WO2021056829A1

WO2021056829A1 - Menu comparison method and apparatus, and computer storage medium

Info

Publication number: WO2021056829A1
Application number: PCT/CN2019/123808
Authority: WO
Inventors: 陈琦; 连秋壮; 刘华芳
Original assignee: 广东美的白色家电技术创新中心有限公司; 美的集团股份有限公司
Priority date: 2019-09-29
Filing date: 2019-12-06
Publication date: 2021-04-01
Also published as: CN110826595A

Abstract

A menu comparison method, a menu comparison apparatus and a computer storage medium. The method comprises the following steps: acquiring first menu information and second menu information, wherein the first menu information comprises first category information and first ratio information of a plurality of first food materials, and the second menu information comprises second category information and second ratio information of a plurality of second food materials (S110); comparing the first category information with the second category information to acquire a food material similarity between each first food material and each second food material (S120); and performing weighted summation on the food material similarities according to the first ratio information and the second ratio information to obtain a menu similarity between a first menu and a second menu (S130). By means of the above mode, the first menu information and the second menu information can be compared more rationally, and the similarity between the first menu information and the second menu information is accurately obtained.

Description

Recipe comparison method, device and computer storage medium

This application claims the priority of the Chinese patent application filed on September 29, 2019 with the application number 2019109367771 and the invention title "Method, Device and Computer Storage Medium for Recipe Comparison", which is fully incorporated into this application by reference.

【Technical Field】

This application relates to the field of smart home technology, in particular to a recipe comparison method, recipe comparison device and computer storage medium.

【Background technique】

At present, traditional home appliances are gradually connecting to the field of Internet of Things, and there are more and more home appliances including kitchen appliances online. How to provide users with more value-added services based on networked online data is a new technical field that the home appliance industry needs to involve.

In the personalized recommendation of recipes, it is often necessary to calculate the similarity of different recipes. However, the current calculation of the similarity of recipes often simply calculates the degree of overlap of the number of ingredients between the two recipes, which cannot accurately reflect the similarity between the two recipes.

[Summary of the invention]

This application provides a recipe comparison method, a recipe comparison device, and a computer storage medium, so as to solve the problem of inaccurate calculation of the similarity between recipes in related technologies.

In order to solve the above technical problems, this application provides a recipe comparison method. The method includes: acquiring first recipe information and second recipe information, the first recipe information includes first category information and first proportion information of a plurality of first ingredients, and the second recipe information includes second recipe information of a plurality of second ingredients. The category information and the second proportion information; compare the first category information and the second category information to obtain the similarity of each first ingredient and each second ingredient; according to the first proportion information and the second proportion information, The weighted summation of the similarity of the ingredients is performed to obtain the similarity of the first recipe and the second recipe.

In order to solve the above technical problems, this application provides a recipe comparison device. The device includes a processor and a memory; a computer program is stored in the memory, and the processor is used to execute the computer program to implement the steps of the recipe comparison method.

In order to solve the above technical problems, this application provides a computer storage medium. The computer storage medium stores a computer program, and the computer program is executed to implement the steps of the recipe comparison method.

This application obtains the similarity of each first ingredient and each second ingredient by comparing the first category information and the second category information. And according to the first proportion information and the second proportion information, the weighted summation of the similarity of the ingredients is performed to obtain the similarity between the first recipe and the second recipe, which can compare the first recipe information and the second recipe more reasonably. Information, accurately get the similarity between the two.

【Explanation of the drawings】

Fig. 1 is a schematic structural diagram of a first embodiment of a recipe comparison method provided by the present application;

2 is a schematic flow chart of the method for calculating the similarity between the first recipe and the second recipe provided by the present application;

3 is a schematic flowchart of a second embodiment of the recipe comparison method provided by the present application;

4 is a schematic structural diagram of an embodiment of a recipe comparison device provided by the present application;

Fig. 5 is a schematic structural diagram of an embodiment of a computer storage medium provided by the present application.

