comprises the steps of checking times of browsing each dish by a user, checking times and checking duration of each dish tutorial, and the like.
And step S306, determining a target recommendation menu corresponding to each target push user according to the historical behavior data and the push total menu.
Specifically, according to the user similarity weight, extracting similar users corresponding to the target pushing user from the user feature cluster, further determining a first dish list with basic features of a first dish according to historical behavior data and a pushing general menu, and determining a second dish list with basic features of a second dish according to the historical behavior data and the pushing general menu. The first dish basic feature is the same dish basic feature which the target pushing user and the similar user have, and the second dish basic feature is the dish basic feature which the target pushing user does not have but the similar user has. And then generating a target recommendation menu corresponding to each target push user according to the first dish list and the second dish list.
When the target pushing user meets the requirement of belonging to a plurality of user characteristic clusters at the same time, a plurality of pushing general menus corresponding to the target pushing user are generated, and then the plurality of pushing general menus are screened according to historical behavior data of the target pushing user. And determining common dishes in the pushed general menu by carrying out pushed menu iteration for multiple times, determining the pushed general menu with the most common dishes, and extracting a target recommendation menu corresponding to each target pushing user from the pushed general menu with the most common dishes. The obtained target recommendation menu is an individualized recommendation menu corresponding to the target pushing user, and the user requirements are better met.
In one embodiment, determining a first list of dishes having a first dish base characteristic based on historical behavior data and a push summary menu comprises:
determining user characteristic values of a target pushing user and similar users thereof according to historical behavior data;
acquiring basic characteristic values of dishes of all dishes of the push general menu;
determining a second public intersection feature of the target pushing user and similar users thereof and a pushing total menu according to the user feature values of the target pushing user and similar users thereof and the dish basic feature value;
determining a second minimum feature weight ratio according to the feature weight ratio of the dish basic feature value corresponding to the second public intersection feature;
summing the second minimum characteristic weight ratios to generate a first dish similarity weight score of the target pushing user and the similar users thereof;
and sequencing the pushed general menus according to the first dish similarity weight score to generate a first dish list with the first dish basic characteristics.
Specifically, according to historical behavior data, a user characteristic value of a target pushing user and a user characteristic value of a similar user are determined, dish basic characteristic values of all dishes in a pushing general menu are obtained, the target pushing user and the similar user are further obtained, a second intersection feature of the target pushing user and all dishes in the pushing general menu and a second intersection feature of all dishes in the pushing general menu are obtained, and a feature weight ratio of dish basic characteristic values corresponding to the second intersection feature is obtained, wherein the feature weight ratio comprises the feature weight ratio of the target pushing user and all dishes in the pushing general menu, and the feature weight ratio of all dishes in the similar user and all dishes in the pushing general menuThe characteristic weight ratio of the product is taken as the second minimum weight P min1 And adding all the minimum second weights to obtain a first dish similarity weight score S item 。
Wherein, the first dish similarity weight score S is calculated by adopting the following formula item ：
Wherein, among others,
i.e. from k 1 to k n, P mink And obtaining the weight of the similarity of the first dish.
Further, the pushed general menus are sorted according to the first dish similarity weight score, and a first dish list with the first dish basic characteristics is generated. And comparing the list of the target pushing user with the list of the similar users, and selecting dishes which do not exist in the list of the target pushing user, but exist in the list of the similar users and have scores from high to low, so as to obtain a dish list with the same characteristics which are liked by people with the similar characteristics, namely the first dish list.
In one embodiment, determining a second menu list having a second menu base characteristic based on the historical behavior data and the push summary menu comprises:
deleting a first user characteristic value corresponding to the target push user from a second user characteristic value of the similar user to obtain a third user characteristic value;
determining a third public intersection feature of the similar user and the pushed total menu according to the third user feature value and the dish basic feature value;
determining a third minimum feature weight ratio according to the feature weight ratio of the dish basic feature value corresponding to the third public intersection feature;
summing the third minimum feature weight ratios to generate a second dish similarity weight score of the similar user;
and sequencing the pushed general menus according to the second dish similarity weight score to generate a second dish list with second dish basic characteristics.
