Menu recommendation method, menu recommendation device and readable storage medium

Abstract

The invention provides a menu recommendation method, a menu recommendation device and a readable storage medium, and the method comprises the steps: obtaining making condition information used for a cooking process; acquiring first demand information of a user; generating a recommendation list according to the production condition information and the first demand information; wherein the making condition information comprises at least one of cooking equipment type information, food material type information and food material remaining amount information used in the cooking process.

Description

Technical Field

[0001] The present invention relates to the technical field of household appliances, and in particular to a recipe recommendation method, a recipe recommendation device and a readable storage medium. Background Art

[0002] In the related art, during the recipe recommendation process, recipes can be recommended based on the demand information input by the user. However, while the recommended recipes meet the user's needs, the user is often unable to implement the selected recipes, which affects the user experience. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art.

[0004] To this end, a first aspect of the present invention provides a recipe recommendation method.

[0005] A second aspect of the present invention provides a recipe recommendation device.

[0006] A third aspect of the present invention provides a recipe recommendation device.

[0007] A fourth aspect of the present invention provides a readable storage medium.

[0008] A first aspect of the present invention provides a recipe recommendation method, comprising: obtaining production condition information used in a cooking process; obtaining a user's first demand information; generating a recommendation list based on the production condition information and the first demand information; wherein the production condition information includes at least one of cooking equipment type information, ingredient type information and ingredient remaining amount information used in the cooking process.

[0009] The recipe recommendation method provided by the present invention can be used to recommend recipes corresponding to the user's needs to meet the user's cooking needs. Specifically, the user can input the cooking needs through the smart device, and then the smart device can recommend a recipe list to the user according to the user's needs, so that the user can select the required recipe from the recipe list.

[0010] Specifically, first, obtain the production condition information used in the cooking process. The production condition information may include information on the types of cooking equipment used in the cooking process. For example, the types of cooking equipment included in the user's kitchen, such as rice cookers, ovens, microwave ovens, or electric ovens. Furthermore, the production condition information may also include the types of ingredients, that is, the different ingredients available to the user. For example, the different types of ingredients in the refrigerator in the user's kitchen, such as chicken, pork, fish, or different types of vegetables. Furthermore, the production condition information may also include information on the remaining amount of ingredients, that is, the remaining amount of ingredients available to the user. For example, the remaining amount of chicken or the remaining amount of various vegetables in the refrigerator in the user's kitchen.

[0011] By obtaining the preparation condition information, it is possible to select recipes from the recipe list according to the user's preparation condition information during the recipe recommendation process, thereby ensuring that the recipe selected by the user can be achieved under the current preparation conditions, thereby improving the accuracy of recipe recommendations.

[0012] Among them, the production condition information can be obtained in the intelligent ecological environment established by the user's home electrical appliances. Specifically, the intelligent ecological environment refers to the intelligent ecological environment that will be formed on the basis of the user's use of a set of intelligent connection devices, and all intelligent device information can be obtained from the unified control center. Each intelligent device can transmit device information, device operation status information, and various other information in the user's home to the control terminal through the local area network, such as temperature, humidity, air quality, and information such as the ingredients contained in the refrigerator and the shelf life, so as to facilitate the unified management of the user's home environment. In this way, before recommending a recipe, the production condition information during the user's cooking process can be determined from the intelligent ecological environment.

[0013] Furthermore, the first demand information of the user is obtained. The first demand information of the user is the user's demand for the dishes to be prepared. Specifically, it may include the type of dishes, such as cold dishes, fried foods, baked foods, etc. It may also include the taste of the dishes, such as sweetness, spicy taste, etc. The first demand information may also include basic information of the user, such as the user's age, gender, etc.

[0014] Furthermore, after obtaining the production condition information for the cooking process and the first requirement information input by the user, a recommendation list can be generated based on the production condition information and the first requirement information. In this way, the user can select the food he wants to make in the generated recommendation list. By generating a recommendation list based on the production condition information and the first requirement information input by the user, on the one hand, the user does not need to perform manual screening, and the automatic generation of the recommendation list of recipes is realized, thereby improving the efficiency of recipe recommendations. On the other hand, while meeting the needs of the user, combined with the production condition information of the user's kitchen, it can ensure that the recipes in the recommendation list obtained by the user can be implemented, thereby ensuring the accuracy of the recipe recommendation and improving the user experience.

[0015] The recipe recommendation method provided by the present invention first obtains the production condition information used in the cooking process during the process of recommending recipes, thereby ensuring that the recipes recommended to the user can be implemented in the user's kitchen environment. The production condition information is further combined with the first demand information input by the user to generate a recommendation list. This can not only realize the automatic generation of the recommendation list, but also improve the efficiency of recipe recommendation. It can also make the recommendation list meet the needs of the user while combining the production condition information of the user's kitchen to ensure that the recipes in the recommendation list obtained by the user can be implemented, thereby ensuring the accuracy of the recipe recommendation and improving the user experience.

[0016] In addition, the recipe recommendation method in the above technical solution provided by the present invention may also have the following additional technical features:

[0017] In the above technical solution, optionally, the recommendation list includes a first recommendation list, and the recommendation list is generated according to the production condition information and the first requirement information, including: generating a recipe list according to the production condition information; determining a first keyword according to the first requirement information; generating the first recommendation list according to the first keyword and the recipe list.