【detailed description】

In order to enable those skilled in the art to better understand the technical solutions of the present application, the recipe comparison method, recipe comparison device and computer storage medium provided by the present application will be described in further detail below in conjunction with the accompanying drawings and specific implementations.

Please refer to FIG. 1, which is a schematic flowchart of a first embodiment of the recipe comparison method provided by the present application. This embodiment includes the following steps:

S110: Acquire first recipe information and second recipe information, where the first recipe information includes first category information and first proportion information of a plurality of first ingredients, and the second recipe information includes second category information of a plurality of second ingredients And the second proportion information.

In this embodiment, the recipe is associated with the recipe information, for example, the first recipe is associated with the first recipe information, and the second recipe is associated with the second recipe information. The first recipe information and the second recipe information may be retrieved from the local database of the recipe comparison device, or retrieved from the Internet.

The first recipe is, for example, a recipe that the user likes. There may be many ways to obtain the first recipe. For example, the first recipe may be acquired according to the user's historical browsing records, favorite records, or recipes input/selected by the user. Specifically, the longer and more times the user browses a certain recipe, the more likely it is that the user is interested in the recipe, and then it can be determined that the recipe is the first recipe. Or when the user browses the recipe, click the favorite or favorite on the recipe page, or the user can input or select the favorite recipe through voice or device screen.

For another example, the first recipe may also be obtained from a favorite recipe publicly shared by the user on a social platform.

For another example, the first recipe may also be obtained through household appliances. Specifically, the household electrical appliances are, for example, kitchen household electrical appliances such as microwave ovens, ovens, range hoods, or refrigerators. Home appliances, for example, are equipped with cameras, which can be used to capture images of the cooking ingredients in the home appliances. For example, microwave ovens and ovens can capture the ingredients being heated, or the range hood can capture the ingredients cooked in the stove, or the refrigerator can capture the removed ingredients. . After the home appliance collects the image of the food material, it analyzes and recognizes the food material in the image to obtain the corresponding recipe. Further, the frequency or number of times a recipe corresponding to the food material is cooked can also be analyzed. The higher the frequency or the number of times a recipe is cooked, the more the user likes the recipe. When the frequency or number of times a recipe is cooked exceeds a set threshold, for example, a recipe that has been cooked more than 5 times in a month, or the frequency or number of times a recipe is cooked is ranked higher among all recipes cooked by the user, such as sorting In the first 3 recipes, it can be determined that this recipe is the first recipe. It is understandable that the number of cooking times in the above-mentioned month exceeds 5 times, and the ranking is in the top 3 are just examples. The threshold or the specific numerical value of the ranking can be adjusted according to the actual cooking situation of the user, which is not limited in this application.

The second recipe is another recipe different from the first recipe, and the second recipe may be obtained by searching keywords related to the first recipe in a local database or the Internet. Therefore, it can be understood that the number of second recipes in this embodiment may be multiple.

Generally, the recipe information includes information such as ingredients, weight of each ingredient, cuisine, taste, cooking method, etc. In addition, in the recipe information in this embodiment, the ingredients specifically include category information and proportion information of the ingredients.

The category information may be, for example, the food material code of the food material obtained from the food material code table. The food code table can be designed by the service party itself, or it can be an existing food code table, such as "Chinese Food Coding Table", "Chinese Food Composition Table", etc. It is understandable that, in order to ensure the consistency of the food material coding, the first category information and the second category information are obtained from the same food material coding table. The food code in the food code table includes multiple levels of code, each level limits the range where the food is located, and the next level continues to narrow the restricted range on the basis of the limit range of the previous level, step by step, until the last level of code points A specific ingredient. Therefore, the category information of the food material is unique and can uniquely represent a certain food material. For example, the food code of pakchoi in the "Chinese Food Ingredients List" is 04-5-107, where 04 on the first level represents vegetables and products, and 04-5 on the second level represents tender stems, leaves, and cauliflowers. Go to the third level 04-5-107, which means Chinese cabbage. On the other hand, using the ingredient code to represent the ingredient can avoid the problem of one-to-one correspondence between the two recipes due to the different expressions of the same ingredient. For example, ginger shred and ginger slices belong to ginger, and the ingredient codes of ginger shreds and ginger slices are The same, so the ingredient code can express the same ingredient more accurately.