Specifically, according to historical behavior data, a user characteristic value of a target pushing user and a user characteristic value of a similar user are determined, dish basic characteristic values of dishes of a pushing general menu are obtained, a first user characteristic value corresponding to the target pushing user is deleted from a second user characteristic value of the similar user, a third user characteristic value is obtained, and then a third public intersection characteristic of the similar user and the pushing general menu is determined according to the third user characteristic value and the dish basic characteristic values. Determining a third minimum feature weight ratio according to the feature weight ratio of the basic feature values of the dishes corresponding to the third public intersection feature, wherein the third minimum feature weight ratio comprises the feature weight ratio of each dish in the target push user and the push general menu and the feature weight ratio of each dish in the similar user and the push general menu, and taking a third minimum weight P min1 And adding all the minimum third weights to obtain a second dish similarity weight score S item 。
Wherein, the second dish similarity weight score S is calculated by the following formula item ：
Wherein, among others,
i.e. from k 1 to k n, P mink And obtaining a second dish similarity weight score.
And further, sorting the pushed general menu according to the second dish similarity weight score to generate a second dish list with the second dish basic characteristics. And comparing the list of the target push user with the list of the similar user, selecting dishes which do not exist in the first dish list, but exist in the similar user list and have scores from high to low, obtaining a dish list with different characteristics which are most favored by people with similar characteristics, and determining the dish list as the second dish list.
According to the dish pushing method based on the cooking equipment, a pushing general menu is generated according to dishes to be recommended, historical behavior data of target pushing users are obtained, and target recommending menus corresponding to the target pushing users are determined according to the historical behavior data and the pushing general menu. The personalized target recommendation menu is pushed to the users according to the targets in the user characteristic grouping, dishes to be recommended are provided for the users, the dish recommendation reasonability is higher, the number of the dishes to be recommended is large, and dish recommendation reasonability of the cooking equipment is further improved.
In one embodiment, after determining a target recommendation menu corresponding to each target push user according to the historical behavior data and the push total menu, the method further includes:
displaying a target recommendation menu; acquiring operation behavior data aiming at a target recommendation menu; and adjusting the dish characteristic weight of the target recommendation menu according to the operation behavior data.
Specifically, the target recommendation menu is displayed on a display screen of the cooking equipment or sent to a mobile terminal device connected with the cooking equipment for displaying, and operation behavior data of a user for the target recommendation menu is acquired. The operation behavior data aiming at the target recommendation menu comprises viewing operation of the target recommendation menu, tutorial viewing operation of recommended dishes included in the target recommendation menu and cooking operation.
Further, when the viewing operation of the user on the target recommendation menu, and the tutorial viewing operation and the cooking operation of the recommended dishes included in the target recommendation menu are detected, the dish feature weight of the target recommendation menu is adjusted according to the corresponding viewing operation or the corresponding cooking operation.
Wherein, if the pushed dish is accepted, the quantitative processing of the behavior is as follows: the characteristics of the dish accord with the characteristics of the user, the characteristics of the user are really liked by the user, and the characteristics of the dish accurately correspond to the attributes of the dish, so the characteristic weight of the dish is positively increased, and the characteristic weight owned by the corresponding user is also positively increased.
On the contrary, if the pushed dish is rejected, the quantitative processing of the behavior is as follows: the feature of the dish may not correspond to the user feature, and the user feature may not be preferred by the user, and the dish feature may not correspond to the dish attribute, so that the feature weight of the dish is inversely reduced, and the feature weight possessed by the corresponding user is also inversely reduced.
In the embodiment, the target recommendation menu is displayed, the operation behavior data aiming at the target recommendation menu is obtained, the dish feature weight of the target recommendation menu is adjusted according to the operation behavior data, the dish feature weight of the target recommendation menu is adjusted in real time according to the operation behavior data of the user, the target recommendation dishes are updated in time, the rationality is higher for the user, and the dish recommendation rationality of the cooking equipment is further improved.
It should be understood that, although the steps in the flowcharts related to the above embodiments are shown in sequence as indicated by the arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in each flowchart related to the above embodiments may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.
In one embodiment, as shown in fig. 4, there is provided a cooking appliance-based dish pushing device including: a user characteristic value generating module 402, a user characteristic clustering generating module 404, a clustering user characteristic obtaining module 406, a dish basic characteristic value generating module 408 and a dish to be recommended determining module 410, wherein:
the user characteristic value generating module 402 is configured to obtain historical user behavior data of the cooking device, and generate a corresponding user characteristic value according to the historical user behavior data.
And a user feature cluster generating module 404, configured to perform user division according to the relevance of each user feature value, and generate a user feature cluster.