[0018] In this technical solution, in the process of generating a recommendation list according to the production condition information and the user's first requirement information, first, a recipe list is generated according to the production condition information. That is, the recipes that meet the user's current production conditions are first screened out, and the recipes displayed in the recipe list are all achievable.

[0019] Then, the first keyword is determined according to the first demand information input by the user, that is, the keyword that can represent the actual demand of the user is extracted from the first demand information input by the user.

[0020] Furthermore, based on the first keyword, the previously generated recipe list is filtered to obtain a first recommendation list, which is a recipe list recommended to the user based on the preparation condition information and the user's first demand information, so that the user can select the desired recipe in the recommendation list.

[0021] In some technical solutions, optionally, a first recommendation list is generated based on the first keyword and the recipe list, including: determining a second keyword in the first keyword that conflicts with the production condition information; when the second keyword is obtained, obtaining confirmation information input by the user; when the confirmation information is obtained, generating a first recommendation list based on the first keyword and the recipe list; when the confirmation information is not obtained, deleting the second keyword in the first keyword; and generating a first recommendation list based on the remaining first keywords and the recipe list.

[0022] In this technical solution, after determining the corresponding first keyword according to the first demand information input by the user, it is first determined whether there is a second keyword in the first keyword that conflicts with the production condition information.

[0023] Furthermore, when the second keyword is obtained, the user's confirmation information needs to be obtained. The confirmation information is used to ask the user whether to continue to generate a recommendation list based on the keyword as the user's need. Specifically, when the user's confirmation information is obtained, it indicates that the user still needs to use the keyword as the user's need for recipe recommendation. At this time, no other operations are required, and the first recommendation list is directly generated based on the first keyword and the recipe list.

[0024] If the user's confirmation information is not obtained, it means that the user no longer needs to use the keyword as the demand information to generate the recommendation list. At this time, the second keyword in the first keyword is deleted, that is, the second keyword in the first keyword that conflicts with the production condition information is deleted, and then the first recommendation list is generated based on the remaining first keyword and the recipe list. In this way, it can be ensured that the recipes in the generated first recommendation list can be realized, thereby improving the user experience.

[0025] In some technical solutions, optionally, determining the first keyword according to the first demand information includes: determining the first keyword corresponding to the first demand information from a preset keyword list according to the demand information.

[0026] In this technical solution, in the process of determining the first keyword according to the first demand information input by the user, the first keyword corresponding to the first demand information input by the user can be determined from a preset keyword list.

[0027] By determining the first keyword corresponding to the first demand information input by the user in the preset keyword list, the first keyword can be determined intuitively, thereby improving the efficiency of determining the first keyword.

[0028] In some technical solutions, optionally, determining the first keyword based on the first demand information includes: inputting the first demand information into a pre-trained deep learning algorithm to generate a first keyword corresponding to the first demand information.

[0029] In this technical solution, in the process of determining the first keyword based on the first demand information input by the user, the first demand information input by the user can be directly input into a pre-trained deep learning algorithm, and then the first keyword corresponding to the first demand information is obtained through calculation of the deep learning algorithm.

[0030] Specifically, the deep learning algorithm can be a keyword extraction algorithm or an intent recognition model.

[0031] By inputting the first demand information into a pre-trained deep learning algorithm and determining the first keyword corresponding to the first demand information, the accuracy of determining the first keyword can be improved, thereby ensuring the accuracy of obtaining user needs, and then ensuring that the recipes in the generated first recommendation list are more in line with user needs, thereby improving user experience.

[0032] In some technical solutions, optionally, the recommendation list also includes a second recommendation list. After the first recommendation list is generated according to the first keyword and the recipe list, the recipe recommendation method also includes: obtaining the user's second demand information; upon receiving the second demand information input by the user, determining the third keyword according to the second demand information; generating the second recommendation list according to the third keyword and the recipe list; and stopping obtaining the second demand information when the user determines the target recipe from the first recommendation list.

[0033] In this technical solution, after the first recommendation list is generated according to the first keyword and the production condition information corresponding to the first demand information of the user, the second demand information input by the user can be further obtained.

[0034] That is, when the target recipe required by the user does not exist in the first recommendation list, that is, when the user does not select the target recipe required from the first recommendation list, the user can continue to input the second requirement information, so as to determine the third keyword corresponding to the second requirement information according to the second requirement information input by the user, and then generate the second recommendation list according to the third keyword and the generated recipe list. At this time, the user can select the target recipe required by himself in the second recommendation list.

[0035] By acquiring the user's second demand information, if the recommendation list generated based on the user's first demand information and production condition information does not meet the user's needs, a recommendation list can be further generated based on the user's second demand information and production condition information to ensure that the generated recommendation list contains recipes that meet the user's needs, thereby improving the user experience.

[0036] Accordingly, when the user determines the target recipe from the first recommendation list, there is no need to continue to obtain the user's second requirement information. The recipe recommendation is completed.

[0037] In some technical solutions, optionally, after generating a recommendation list based on the production condition information and the first requirement information, the recommendation method further includes: obtaining the user's historical cooking information; determining the priority of the recipes in the recommendation list based on the historical cooking information; and sorting the recipes in the recommendation list according to priority.