The proportion information is, for example, the percentage of the weight of each ingredient in the total weight of all ingredients in the recipe. Compared with the weight of the ingredients in the recipe information, the proportion information of the ingredients can more intuitively reflect the priority of a certain ingredient in the recipe, making different recipes more comparable.

S120: Compare the first category information with the second category information, and obtain the similarity of each first ingredient and each second ingredient.

It can be seen from the description in S110 that the first category information may be the food material code of the first food material, and the second category information may be the food material code of the second food material. From the highest level to the lowest level in the food material compilation, the scope of meaning represented by each level of code is reduced once. Comparing each layer code of the first category information with each layer code of the second category information, the similarity of each first food material and each second food material can be obtained.

Specifically, the number of first coding layers of the first category information and the number of second coding layers of the second category information are determined. Compare each layer code of the first category information with each layer code of the second category information to determine the number of layers with the same code. Calculate the square root value of the product of the first coded layer number and the second coded layer number, and calculate the quotient of the same coded layer number and the square root value as the food similarity. The formula is as follows:

It should be noted that the number of layers with the same encoding refers to the same number of layers starting from the highest level of the food encoding until the layer with different encodings. Specifically, from the highest level to the lowest level of the food material coding, the same layer codes of the first category information and the second category information are sequentially compared until the comparison results are different, and the number of layers above the different levels is determined to be the same level as the comparison result. number. Of course, the coding is still the same until the lowest level of the food coding of the first category information or the second category information is compared, and it is determined that the comparison result is the first coding layer number or the second coding layer number as the same coding layer number.

For example, the ingredient code of pork belly in the "Chinese Food Coding List" is 08-1-1-007, and the ingredient code of tenderloin is 08-1-1-006, so the number of layers with the same code for pork belly and tenderloin is 3. The ingredient code of carrots is 04-1-1-011. The top-level code of tenderloin is different from the top-level code of carrots. Even if the second and third levels are the same, the code of tenderloin and carrot is still the same. 0.

Taking the calculation of the similarity of the ingredients of pork belly and tenderloin as an example, the number of layers with the same encoding of pork belly and tenderloin is 3, the number of encoding layers for pork belly and tenderloin is 4, and the number of encoding layers for tenderloin is 4. The similarity of the ingredients of pork belly and tenderloin is:

S130: Perform a weighted summation on the similarity of the ingredients according to the first proportion information and the second proportion information to obtain the recipe similarity of the first recipe and the second recipe.

In this embodiment, the similarity between the first recipe and the second recipe is calculated through two dimensions of food similarity and proportion information.

There are many ways to calculate the similarity between the first recipe and the second recipe. For example, the product of the first proportion information and the second proportion information can be used as the weight, and the similarity of the ingredients can be weighted and summed to obtain the similarity of the recipe. degree. It should be noted that the product of the first proportion information and the second proportion information is used as the weight, and the similarity of the ingredients is weighted, which means that the first ingredient and the second proportion information corresponding to the first proportion information are corresponding to each other. The ingredients similarity between the second ingredients is weighted. The weighted values of the similarity of each first ingredient and each of the second ingredients are added to obtain the similarity of the recipes of the first recipe and the second recipe. The formula is as follows:

Among them, Sim _AB and Sim _BA both represent the recipe similarity between the first recipe and the second recipe,

Indicates the similarity between the first ingredient and the second ingredient. i is a positive integer and represents the number of ingredients in the first recipe information. For example, if the first recipe information contains 5 first ingredients, then i=5. This is just an example. The specific value of i is based on the actual number of ingredients in the recipe. Certainly, it is not limited in this embodiment. A _i represents a first information specific recipe ingredients a first, each of the first food material A _i has a corresponding first accounting information p _Ai. j is a positive integer, indicating the number of ingredients in the second recipe information. B _j represents a specific first ingredient in the first recipe information, and each second ingredient B _j has corresponding second proportion information p _Bj .