A group user characteristic obtaining module 406, configured to obtain a group user characteristic corresponding to each user characteristic group.
And the dish basic characteristic value generating module 408 is configured to obtain a dish basic characteristic value generated according to the dish attribute information.
And the to-be-recommended dish determining module 410 is configured to determine a dish to be recommended according to the dish basic characteristic value and the grouped user characteristics.
According to the dish pushing device based on the cooking equipment, the historical behavior data of the user of the cooking equipment is obtained, and the corresponding user characteristic value is generated according to the historical behavior data of the user. And carrying out user division according to the relevance of each user characteristic value, generating user characteristic clusters, and acquiring the cluster user characteristics corresponding to each user characteristic cluster. And determining the dish to be recommended according to the dish basic characteristic value generated according to the dish attribute information and the dish basic characteristic value and the grouped user characteristics. Because the user characteristic groups with similar user characteristic values are obtained according to the historical behavior data of the users, the users under each user characteristic group have the same or similar user characteristic values, the association degree among the users is high, and the dishes to be recommended, which are acceptable by the users under the same group with the high association degree, are determined by combining the existing dish attribute information, so that the dish recommendation method is not limited to the recommendation of popular dishes or new dishes, provides more reasonable and selective dishes to be recommended for the users under the same group, and further improves the dish recommendation rationality of the cooking equipment.
In one embodiment, a dish pushing device based on a cooking device is provided, further comprising:
and the pushing general menu generating module is used for generating a pushing general menu according to the dishes to be recommended.
And the historical behavior data acquisition module is used for acquiring the historical behavior data of the target pushing user.
And the target recommendation menu generation module is used for determining a target recommendation menu corresponding to each target push user according to the historical behavior data and the push total menu.
In one embodiment, a dish pushing device based on a cooking device is provided, which further comprises a correlation degree calculation module of user characteristic values, which is used for calculating the correlation degree of the user characteristic values
Carrying out quantization processing on the user characteristic value to generate a user characteristic attribute table; determining the characteristic weight ratio of each user characteristic value of the corresponding user according to the user characteristic attribute table; and determining the association degree of each user characteristic value according to the user characteristic attribute table and the characteristic weight ratio.
In one embodiment, a dish pushing device based on a cooking device is provided, further comprising:
and the target recommendation menu display module is used for displaying the target recommendation menu.
And the operation behavior data acquisition module is used for acquiring operation behavior data aiming at the target recommendation menu.
And the dish characteristic weight adjusting module is used for adjusting the dish characteristic weight of the target recommendation menu according to the operation behavior data.
In one embodiment, the dish to be recommended determining module is further configured to:
carrying out user feature similarity quantization processing on the user grouping features to generate user similarity weight scores of the user feature groupings; and determining the dishes to be recommended according to the similarity weight scores and the basic characteristic values of the dishes.
In one embodiment, the dish to be recommended determining module is further configured to:
acquiring user characteristic values of any two users in the user characteristic cluster; determining a first public intersection feature of any two selected users according to the user feature values of any two selected users; determining a first minimum feature weight ratio according to the feature weight ratio of the user feature value corresponding to the first public intersection feature; and summing the first minimum feature weight ratios to generate a user similarity weight score of each user in the user feature cluster.
In one embodiment, the target recommendation menu generating module is further configured to:
extracting similar users corresponding to the target pushing users from the user feature clusters according to the user similarity weight scores; determining a first dish list with a first dish basic characteristic according to historical behavior data and a push general menu; the first dish basic feature is the same dish basic feature of the target pushing user and similar users thereof; determining a second dish list with second dish basic characteristics according to the historical behavior data and the push general menu; the second dish basic characteristic is a dish basic characteristic which the target pushing user does not have but the similar user does; and generating a target recommendation menu corresponding to each target push user according to the first dish list and the second dish list.
In one embodiment, the target recommendation menu generating module is further configured to:
determining user characteristic values of a target pushing user and similar users thereof according to historical behavior data; acquiring basic characteristic values of dishes of all dishes of the push general menu; determining a second public intersection feature of the target pushing user and similar users thereof and a pushing total menu according to the user feature values of the target pushing user and similar users thereof and the dish basic feature value; determining a second minimum feature weight ratio according to the feature weight ratio of the dish basic feature value corresponding to the second public intersection feature; summing the second minimum characteristic weight ratios to generate a first dish similarity weight score of the target pushing user and the similar users thereof; and sequencing the pushed general menu according to the first dish similarity weight to generate a first dish list with the first dish basic characteristics.