[0038] In this technical solution, after generating a recommendation list based on the production condition information and the user's first demand information, multiple recipes in the recommendation list can also be sorted according to the user's historical cooking information. The user's historical cooking information can reflect the user's cooking preferences, and the multiple recipes in the recommendation list can be further sorted according to the user's preferences, making it easier for the user to view and select.

[0039] Specifically, first, the user's historical cooking information is obtained, wherein the historical cooking information may include the user's historical recipe interaction behaviors, such as which recipes the user has cooked before, and the number of times the user has cooked the recipes.

[0040] Then, based on the user's historical cooking information, the priorities of all recipes in the generated recommendation list are determined, and then all recipes in the recommendation list are sorted according to the priorities for the user to view.

[0041] Furthermore, all the recipes in the recommendation list may be sorted according to other information. For example, the priority of all the recipes in the recommendation list may be determined according to the user's taste preference. Alternatively, the recipe sorting method may be determined according to the similarity of the main ingredients of all the recipes in the recommendation list, for example, recipes with the same or similar main ingredients may be arranged together so that the user can select a recipe based on the main ingredients. Alternatively, the recipe sorting method may be determined according to the similarity of the taste of all the recipes in the recommendation list, for example, recipes with the same or similar taste may be arranged together so that the user can select a recipe based on the main ingredients.

[0042] In some technical solutions, optionally, the priority of recipes in the recommendation list is determined based on the historical cooking information, including: constructing a historical cooking information matrix based on the historical cooking information; inputting the historical cooking information matrix into a preset algorithm to generate the priority of the recipes in the recommendation list.

[0043] In this technical solution, a historical cooking information matrix can be constructed based on the user's historical cooking information, specifically, the user's historical recipe interaction behavior, such as which recipes the user has cooked, and the number of times the user has cooked the recipe. Then the user's historical recipe interaction behavior is constructed into a historical cooking information matrix, and then the historical cooking information matrix is ​​input into a preset algorithm, and the priority of the recipes in the recommendation list is determined through the calculation of the preset algorithm.

[0044] Specifically, the preset algorithm may be a collaborative filtering algorithm.

[0045] In some technical solutions, optionally, obtaining the user's first demand information includes: obtaining voice information input by the user; converting the voice information into text information; and determining the first demand information based on the text information.

[0046] In this technical solution, the user can interact with the smart device by voice, so that the smart device can determine the user's first demand information according to the voice information input by the user.

[0047] Specifically, first, the voice information input by the user is obtained, then the voice information input by the user is converted into text information, and finally, the user's first demand information is determined based on the text information. Through voice interaction, users can conveniently express their real-time recipe search needs, realizing convenient user recipe search demand interaction.

[0048] According to a second aspect of the present invention, a recipe recommendation device is proposed, comprising: an acquisition unit for acquiring production condition information used for a cooking process; and acquiring a user's first demand information; a generation unit for generating a recommendation list based on the production condition information and the first demand information; wherein the production condition information includes at least one of cooking equipment type information, ingredient type information and ingredient remaining amount information used for the cooking process.

[0049] The recipe recommendation device provided by the present invention first obtains the production condition information used in the cooking process during the process of recommending recipes, thereby ensuring that the recipes recommended to the user can be implemented in the user's kitchen environment. The production condition information is further combined with the first demand information input by the user to generate a recommendation list. This can not only realize the automatic generation of the recommendation list, but also improve the efficiency of recipe recommendation. It can also make the recommendation list meet the needs of the user while combining the production condition information of the user's kitchen to ensure that the recipes in the recommendation list obtained by the user can be implemented, thereby ensuring the accuracy of the recipe recommendation and improving the user experience.

[0050] Furthermore, the generating unit is specifically used to: generate a recipe list according to the production condition information; determine a first keyword according to the first demand information; and generate a first recommendation list according to the first keyword and the recipe list.

[0051] Furthermore, the generation unit is specifically used to: determine the second keyword that conflicts with the production condition information among the first keywords; the acquisition unit is also used to: when the second keyword is acquired, acquire confirmation information input by the user; the generation unit is also specifically used to: when the confirmation information is acquired, generate a first recommendation list based on the first keyword and the recipe list; when the confirmation information is not acquired, delete the second keyword in the first keyword; and generate a first recommendation list based on the remaining first keywords and the recipe list.

[0052] Furthermore, the generating unit is specifically configured to determine, according to the demand information, a first keyword corresponding to the first demand information from a preset keyword list.

[0053] Furthermore, the generating unit is specifically used to input the demand information into a pre-trained deep learning algorithm to generate a first keyword corresponding to the first demand information.

[0054] Furthermore, the acquisition unit is further configured to acquire second demand information of the user; the generation unit is further configured to determine a third keyword based on the second demand information when receiving the second demand information input by the user; and generate a second recommendation list based on the third keyword and the first recommendation list. When the user determines the target recipe from the first recommendation list, the acquisition unit stops acquiring the second demand information.

[0055] Furthermore, after generating the recommendation list according to the preparation condition information and the first requirement information, the acquisition unit is further used to acquire the user's historical cooking information.

[0056] The recipe recommendation device also includes a sorting unit, which is used to determine the priority of the recipes in the recommendation list according to the historical cooking information; and sort the recipes in the recommendation list according to the priority.