For another example, the similarity between the first recipe and the second recipe can be calculated by the following method. Please refer to FIG. 2. FIG. 2 is a schematic flow chart of the recipe similarity calculation method for the first recipe and the second recipe provided in the present application. The calculation process of this method is as follows:

S131: Compare the first category information and the second category information, determine a common ingredient among the plurality of first ingredients and the plurality of second ingredients, and obtain the similarity of each first ingredient and each second ingredient.

Each piece of first category information is compared with each piece of second category information to determine a common ingredient among the plurality of first ingredients and the plurality of second ingredients. At the same time, the similarity of each first ingredient and each second ingredient is obtained.

S132: Compare the first proportion information and the second proportion information of the common ingredients to determine the common proportion of the common ingredients.

After obtaining the common ingredients, compare the first proportion information and the second proportion information of each common ingredient to determine the common proportion of the common ingredients.

For example, if the proportion of pork in the first recipe information is 0.3, and the proportion of pork in the second recipe information is 0.5, then the common proportion of pork is 0.3.

S133: Remove the common proportion in the first proportion information and the second proportion information of the common ingredient, and perform a weighted summation on the similarity of the ingredients according to the first proportion information and the second proportion information after the removal process.

The common proportion of the common ingredients in the first recipe information and the common proportion of the common ingredients in the second recipe information are respectively removed to obtain the first recipe information and the second recipe information after the removal process. The first recipe information after the removal process includes the first category information of the multiple first ingredients and the first proportion information after the removal process, and the second recipe information after the removal process includes the second category information of the multiple second ingredients and Remove the processed second proportion information. According to the first proportion information after the removal process and the second proportion information after the removal process, a weighted summation is performed on the similarity of the food ingredients. Similarly, weighting the similarity of ingredients means using the first proportion information after the removal process and the second proportion information after the removal process, and the first proportion information after the removal process and the second proportion information after the removal process are used. The food similarity between the first food material and the second food material corresponding to the proportion information is weighted. The weighted values of the similarity of each first ingredient and each second ingredient are added together to obtain the recipe similarity of the first recipe after the removal process and the second recipe after the removal process. The formula is as follows:

Among them, A^ represents the first recipe information after the removal process, B^ represents the second recipe information after the removal process, p _A^ (p _A^ may be 0, so p _{A^ is} greater than or equal to 0) represents the removal process The first proportion information, p _B^ (p _B^ may be 0, so p _{B^ is} greater than or equal to 0) indicates the second proportion information after the removal process, and Sim _A^B^ indicates the first recipe information after the removal process Recipe similarity with the second recipe information after removal processing.

S134: Taking the product of the first proportion information and the second proportion information after the removal process as the weight value, weighted summation of the similarity of the ingredients, and adds the sum of the common proportions to obtain the similarity of the recipe.

The recipe similarity between the first recipe information after the removal processing and the second recipe information after the removal processing is added to the sum of the common proportions to obtain the recipe similarity. The formula is as follows:

Among them, p _cm represents the common proportion of the m-th common ingredient.

Adding the common proportions separately is equivalent to increasing the weight of the common ingredients, which can increase the recipe similarity between the first recipe and the second recipe to a certain extent. In other words, the greater the weight of the same ingredients or ingredients with higher similarity in the recipe, the higher the similarity of the recipe, which can improve the accuracy of the recommended recipe.