In one embodiment, the target recommendation menu generating module is further configured to:
deleting a first user characteristic value corresponding to the target push user from a second user characteristic value of the similar user to obtain a third user characteristic value; determining a third public intersection feature of the similar user and the pushed total menu according to the third user feature value and the dish basic feature value; determining a third minimum feature weight ratio according to the feature weight ratio of the dish basic feature value corresponding to the third public intersection feature; summing the third minimum feature weight ratios to generate a second dish similarity weight score of the similar user; and sequencing the pushed general menus according to the second dish similarity weight score to generate a second dish list with second dish basic characteristics.
For specific definition of the dish pushing device based on the cooking device, reference may be made to the above definition of the dish pushing method based on the cooking device, and details are not repeated here. The modules in the dish pushing device based on the cooking equipment can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a cooking device, the internal structure of which may be as shown in fig. 5. The cooking apparatus includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Wherein the processor of the cooking appliance is configured to provide computing and control capabilities. The memory of the cooking device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the cooking device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a cooking device based dish pushing method. The display screen of the cooking equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the cooking equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on a shell of computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring historical behavior data of a user of the cooking equipment, and generating a corresponding user characteristic value according to the historical behavior data of the user;
dividing users according to the relevance of each user characteristic value to generate user characteristic clusters;
acquiring grouped user characteristics corresponding to each user characteristic group;
acquiring a dish basic characteristic value generated according to dish attribute information;
and determining the dishes to be recommended according to the dish basic characteristic value and the grouped user characteristics.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
carrying out user feature similarity quantization processing on the user grouping features to generate user similarity weight scores of the user feature groupings;
and determining the dishes to be recommended according to the similarity weight scores and the basic characteristic values of the dishes.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring user characteristic values of any two users in the user characteristic cluster;
determining a first public intersection feature of any two selected users according to the user feature values of any two selected users;
determining a first minimum feature weight ratio according to the feature weight ratio of the user feature value corresponding to the first public intersection feature;
and summing the first minimum feature weight ratios to generate a user similarity weight score of each user in the user feature cluster.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
generating a push general menu according to the dishes to be recommended;
acquiring historical behavior data of a target pushing user;
and determining a target recommendation menu corresponding to each target push user according to the historical behavior data and the push total menu.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
extracting similar users corresponding to the target pushing users from the user feature clusters according to the user similarity weight scores;
determining a first dish list with a first dish basic characteristic according to historical behavior data and a push general menu; the first dish basic feature is the same dish basic feature of the target pushing user and similar users thereof;
determining a second dish list with second dish basic characteristics according to the historical behavior data and the push general menu; the second dish basic characteristic is a dish basic characteristic which the target pushing user does not have but the similar user does;
and generating a target recommendation menu corresponding to each target push user according to the first dish list and the second dish list.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
determining user characteristic values of a target pushing user and similar users thereof according to historical behavior data;
acquiring basic characteristic values of dishes of all dishes of the push general menu;
determining a second public intersection feature of the target pushing user and the similar users thereof and the pushing total menu according to the user feature values of the target pushing user and the similar users thereof and the dish basic feature value;
determining a second minimum feature weight ratio according to the feature weight ratio of the dish basic feature value corresponding to the second public intersection feature;
summing the second minimum characteristic weight ratios to generate a first dish similarity weight score of the target pushing user and the similar users thereof;
and sequencing the pushed general menus according to the first dish similarity weight score to generate a first dish list with the first dish basic characteristics.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
deleting a first user characteristic value corresponding to the target push user from a second user characteristic value of the similar user to obtain a third user characteristic value;
determining a third public intersection feature of the similar user and the pushed total menu according to the third user feature value and the dish basic feature value;
determining a third minimum feature weight ratio according to the feature weight ratio of the dish basic feature value corresponding to the third public intersection feature;
summing the third minimum feature weight ratios to generate a second dish similarity weight score of the similar user;
and sequencing the pushed general menus according to the second dish similarity weight score to generate a second dish list with second dish basic characteristics.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
carrying out quantization processing on the user characteristic value to generate a user characteristic attribute table;
determining the characteristic weight ratio of each user characteristic value of the corresponding user according to the user characteristic attribute table;
and determining the association degree of each user characteristic value according to the user characteristic attribute table and the characteristic weight ratio.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
displaying a target recommendation menu;
acquiring operation behavior data aiming at a target recommendation menu;
and adjusting the dish characteristic weight of the target recommendation menu according to the operation behavior data.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, performs the steps of:
acquiring historical behavior data of a user of the cooking equipment, and generating a corresponding user characteristic value according to the historical behavior data of the user;
dividing users according to the relevance of each user characteristic value to generate user characteristic clusters;
acquiring grouped user characteristics corresponding to each user characteristic group;
acquiring a dish basic characteristic value generated according to dish attribute information;
and determining the dishes to be recommended according to the basic characteristic values of the dishes and the characteristics of the grouped users.