[0057] Furthermore, the sorting unit is specifically used to construct a historical cooking information matrix based on the historical cooking information; and input the historical cooking information matrix into a preset algorithm to generate the priority of the recipes in the recommendation list.

[0058] Furthermore, the acquisition unit is specifically used to acquire voice information input by the user; convert the voice information into text information; and determine the first demand information according to the text information.

[0059] According to a third aspect of the present invention, a recipe recommendation device is proposed, comprising: a processor and a memory, the memory storing programs or instructions executable on the processor, and the programs or instructions implementing the steps of the recipe recommendation method provided in the first aspect when executed by the processor.

[0060] The recipe recommendation device provided by the present invention includes a memory and a processor, and also includes a program or instruction stored in the memory. When the program or instruction is executed by the processor, the steps of the recipe recommendation method of the first aspect mentioned above can be implemented. Therefore, the recipe recommendation device has all the beneficial effects of the above-mentioned recipe recommendation method, which will not be repeated here.

[0061] According to a fourth aspect of the present invention, a readable storage medium is provided, on which a program or instruction is stored, and when the program or instruction is executed by a processor, a recipe recommendation method as described in any one of the above technical solutions is implemented.

[0062] The readable storage medium provided by the present invention stores a program or instruction thereon. When the program or instruction is executed by the processor, it can implement a recipe recommendation method as described in any one of the above-mentioned technical solutions. Therefore, the storage medium has all the beneficial effects of the above-mentioned recipe recommendation method, which will not be repeated here.

[0063] Additional aspects and advantages of the present invention will become apparent from the following description or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0065] Figure 1 A schematic diagram showing a process flow of a recipe recommendation method provided according to an embodiment of the present invention is shown;

[0066] Figure 2 A schematic diagram showing a process flow of a recipe recommendation method provided according to another embodiment of the present invention is shown;

[0067] Figure 3 A schematic diagram showing a process flow of a recipe recommendation method provided according to yet another embodiment of the present invention;

[0068] Figure 4 A schematic diagram showing a process flow of a recipe recommendation method provided according to yet another embodiment of the present invention;

[0069] Figure 5 A schematic diagram showing a process flow of a recipe recommendation method provided according to yet another embodiment of the present invention;

[0070] Figure 6 A schematic diagram showing a process flow of a recipe recommendation method provided according to yet another embodiment of the present invention;

[0071] Figure 7 A schematic diagram showing a process flow of a recipe recommendation method provided according to yet another embodiment of the present invention;

[0072] Figure 8 A schematic diagram showing a process flow of a recipe recommendation method provided according to yet another embodiment of the present invention;

[0073] Fig. 9 A flowchart of a recipe recommendation method provided according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0074] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0075] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0076] Refer to the following Figures 1 to 9 The recipe recommendation method, recipe recommendation device and readable storage medium provided according to some embodiments of the present invention are described.

[0077] like Figure 1 As shown, according to one embodiment of the present invention, a recipe recommendation method is proposed, comprising:

[0078] S102, obtaining production condition information for a cooking process;

[0079] S104, obtaining the user's first demand information;

[0080] S106: Generate a recommendation list according to the production condition information and the first requirement information.

[0081] The preparation condition information includes at least one of the type information of cooking equipment used in the cooking process, the type information of ingredients and the remaining amount information of ingredients.

[0082] The recipe recommendation method provided by the present invention can be used to recommend recipes corresponding to the user's needs to meet the user's cooking needs. Specifically, the user can input the cooking needs through the smart device, and then the smart device can recommend a recipe list to the user according to the user's needs, so that the user can select the required recipe from the recipe list.

[0083] Specifically, first, obtain the production condition information used in the cooking process. The production condition information may include information on the types of cooking equipment used in the cooking process. For example, the types of cooking equipment included in the user's kitchen, such as rice cookers, ovens, microwave ovens, or electric ovens. Furthermore, the production condition information may also include the types of ingredients, that is, the different ingredients available to the user. For example, the different types of ingredients in the refrigerator in the user's kitchen, such as chicken, pork, fish, or different types of vegetables. Furthermore, the production condition information may also include information on the remaining amount of ingredients, that is, the remaining amount of ingredients available to the user. For example, the remaining amount of chicken or the remaining amount of various vegetables in the refrigerator in the user's kitchen.

[0084] By obtaining the preparation condition information, it is possible to select recipes from the recipe list according to the user's preparation condition information during the recipe recommendation process, thereby ensuring that the recipe selected by the user can be achieved under the current preparation conditions, thereby improving the accuracy of recipe recommendations.

[0085] Among them, the production condition information can be obtained in the intelligent ecological environment established by the user's home electrical appliances. Specifically, the intelligent ecological environment refers to the intelligent ecological environment that will be formed on the basis of the user's use of a set of intelligent connection devices, and all intelligent device information can be obtained from the unified control center. Each intelligent device can transmit device information, device operation status information, and various other information in the user's home to the control terminal through the local area network, such as temperature, humidity, air quality, and information such as the ingredients contained in the refrigerator and the shelf life, so as to facilitate the unified management of the user's home environment. In this way, before recommending a recipe, the production condition information during the user's cooking process can be determined from the intelligent ecological environment.

[0086] Alternatively, the preparation condition information can also be obtained by receiving active input of existing cooking equipment conditions by the user and regularly updating the food management table to ensure that the system can obtain the cooking preparation condition information.