In this embodiment, by comparing the first category information and the second category information, the similarity of each first ingredient and each second ingredient is obtained. And according to the first proportion information and the second proportion information, the weighted summation of the similarity of the ingredients is performed to obtain the similarity between the first recipe and the second recipe, which can compare the first recipe information and the second recipe more reasonably. Information, accurately get the similarity between the two.

In order to describe the technical solution of the present application more clearly and accurately, the following takes the calculation of the recipe similarity between the small farmer's fried pork and the fish-flavored pork as an example for description, but the present application is not limited to this.

Obtain the ingredient composition, ingredient code, and weight percentage of each ingredient from the recipe ingredient database:

The composition of the ingredients and their proportions of the farmer’s fried pork is: pork belly 70%, ginger 7%, garlic 3%, and green pepper 20%. The code of the ingredients is: pork belly 08-1-1-007, ginger 04-4-9-001, garlic 04-4-1-001, green pepper 04-3-1-003;

The ingredient composition of Yuxiang Pork Shredded and its proportion information are: carrot 20%, tenderloin 41%, fungus 2.7%, bamboo shoot 13.7%, ginger 7%, green onion 1.4%, garlic 6%, and green pepper 8.2%. The ingredients code is: carrot 04-1-1-011, tenderloin 08-1-1-006, fungus 05-1-0-014, bamboo shoots 04-5-2-006, ginger 04-4-9-001 , Green onion 04-4-2-001, garlic 04-4-1-001, green pepper 04-3-1-003.

Comparing the ingredients of the farmhouse fried pork and the shredded pork with fish flavor, we get the common ingredients: ginger, garlic and green pepper. Further obtain the common proportion of common ingredients: the proportion of ginger in the farmer’s small fried pork and fish-flavored pork is 7%, which is removed from the respective table of ingredients. Green peppers account for 20% of the farm’s small fried pork, and green peppers account for 8.2% of fish-flavored shredded pork. The smaller proportion is taken as the common proportion of 8.2%. By analogy, traversing the ingredients of the farmer's fried pork and fish-flavored shredded pork, we obtained the following common proportions: 7% of ginger, 3% of garlic, and 8.2% of green pepper.

Remove the common proportion of common ingredients in the original recipes of farmer's fried pork and Yuxiang pork, and obtain the processed farmer's fried pork ingredients and their proportions: 70% of pork belly and 11.8% of green pepper; the ingredients of the processed Yuxiang pork are removed And the proportion: carrot 20%, tenderloin 41%, fungus 2.7%, bamboo shoot 13.7%, green onion 1.4%, garlic 3%.

According to the formula in S120, the similarity between the ingredients of the farmer's fried pork and the ingredients of the fish-flavored pork is calculated. The specific calculation process will not be repeated here, and the results are as follows:

sim _{pork belly-carrot} = 0; sim _{pork belly-tenderloin} = 0.75; sim _{pork belly-fungus} = 0; sim _{pork belly-small bamboo shoots} = 0; sim _{pork belly-fungus} = 0; sim _{pork belly-small bamboo shoots} = 0; sim _{pork belly-green onion} = 0; sim _{pork belly-garlic} = 0; sim _{green pepper-carrot} = 0.25; sim _{green pepper-tenderloin} = 0; sim _{green pepper-fungus} = 0; sim _{green pepper-small bamboo shoots} = 0.25; sim _{green pepper-green onion} = 0.25; sim _{green pepper-garlic =} =0.25.

Calculate the similarity of the recipes of the farmer's fried pork and the fish-flavored pork. The recipe similarity of the farmer’s fried pork and the fish-flavored pork is to take the product of the proportion of the ingredients of the farmer’s fried pork and the fish-flavored pork after the removal process is taken as the weight, and the corresponding ingredients are weighted and summed, and added The sum of the common proportion and the common proportion of the farmer’s fried pork and the fish-flavored pork, the recipe similarity of the farmer’s fried pork and the fish-flavored pork is obtained:

Please refer to FIG. 3, which is a schematic flowchart of a second embodiment of the recipe comparison method provided by the present application. This embodiment is based on the first embodiment of the recipe comparison method, so the same steps will not be repeated here. This embodiment includes the following steps:

S310: Acquire first recipe information and second recipe information, where the first recipe information includes first category information and first proportion information of a plurality of first ingredients, and the second recipe information includes second category information of a plurality of second ingredients And the second proportion information.