In one embodiment, the computer program when executed by the processor further performs the steps of:
carrying out user feature similarity quantization processing on the user grouping features to generate user similarity weight scores of the user feature groupings;
and determining the dishes to be recommended according to the similarity weight scores and the basic characteristic values of the dishes.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring user characteristic values of any two users in the user characteristic cluster;
determining a first public intersection feature of any two selected users according to the user feature values of the any two selected users;
determining a first minimum feature weight ratio according to the feature weight ratio of the user feature value corresponding to the first public intersection feature;
and summing the first minimum feature weight ratios to generate a user similarity weight score of each user in the user feature cluster.
In one embodiment, the computer program when executed by the processor further performs the steps of:
generating a push general menu according to the dishes to be recommended;
acquiring historical behavior data of a target pushing user;
and determining a target recommendation menu corresponding to each target push user according to the historical behavior data and the push total menu.
In one embodiment, the computer program when executed by the processor further performs the steps of:
extracting similar users corresponding to the target pushing users from the user feature clusters according to the user similarity weight scores;
determining a first dish list with a first dish basic characteristic according to historical behavior data and a push general menu; the first dish basic feature is the same dish basic feature of the target pushing user and similar users thereof;
determining a second dish list with second dish basic characteristics according to the historical behavior data and the push general menu; the second dish basic characteristic is a dish basic characteristic which the target pushing user does not have but the similar user does;
and generating a target recommendation menu corresponding to each target push user according to the first dish list and the second dish list.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining user characteristic values of a target pushing user and similar users thereof according to historical behavior data;
acquiring basic characteristic values of dishes of all dishes of the push general menu;
determining a second public intersection feature of the target pushing user and similar users thereof and a pushing total menu according to the user feature values of the target pushing user and similar users thereof and the dish basic feature value;
determining a second minimum feature weight ratio according to the feature weight ratio of the dish basic feature value corresponding to the second public intersection feature;
summing the second minimum characteristic weight ratios to generate a first dish similarity weight score of the target pushing user and the similar users thereof;
and sequencing the pushed general menus according to the first dish similarity weight score to generate a first dish list with the first dish basic characteristics.
In one embodiment, the computer program when executed by the processor further performs the steps of:
deleting a first user characteristic value corresponding to the target push user from a second user characteristic value of the similar user to obtain a third user characteristic value;
determining a third public intersection feature of the similar user and the pushed total menu according to the third user feature value and the dish basic feature value;
determining a third minimum feature weight ratio according to the feature weight ratio of the dish basic feature value corresponding to the third public intersection feature;
summing the third minimum feature weight ratios to generate a second dish similarity weight score of the similar user;
and sequencing the pushed general menu according to the second dish similarity weight to generate a second dish list with second dish basic characteristics.
In one embodiment, the computer program when executed by the processor further performs the steps of:
carrying out quantization processing on the user characteristic value to generate a user characteristic attribute table;
determining the characteristic weight ratio of each user characteristic value of the corresponding user according to the user characteristic attribute table;
and determining the association degree of each user characteristic value according to the user characteristic attribute table and the characteristic weight ratio.