[0087] Furthermore, the first demand information of the user is obtained. The first demand information of the user is the user's demand for the dishes to be prepared. Specifically, it may include the type of dishes, such as cold dishes, fried foods, baked foods, etc. It may also include the taste of the dishes, such as sweetness, spicy taste, etc. The first demand information may also include basic information of the user, such as the user's age, gender, etc.

[0088] Furthermore, after obtaining the production condition information for the cooking process and the first requirement information input by the user, a recommendation list can be generated based on the production condition information and the first requirement information. In this way, the user can select the food he wants to make in the generated recommendation list. By generating a recommendation list based on the production condition information and the first requirement information input by the user, on the one hand, the user does not need to perform manual screening, and the automatic generation of the recommendation list of recipes is realized, thereby improving the efficiency of recipe recommendations. On the other hand, while meeting the needs of the user, combined with the production condition information of the user's kitchen, it can ensure that the recipes in the recommendation list obtained by the user can be implemented, thereby ensuring the accuracy of the recipe recommendation and improving the user experience.

[0089] The recipe recommendation method provided by the present invention first obtains the production condition information used in the cooking process during the process of recommending recipes, thereby ensuring that the recipes recommended to the user can be implemented in the user's kitchen environment. The production condition information is further combined with the first demand information input by the user to generate a recommendation list. This can not only realize the automatic generation of the recommendation list, but also improve the efficiency of recipe recommendation. It can also make the recommendation list meet the needs of the user while combining the production condition information of the user's kitchen to ensure that the recipes in the recommendation list obtained by the user can be implemented, thereby ensuring the accuracy of the recipe recommendation and improving the user experience.

[0090] According to one embodiment of the present invention, Figure 2 As shown, a recipe recommendation method is proposed, comprising:

[0091] S202, obtaining preparation condition information for a cooking process;

[0092] S204, obtaining the user's first demand information;

[0093] S206, generating a recipe list according to the preparation condition information;

[0094] S208, determining a first keyword according to the first demand information;

[0095] S210: Generate a first recommendation list according to the first keyword and the recipe list.

[0096] In this embodiment, in the process of generating a recommendation list according to the production condition information and the user's first requirement information, first, a recipe list is generated according to the production condition information. That is, the recipes that meet the user's current production conditions are first screened out, and the recipes displayed in the recipe list are all achievable.

[0097] Then, the first keyword is determined according to the first demand information input by the user, that is, the keyword that can represent the actual demand of the user is extracted from the first demand information input by the user.

[0098] For example, the user's first demand information is "What should I eat today because I have a cold? I am in a bad mood and want to eat something sweet, such as a dessert made from strawberries." At this time, the types of keywords can be determined as "common diseases," "mood," "taste," "dishes," and "ingredients" based on the first demand information, and the keywords of the first demand information can be further determined as "cold," "sadness," "sweet," "dessert," and "strawberry."

[0099] Furthermore, based on the first keyword, the previously generated recipe list is filtered to obtain a first recommendation list, which is a recipe list recommended to the user based on the preparation condition information and the user's first demand information, so that the user can select the desired recipe in the recommendation list.

[0100] According to one embodiment of the present invention, Figure 3 As shown, a recipe recommendation method is proposed, comprising:

[0101] S302, obtaining preparation condition information for a cooking process;

[0102] S304, obtaining the user's first demand information;

[0103] S306, generating a recipe list according to the preparation condition information;

[0104] S308, determining a first keyword according to the first demand information;

[0105] S310, determining, from among the first keywords, a second keyword that conflicts with the production condition information;

[0106] S312, when the second keyword is obtained, obtaining confirmation information input by the user;

[0107] S314, when the confirmation information is obtained, generating a first recommendation list according to the first keyword and the recipe list;

[0108] S316, if the confirmation information is not obtained, deleting the second keyword in the first keyword;

[0109] S318: Generate a first recommendation list based on the remaining first keywords and recipe list.

[0110] In this embodiment, after determining the corresponding first keyword according to the first demand information input by the user, it is first determined whether there is a second keyword in the first keyword that conflicts with the production condition information.

[0111] For example, the user's first demand information is "I have a cold today, what should I eat? I am in a bad mood and want to eat something sweet, a dessert made from strawberries." At this time, the types of keywords can be determined as "common symptoms," "mood," "taste," "dish," and "ingredients" according to the first demand information, and the keywords of the first demand information are further determined to be "cold," "sadness," "sweet," "dessert," and "strawberry." However, the ingredient "strawberry" is not found in the production condition information. At this time, it can be determined that "strawberry" in the first keyword is the second keyword that conflicts with the production condition information.

[0112] Furthermore, when the second keyword is obtained, the user's confirmation information needs to be obtained. The confirmation information is used to ask the user whether to continue to generate a recommendation list based on the keyword as the user's need. Specifically, when the user's confirmation information is obtained, it indicates that the user still needs to use the keyword as the user's need for recipe recommendation. At this time, no other operations are required, and the first recommendation list is directly generated based on the first keyword and the recipe list.

[0113] If the user's confirmation information is not obtained, it means that the user no longer needs to use the keyword as the demand information to generate the recommendation list. At this time, the second keyword in the first keyword is deleted, that is, the second keyword in the first keyword that conflicts with the production condition information is deleted, and then the first recommendation list is generated based on the remaining first keyword and the recipe list. In this way, it can be ensured that the recipes in the generated first recommendation list can be realized, thereby improving the user experience.