S320: Compare the information of the first category with the information of the second category, and obtain the similarity of each first ingredient and each second ingredient.

S330: Perform a weighted summation on the similarity of the ingredients according to the first proportion information and the second proportion information to obtain the recipe similarity of the first recipe and the second recipe.

S340: Push the second recipe information whose recipe similarity with the first recipe information is greater than or equal to a threshold.

After the recipe similarity between the first recipe and the second recipe is calculated, if the recipe similarity is greater than or equal to the threshold, the second recipe is pushed to the user for the user to consult and select. The above threshold may be set between 60% and 100%, such as 70%, 80%, 85%, or 90%.

When there are multiple second recipes with a recipe similarity that is greater than the threshold value, the multiple second recipes may be pushed in priority order according to the similarity of the recipes. The higher the similarity of the recipes, the higher the priority of the push. Prioritize the second recipes with high priority to users, reducing the trouble that may be caused to users by recommending multiple second recipes at the same time.

Further, after recommending a second recipe with a recipe similarity greater than a threshold to the user, monitor whether the user views the second recipe in time. If the user has not viewed the second recipe after a preset time, the user can be reminded to read the second recipe through a voice prompt. menu. Of course, the reason why the user did not view the second recipe may also be that he is not interested in the recipe. Then, it can also be set to hide the recipe if the user does not view the second recipe for more than a preset time.

In this embodiment, after the recipe similarity between the first recipe and the second recipe is calculated, the second recipe with the recipe similarity greater than the threshold is pushed to the user, so that the user can obtain other recipes that are similar to their favorite recipes, which can satisfy The personalized needs of users improve the user experience. In addition, prioritizing according to the degree of similarity can reduce the confusion that may be caused to the user by recommending multiple second recipes at the same time.

The above recipe comparison method is implemented by a recipe comparison device. Therefore, this application also provides a recipe comparison device. Please refer to FIG. 4. FIG. 4 is a schematic structural diagram of an embodiment of the recipe comparison device provided by the application. The recipe comparison device 100 of this embodiment may be Household appliances, such as range hoods, stoves, or refrigerators, can also be mobile terminals, such as smart phones, tablet computers, and wearable devices. The recipe comparison device 100 includes a display screen 11, a processor 12, and a memory 13, which are connected to each other. The recipe comparison device 100 of this embodiment can implement the above-mentioned recipe comparison method. Wherein, the display screen 11 is used to display recipe information to the user, a computer program is stored in the memory 13, and the processor 12 is used to execute the computer program to implement the above recipe comparison method. Specifically, the processor 12 is used to calculate the similarity of each first ingredient and each of the second ingredients, and calculate the similarity between the first recipe and the multiple second recipes.

Wherein, the processor 12 may be an integrated circuit chip with signal processing capability. The processor 12 may also be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component . The general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.

For the method of the foregoing embodiment, it can exist in the form of a computer program. Therefore, this application proposes a computer storage medium. Please refer to FIG. 5. FIG. 5 is a schematic structural diagram of an embodiment of the computer storage medium provided by the present application. The computer storage medium 200 of this embodiment stores a computer program 21, which can be executed to implement the method in the foregoing embodiment.

The computer storage medium 200 in this embodiment may be a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disk that can store program instructions. Or, it may also be a server storing the program instructions, and the server may send the stored program instructions to other devices to run, or it may run the stored program instructions by itself.

In the several embodiments provided in this application, it should be understood that the disclosed method and device can be implemented in other ways. For example, the device implementation described above is only illustrative, for example, the division of modules or units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components can be combined or It can be integrated into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of this embodiment.

In addition, the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , Including several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor execute all or part of the steps of the methods in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks and other media that can store program codes. .

The above are only implementations of this application, and do not limit the scope of this application. Any equivalent structure or equivalent process transformation made using the content of the description and drawings of this application, or directly or indirectly applied to other related technologies In the same way, all fields are included in the scope of patent protection of this application.

Claims

A method for comparing recipes, characterized in that the method comprises:

Acquire first recipe information and second recipe information, where the first recipe information includes first category information and first proportion information of a plurality of first ingredients, and the second recipe information includes second recipe information of a plurality of second ingredients. Category information and second proportion information;

Comparing the first category information and the second category information to obtain the similarity of each of the first food material and each of the second food material;

According to the first proportion information and the second proportion information, a weighted summation of the similarity of the ingredients is performed to obtain the similarity of the recipes of the first recipe and the second recipe.
The method according to claim 1, wherein the comparing the first category information and the second category information to obtain the similarity of each of the first food material and each of the second food material includes:

Compare the first category information and the second category information, determine a common ingredient among a plurality of the first ingredients and a plurality of the second ingredients, and obtain each of the first ingredients and each of the first ingredients 2. The similarity of the ingredients of the ingredients;

The performing a weighted summation on the similarity of the ingredients according to the first proportion information and the second proportion information includes:

Comparing the first proportion information and the second proportion information of the common ingredient to determine the common proportion of the common ingredient;

Removing the common proportion of the common ingredient in the first proportion information and the second proportion information;

Perform a weighted summation on the similarity of the ingredients according to the first proportion information and the second proportion information after the removal process.
The method according to claim 2, wherein the weighted summation of the similarity of the food ingredients according to the first proportion information and the second proportion information after the removal process includes:

The product of the first proportion information and the second proportion information after the removal processing is used as a weight, and the similarity of the ingredients is weighted and summed, and the sum of the common proportion is added to obtain the Recipe similarity.
The method according to claim 1, wherein the first category information and the second category information are derived from the same food material code, and the food material code includes a multi-layer code;

The comparing the first category information and the second category information to obtain the similarity of each of the first food material and each of the second food material includes:

The code of each layer of the first category information is compared with the code of each layer of the second category information to obtain the similarity of each of the first food material and each of the second food material.
The method according to claim 4, said comparing each layer of code of said first category information with each layer of code of said second category information to obtain each of said first ingredients and each of said second ingredients. The similarity of the ingredients, including:

Determining the number of first coding layers of the first category information and the number of second coding layers of the second category information;

Comparing each layer code of the first category information with each layer code of the second category information to determine the number of layers with the same code;

Calculate the square root value of the product of the first coded layer number and the second coded layer number, and calculate the quotient of the same coded layer number and the square root value as the food similarity.
According to the method of claim 5, in the multi-layer code, from the highest level to the lowest level, the meaning range of each level of code is reduced in sequence;

The comparing each layer code of the first category information with each layer code of the second category information to determine the number of layers with the same code includes:

From the highest level to the lowest level, sequentially comparing the same layer codes of the first category information and the second category information until the comparison result is different;

It is determined that the comparison result is that the number of layers above different levels is the number of layers with the same coding.
The method according to claim 1, wherein the weighted summation of the similarity of the ingredients is performed on the basis of the first share information and the second share information to obtain the first recipe and the second recipe. Recipe similarity of recipes, including:

The product of the first proportion information and the second proportion information is used as a weight, and a weighted summation is performed on the similarity of the ingredients to obtain the similarity of the recipe.
The method according to claim 1, further comprising: pushing second recipe information whose recipe similarity with the first recipe information is greater than or equal to a threshold.
A recipe comparison device, wherein the recipe comparison device includes a processor and a memory; a computer program is stored in the memory, and the processor is used to execute the computer program to implement any of claims 1-8. One of the steps of the described method.
A computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed to implement the steps of the method according to any one of claims 1-8.