In one embodiment, the computer program when executed by the processor further performs the steps of:
displaying a target recommendation menu;
acquiring operation behavior data aiming at a target recommendation menu;
and adjusting the dish characteristic weight of the target recommendation menu according to the operation behavior data.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A dish pushing method based on a cooking device is characterized by comprising the following steps:
acquiring historical user behavior data of the cooking equipment, and generating a corresponding user characteristic value according to the historical user behavior data;
carrying out user division according to the relevance of each user characteristic value to generate user characteristic clusters;
obtaining the grouped user characteristics corresponding to each user characteristic group;
acquiring a dish basic characteristic value generated according to dish attribute information;
carrying out user feature similarity quantization processing on the user grouping features to generate user similarity weight scores of the user feature groupings;
determining dishes to be recommended according to the similarity weight and the dish basic characteristic value;
the performing user feature similarity quantization processing on the user clustering features to generate user similarity weight scores of the user feature clusters includes:
acquiring user characteristic values of any two users in the user characteristic cluster; determining a first public intersection feature of any two selected users according to the user feature values of any two selected users; determining a first minimum feature weight ratio according to the feature weight ratio of the user feature value corresponding to the first public intersection feature; and summing the first minimum feature weight ratios to generate a user similarity weight score of each user in the user feature cluster.
2. The method of claim 1, further comprising:
generating a push general menu according to the dishes to be recommended;
acquiring historical behavior data of a target pushing user;
and determining a target recommendation menu corresponding to each target push user according to the historical behavior data and the push total menu.
3. The method of claim 2, wherein the determining a target recommendation menu corresponding to each target push user according to the historical behavior data and the push general menu comprises:
according to the user similarity weight score, extracting similar users corresponding to the target pushing user from the user feature cluster;
determining a first dish list with a first dish basic characteristic according to the historical behavior data and the push total menu; the first dish basic feature is the same dish basic feature of the target pushing user and similar users thereof;
determining a second dish list with second dish basic characteristics according to the historical behavior data and the push total menu; the second dish basic feature is a dish basic feature which the target pushing user does not have and the similar user does;
and generating a target recommendation menu corresponding to each target push user according to the first dish list and the second dish list.
4. The method of claim 3, wherein determining a first menu list having a first menu base characteristic based on the historical behavior data and the push global menu comprises:
determining user characteristic values of the target pushing user and similar users thereof according to the historical behavior data;
acquiring dish basic characteristic values of all dishes of the push general menu;
determining a second intersection feature of the target pushing user and similar users thereof and the pushing general menu according to the user feature values of the target pushing user and similar users thereof and the dish basic feature value;
determining a second minimum feature weight ratio according to the feature weight ratio of the dish basic feature value corresponding to the second public intersection feature;
summing the second minimum feature weight ratios to generate a first dish similarity weight score of the target pushing user and similar users thereof;
and sequencing the push general menu according to the first dish similarity weight to generate a first dish list with first dish basic characteristics.
5. The method of claim 4, wherein determining a second menu list having a second menu base characteristic based on the historical behavior data and the push summary menu comprises:
deleting the first user characteristic value corresponding to the target push user from the second user characteristic value of the similar user to obtain a third user characteristic value;
determining a third public intersection feature of the similar user and the push total menu according to the third user feature value and the dish basic feature value;
determining a third minimum feature weight ratio according to the feature weight ratio of the dish basic feature value corresponding to the third public intersection feature;
summing the third minimum feature weight ratios to generate a second dish similarity weight score of the similar user;
and sorting the push general menu according to the second dish similarity weight to generate a second dish list with second dish basic characteristics.
6. The method according to claim 1 or 2, wherein before the performing user partition according to the association degree of each user feature value to generate a user feature cluster, the method further comprises:
carrying out quantization processing on the user characteristic value to generate a user characteristic attribute table;
determining the characteristic weight ratio of each user characteristic value of the corresponding user according to the user characteristic attribute table;
and determining the association degree of each user characteristic value according to the user characteristic attribute table and the characteristic weight ratio.
7. The method of claim 2, further comprising:
displaying the target recommendation menu;
acquiring operation behavior data aiming at the target recommendation menu;
and adjusting the dish characteristic weight of the target recommendation menu according to the operation behavior data.
8. A dish pushing device based on a cooking device, characterized in that the device comprises:
the user characteristic value generating module is used for acquiring historical user behavior data of the cooking equipment and generating a corresponding user characteristic value according to the historical user behavior data;
the user characteristic clustering generation module is used for carrying out user division according to the relevance of each user characteristic value to generate user characteristic clustering;
a group user characteristic obtaining module for obtaining the group user characteristics corresponding to each user characteristic group;
the dish basic characteristic value generating module is used for acquiring dish basic characteristic values generated according to the dish attribute information;
the dish to be recommended determining module is used for carrying out user feature similarity quantization processing on the user grouping features to generate user similarity weight scores of the user feature groupings; determining dishes to be recommended according to the similarity weight and the dish basic characteristic value;
the dish to be recommended determining module is further configured to: acquiring user characteristic values of any two users in the user characteristic cluster; determining a first public intersection feature of any two selected users according to the user feature values of any two selected users; determining a first minimum feature weight ratio according to the feature weight ratio of the user feature value corresponding to the first public intersection feature; and summing the first minimum feature weight ratios to generate a user similarity weight score of each user in the user feature cluster.