[0114] According to one embodiment of the present invention, Figure 4 As shown, a recipe recommendation method is proposed, comprising:

[0115] S402, obtaining preparation condition information for a cooking process;

[0116] S404, obtaining the user's first demand information;

[0117] S406, generating a recipe list according to the preparation condition information;

[0118] S408, determining a first keyword corresponding to the first demand information from a preset keyword list according to the demand information;

[0119] S410: Generate a first recommendation list according to the first keyword and the recipe list.

[0120] In this embodiment, in the process of determining the first keyword according to the first demand information input by the user, the first keyword corresponding to the first demand information input by the user may be determined from a preset keyword list.

[0121] Specifically, in the first keyword list, multiple first keywords can be classified according to keyword types, for example, keyword types can include "common symptoms", "mood", "taste", "dishes" and "ingredients". Further, each keyword type can include multiple specific first keywords. For example, in the "taste" type, first keywords such as "sour", "sweet", "spicy" and "salty" can be included.

[0122] By determining the first keyword corresponding to the first demand information input by the user in the preset keyword list, the first keyword can be determined intuitively, thereby improving the efficiency of determining the first keyword.

[0123] According to one embodiment of the present invention, Figure 5 As shown, a recipe recommendation method is proposed, comprising:

[0124] S502, obtaining preparation condition information for a cooking process;

[0125] S504, obtaining the user's first demand information;

[0126] S506, generating a recipe list according to the preparation condition information;

[0127] S508, inputting the first demand information into a pre-trained deep learning algorithm to generate a first keyword corresponding to the first demand information;

[0128] S510: Generate a first recommendation list according to the first keyword and the recipe list.

[0129] In this embodiment, in the process of determining the first keyword based on the first demand information input by the user, the first demand information input by the user can be directly input into a pre-trained deep learning algorithm, and then the first keyword corresponding to the first demand information is obtained through calculation of the deep learning algorithm.

[0130] Specifically, the deep learning algorithm can be a keyword extraction algorithm or an intent recognition model.

[0131] By inputting the first demand information into a pre-trained deep learning algorithm and determining the first keyword corresponding to the first demand information, the accuracy of determining the first keyword can be improved, thereby ensuring the accuracy of obtaining user needs, and then ensuring that the recipes in the generated first recommendation list are more in line with user needs, thereby improving user experience.

[0132] According to one embodiment of the present invention, Figure 6 As shown, a recipe recommendation method is proposed, comprising:

[0133] S602, obtaining preparation condition information for a cooking process;

[0134] S604, obtaining the user's first demand information;

[0135] S606, generating a recipe list according to the preparation condition information;

[0136] S608, determining a first keyword according to the first demand information;

[0137] S610, generating a first recommendation list according to the first keyword and the recipe list;

[0138] S612, obtaining the second demand information of the user;

[0139] S614, upon receiving the second demand information input by the user, determining a third keyword according to the second demand information;

[0140] S616: Generate a second recommendation list based on the third keyword and the recipe list.

[0141] In this embodiment, after the first recommendation list is generated according to the first keyword and the production condition information corresponding to the first demand information of the user, the second demand information input by the user may be further obtained.

[0142] That is, when the target recipe required by the user does not exist in the first recommendation list, that is, when the user does not select the target recipe required from the first recommendation list, the user can continue to input the second requirement information, so as to determine the third keyword corresponding to the second requirement information according to the second requirement information input by the user, and then generate the second recommendation list according to the third keyword and the generated recipe list. At this time, the user can select the target recipe required by himself in the second recommendation list.

[0143] By acquiring the user's second demand information, if the recommendation list generated based on the user's first demand information and production condition information does not meet the user's needs, a recommendation list can be further generated based on the user's second demand information and production condition information to ensure that the generated recommendation list contains recipes that meet the user's needs, thereby improving the user experience.

[0144] Accordingly, when the user determines the target recipe from the first recommendation list, there is no need to continue to obtain the user's second requirement information. The recipe recommendation is completed.

[0145] Furthermore, if Fig. 9 As shown, if the second recommendation list still does not contain the recipe the user needs, the user's third demand information can be obtained, and then a fourth recommendation list can be generated based on the third demand information and the recipe list. In this way, the user's demand information can be obtained in multiple rounds until the generated recommendation list contains the recipe the user needs. There is no need to continue obtaining the user's demand information.

[0146] According to one embodiment of the present invention, Figure 7 As shown, a recipe recommendation method is proposed, comprising:

[0147] S702, obtaining preparation condition information for a cooking process;

[0148] S704, obtaining the user's first demand information;

[0149] S706, generating a recommendation list according to the production condition information and the first requirement information;

[0150] S708, obtaining the user's historical cooking information;

[0151] S710, determining the priority of recipes in the recommendation list according to the historical cooking information;

[0152] S712, sorting the recipes in the recommendation list according to priority.

[0153] In this embodiment, after generating a recommendation list based on the production condition information and the user's first demand information, the multiple recipes in the recommendation list can also be sorted according to the user's historical cooking information. The user's historical cooking information can reflect the user's cooking preferences, and the multiple recipes in the recommendation list can be further sorted according to the user's preferences, making it easier for the user to view and select.

[0154] Specifically, first, the user's historical cooking information is obtained, wherein the historical cooking information may include the user's historical recipe interaction behaviors, such as which recipes the user has cooked before, and the number of times the user has cooked the recipes.

[0155] Then, based on the user's historical cooking information, the priorities of all recipes in the generated recommendation list are determined, and then all recipes in the recommendation list are sorted according to the priorities for the user to view.

[0156] Furthermore, all the recipes in the recommendation list may be sorted according to other information. For example, the priority of all the recipes in the recommendation list may be determined according to the user's taste preference. Alternatively, the recipe sorting method may be determined according to the similarity of the main ingredients of all the recipes in the recommendation list, for example, recipes with the same or similar main ingredients may be arranged together so that the user can select a recipe based on the main ingredients. Alternatively, the recipe sorting method may be determined according to the similarity of the taste of all the recipes in the recommendation list, for example, recipes with the same or similar taste may be arranged together so that the user can select a recipe based on the main ingredients.

[0157] In some embodiments, optionally, determining the priority of recipes in the recommendation list based on historical cooking information includes: constructing a historical cooking information matrix based on the historical cooking information; and inputting the historical cooking information matrix into a preset algorithm to generate the priority of recipes in the recommendation list.

[0158] In this embodiment, a historical cooking information matrix can be constructed based on the user's historical cooking information, specifically, the user's historical recipe interaction behavior, such as which recipes the user has cooked, and the number of times the user has cooked the recipe, etc. Then the user's historical recipe interaction behavior is constructed into a historical cooking information matrix, and then the historical cooking information matrix is ​​input into a preset algorithm, and the priority of the recipes in the recommendation list is determined through calculation by the preset algorithm.

[0159] Specifically, the preset algorithm may be a collaborative filtering algorithm.

[0160] According to one embodiment of the present invention, Figure 8 As shown, a recipe recommendation method is proposed, comprising:

[0161] S802, obtaining preparation condition information for a cooking process;

[0162] S804, obtaining voice information input by the user;

[0163] S806, converting the voice information into text information;

[0164] S808, determining first demand information according to the text information;

[0165] S810: Generate a recommendation list according to the production condition information and the first requirement information.

[0166] In this embodiment, the user can interact with the smart device by voice, so that the smart device can determine the user's first demand information according to the voice information input by the user.

[0167] Specifically, first, the voice information input by the user is obtained, then the voice information input by the user is converted into text information, and finally, the user's first demand information is determined based on the text information. Through voice interaction, users can conveniently express their real-time recipe search needs, realizing convenient user recipe search demand interaction.

[0168] According to a second aspect of the present invention, a recipe recommendation device is proposed, comprising: an acquisition unit for acquiring production condition information used for a cooking process; and acquiring a user's first demand information; a generation unit for generating a recommendation list based on the production condition information and the first demand information; wherein the production condition information includes at least one of cooking equipment type information, ingredient type information and ingredient remaining amount information used for the cooking process.

[0169] The recipe recommendation device provided by the present invention first obtains the production condition information used in the cooking process during the process of recommending recipes, thereby ensuring that the recipes recommended to the user can be implemented in the user's kitchen environment. The production condition information is further combined with the first demand information input by the user to generate a recommendation list. This can not only realize the automatic generation of the recommendation list, but also improve the efficiency of recipe recommendation. It can also make the recommendation list meet the needs of the user while combining the production condition information of the user's kitchen to ensure that the recipes in the recommendation list obtained by the user can be implemented, thereby ensuring the accuracy of the recipe recommendation and improving the user experience.

[0170] Furthermore, the generating unit is specifically used to: generate a recipe list according to the production condition information; determine a first keyword according to the first demand information; and generate a first recommendation list according to the first keyword and the recipe list.

[0171] Furthermore, the generation unit is specifically used to: determine the second keyword that conflicts with the production condition information among the first keywords; the acquisition unit is also used to: when the second keyword is acquired, acquire confirmation information input by the user; the generation unit is also specifically used to: when the confirmation information is acquired, generate a first recommendation list based on the first keyword and the recipe list; when the confirmation information is not acquired, delete the second keyword in the first keyword; and generate a first recommendation list based on the remaining first keywords and the recipe list.

[0172] Furthermore, the generating unit is specifically configured to determine, according to the demand information, a first keyword corresponding to the first demand information from a preset keyword list.

[0173] Furthermore, the generating unit is specifically used to input the demand information into a pre-trained deep learning algorithm to generate a first keyword corresponding to the first demand information.

[0174] Furthermore, the acquisition unit is further configured to acquire second demand information of the user; the generation unit is further configured to determine a third keyword based on the second demand information when receiving the second demand information input by the user; and generate a second recommendation list based on the third keyword and the first recommendation list. When the user determines the target recipe from the first recommendation list, the acquisition unit stops acquiring the second demand information.

[0175] Furthermore, after generating the recommendation list according to the preparation condition information and the first requirement information, the acquisition unit is further used to acquire the user's historical cooking information.

[0176] The recipe recommendation device also includes a sorting unit, which is used to determine the priority of the recipes in the recommendation list according to the historical cooking information; and sort the recipes in the recommendation list according to the priority.

[0177] Furthermore, the sorting unit is specifically used to construct a historical cooking information matrix based on the historical cooking information; and input the historical cooking information matrix into a preset algorithm to generate the priority of the recipes in the recommendation list.

[0178] Furthermore, the acquisition unit is specifically used to acquire voice information input by the user; convert the voice information into text information; and determine the first demand information according to the text information.

[0179] According to a third aspect of the present invention, a recipe recommendation device is proposed, comprising: a processor and a memory, the memory storing programs or instructions executable on the processor, and the programs or instructions implementing the steps of the recipe recommendation method provided in the first aspect when executed by the processor.

[0180] The recipe recommendation device provided by the present invention includes a memory and a processor, and also includes a program or instruction stored in the memory. When the program or instruction is executed by the processor, the steps of the recipe recommendation method of the first aspect mentioned above can be implemented. Therefore, the recipe recommendation device has all the beneficial effects of the above-mentioned recipe recommendation method, which will not be repeated here.

[0181] According to a fourth aspect of the present invention, a readable storage medium is provided, on which a program or instruction is stored, and when the program or instruction is executed by a processor, a recipe recommendation method as described in any one of the above technical solutions is implemented.

[0182] The readable storage medium provided by the present invention stores a program or instruction thereon. When the program or instruction is executed by the processor, it can implement a recipe recommendation method as described in any one of the above-mentioned technical solutions. Therefore, the storage medium has all the beneficial effects of the above-mentioned recipe recommendation method, which will not be repeated here.

[0183] In the description of the present invention, the term "plurality" refers to two or more than two. Unless otherwise clearly defined, the orientation or positional relationship indicated by the terms "upper" and "lower" is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention. The terms "connection", "installation", "fixation", etc. should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be directly connected or indirectly connected through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0184] In the description of this specification, the description of the terms "one embodiment", "some embodiments", "specific embodiments", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0185] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A recipe recommendation method, characterized in that: include: Obtaining information about preparation conditions used in the cooking process; Obtain the user's first demand information; generating a recommendation list according to the production condition information and the first requirement information; The preparation condition information includes at least one of information on the type of cooking equipment used in the cooking process, information on the type of ingredients, and information on the remaining amount of ingredients.

2. The recipe recommendation method according to claim 1, characterized in that: The recommendation list includes a first recommendation list, and generating the recommendation list according to the production condition information and the first requirement information includes: Generate a recipe list according to the production condition information; Determining a first keyword according to the first demand information; The first recommendation list is generated according to the first keyword and the recipe list.

3. The recipe recommendation method according to claim 2, characterized in that: The step of generating the first recommendation list according to the first keyword and the recipe list includes: Determining, among the first keywords, a second keyword that conflicts with the production condition information; When the second keyword is obtained, obtaining confirmation information input by the user; When the confirmation information is obtained, generating the first recommendation list according to the first keyword and the recipe list; If the confirmation information is not obtained, deleting the second keyword from the first keyword; The first recommendation list is generated according to the remaining first keywords and the recipe list.

4. The recipe recommendation method according to claim 2, characterized in that: The determining the first keyword according to the first demand information includes: According to the demand information, the first keyword corresponding to the first demand information is determined from a preset keyword list.

5. The recipe recommendation method according to claim 2, characterized in that: The determining the first keyword according to the first demand information includes: The first demand information is input into a pre-trained deep learning algorithm to generate the first keyword corresponding to the first demand information.

6. The recipe recommendation method according to claim 2, characterized in that: The recommendation list further includes a second recommendation list. After the first recommendation list is generated according to the first keyword and the recipe list, the recipe recommendation method further includes: Acquiring second demand information of the user; In case of receiving the second demand information input by the user, determining a third keyword according to the second demand information; generating the second recommendation list according to the third keyword and the recipe list; When the user determines the target recipe from the first recommendation list, the acquisition of the second demand information is stopped.

7. The recipe recommendation method according to any one of claims 1 to 6, characterized in that: The generating a recommendation list according to the production condition information and the first requirement information, the recommendation method further comprises: Acquire historical cooking information of the user; Determining the priority of the recipes in the recommendation list according to the historical cooking information; The recipes in the recommendation list are sorted according to the priority.

8. The recipe recommendation method according to claim 7, characterized in that: Determining the priority of the recipes in the recommendation list according to the historical cooking information includes: Constructing a historical cooking information matrix according to the historical cooking information; The historical cooking information matrix is ​​input into a preset algorithm to generate the priority of the recipes in the recommendation list.

9. The recipe recommendation method according to any one of claims 1 to 6, characterized in that: The obtaining of the user's first demand information includes: Acquiring voice information input by the user; Converting the voice information into text information; The first requirement information is determined according to the text information.

10. A recipe recommendation device, characterized in that: include: An acquisition unit, used for acquiring preparation condition information for a cooking process; as well as Obtain the user's first demand information; A generating unit, configured to generate a recommendation list according to the production condition information and the first requirement information; The preparation condition information includes at least one of information on the type of cooking equipment used in the cooking process, information on the type of ingredients, and information on the remaining amount of ingredients.

11. A recipe recommendation device, characterized in that: include: A processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the recipe recommendation method as described in any one of claims 1 to 9 are implemented.

12. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the recipe recommendation method according to any one of claims 1 to 9 are implemented.

Images