9. A cooking device comprises a cooking device body, a display screen, a memory and a processor, wherein the display screen, the memory and the processor are arranged on the cooking device body; the memory stores a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011259689.1A CN112328845B (en) | 2020-11-12 | 2020-11-12 | Dish pushing method and device based on cooking equipment and cooking equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011259689.1A CN112328845B (en) | 2020-11-12 | 2020-11-12 | Dish pushing method and device based on cooking equipment and cooking equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112328845A CN112328845A (en) | 2021-02-05 |
| CN112328845B true CN112328845B (en) | 2022-09-16 |
Family
ID=74317481
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011259689.1A Active CN112328845B (en) | 2020-11-12 | 2020-11-12 | Dish pushing method and device based on cooking equipment and cooking equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112328845B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111414396A (en) * | 2020-05-07 | 2020-07-14 | 珠海格力电器股份有限公司 | Dish pushing method and device, storage medium and cooking equipment |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107092609B (en) * | 2016-05-10 | 2021-04-02 | 口碑控股有限公司 | Information pushing method and device |
| CN107862542A (en) * | 2017-09-28 | 2018-03-30 | 北京三快在线科技有限公司 | A kind of vegetable recommends method and apparatus |
| CN109102332A (en) * | 2018-08-06 | 2018-12-28 | 北京小度信息科技有限公司 | A kind of method, apparatus and electronic equipment of data processing |
| CN109461490A (en) * | 2018-09-13 | 2019-03-12 | 北京辰森世纪科技股份有限公司 | The processing method of healthy diet data, apparatus and system |
-
2020
- 2020-11-12 CN CN202011259689.1A patent/CN112328845B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111414396A (en) * | 2020-05-07 | 2020-07-14 | 珠海格力电器股份有限公司 | Dish pushing method and device, storage medium and cooking equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112328845A (en) | 2021-02-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105531691B (en) | Method and apparatus for the privacy correlation correlation between mark data value | |
| CN105468598A (en) | Friend recommendation method and device | |
| JP6291145B2 (en) | Information processing apparatus, information processing method, program, and storage medium | |
| US20180033074A1 (en) | System, method, and recording medium for recipe and shopping list recommendation | |
| CN109872796A (en) | A kind of menu recommended method and device | |
| CN110472016B (en) | Article recommendation method and device, electronic equipment and storage medium | |
| CN110472153B (en) | Menu recommendation method, system, equipment and storage medium | |
| US10055496B2 (en) | Cuisine search device, cuisine search method, program, and computer-readable storage medium | |
| CN105681089B (en) | Networks congestion control clustering method, device and terminal | |
| US9201968B2 (en) | System and method for finding mood-dependent top selling/rated lists | |
| CN112328845B (en) | Dish pushing method and device based on cooking equipment and cooking equipment | |
| JP7351782B2 (en) | Information processing system, information processing device, information processing method and program | |
| WO2021056829A1 (en) | Menu comparison method and apparatus, and computer storage medium | |
| CN113158036A (en) | Automatic recipe recommendation method, device, terminal and storage medium | |
| JP6682690B1 (en) | Information processing system, information processing apparatus, information processing method, and program | |
| KR20200118584A (en) | Food recommendation system | |
| WO2019119053A1 (en) | Generating a user-specific user interface | |
| CN111414396A (en) | Dish pushing method and device, storage medium and cooking equipment | |
| JP6279823B1 (en) | Information processing apparatus, information processing method, and program | |
| CN110580636A (en) | Key setting method based on user behavior analysis, intelligent electric appliance and server | |
| CN112417272A (en) | Menu recommendation method and device, electronic equipment and storage medium | |
| EP3639713A1 (en) | Automatic main ingredient extraction from food recipe | |
| CN110688561A (en) | Method and device for determining dietary preference and computer storage medium | |
| CN110580945A (en) | Menu recommendation method and device and storage medium | |
| JP7240936B2 (en) | Server, server control method and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |