Method for generating food recommendation list, refrigerator, and computer-readable storage medium

Abstract

The present invention discloses a method for generating an ingredient recommendation list, a refrigerator, and a computer-readable storage medium. The method includes the following steps: obtaining the most recent n historical shopping information, aggregating the ingredient information of the n historical shopping information, and generating ingredient summary information; calculating the ingredient recommendation coefficient kj based on the weight of the number of times the ingredient appears in the n historical shopping information and the weight of the time when the ingredient appears; and sorting each element in the shopping summary information by the size of kj to generate an ingredient recommendation list. By calculating the recommendation coefficient for each ingredient in the historical shopping information, the recommendation coefficient is adjusted based on the number of times the corresponding ingredient appears in the historical shopping information and the time of appearance. Ingredients with more appearances and closer appearance times are assigned a larger recommendation coefficient. Different ingredients are sorted by the recommendation coefficient to generate a recommendation list, making the refrigerator more intelligent and providing a better user experience.

Description

Technical Field

[0001] The present invention relates to a method for generating a food recommendation list, and in particular to a refrigerator and a computer-readable storage medium involving the method. Background Art

[0002] As living standards continue to improve and technology advances, users are increasingly demanding smarter home appliances, seeking better, more convenient human-computer interaction, and more intelligent algorithms. For example, refrigerators are a common household appliance used to keep food and other items at a constant low temperature. Today, users demand more than just better, more practical, more economical, and more convenient refrigerators. They also want more intelligent features and refrigerators that effectively enhance the user experience.

[0003] Today's smart refrigerators have Internet access, allowing users to choose and purchase ingredients, and the refrigerator can also recommend diet recipes. However, how the recipes are recommended depends on the ingredients purchased by the customer. The ingredients purchased by different users may also vary greatly. How to recommend a shopping list that meets the needs of each customer is the difficulty in realizing the intelligent improvement of refrigerators. The method of generating a recommended list of ingredients that meets customer needs is more in line with the needs of smart homes. Summary of the Invention

[0004] In order to solve the above-mentioned problems in the prior art, an object of the present invention is to provide a method for generating a food recommendation list, a refrigerator and a computer-readable storage medium.

[0005] To achieve the above-mentioned object of the invention, one embodiment of the present invention provides a method for generating a food recommendation list, comprising the steps of:

[0006] Get the most recent n shopping history information, where each shopping history information is Ai = {a1, a2…aj}, where i represents the i-th shopping history, i∈[1,n], and aj represents the food information. The larger the value of n, the closer the shopping time is to the current one.

[0007] Aggregate the food information of the n-times historical shopping information A1, A2…An to generate food summary information B = {a1, a2…aj…am};

[0008] Calculate the recommendation coefficient kj of ingredient aj by combining the weight of the number of times ingredient aj appears in the n times of historical shopping information and the weight of the time when ingredient aj appears;

[0009] Generate shopping summary information C = {k1a1, k2a2…kjaj…kmam};

[0010] Sort each element in the shopping summary information C by the size of kj to generate a recommended ingredient list.

[0011] As a further improvement of the present invention, the step of "calculating the recommendation coefficient kj of ingredient aj by combining the weight of the number of times ingredient aj appears in the n times of historical shopping information and the weight of the time when ingredient aj appears" includes:

[0012] Calculate the recommendation coefficient kj of ingredient aj, in,

[0013] As a further improvement of the present invention, the step of "sorting each element in the shopping recommendation list B by the size of kj to generate a recommended ingredient list" includes:

[0014] Sort each element in the shopping recommendation list B from large to small according to the size of kj to generate a food recommendation list.

[0015] As a further improvement of the present invention, the step of "sorting each element in the shopping recommendation list B from large to small according to the size of kj to generate a recommended ingredient list" includes:

[0016] When m is less than or equal to x, sort each element in the shopping recommendation list B from large to small according to the size of kj to generate a recommended ingredient list;

[0017] When m is greater than x, each element in the shopping recommendation list B is sorted from large to small according to the size of kj, and the first x elements are taken to generate a food recommendation list.

[0018] As a further improvement of the present invention, the step of "sorting each element in the shopping summary information C by the size of kj to generate a recommended ingredient list" includes:

[0019] When m is greater than x, take the first x elements in {k1a1, k2a2…kjaj…kmam} as the undetermined set D, D = {k1a1, k2a2…kxax};

[0020] Compare kx+1, kx+1…kx+y…km in turn to see if they are greater than all elements in {k1,k2…kx}. If kx+y is greater than any element kz in {k1,k2…kx}, replace kzaz in the undetermined set D with kx+yax+y.

[0021] All the food information in the set D after the comparison is completed is used as the food recommendation list.

[0022] To achieve one of the above-mentioned objectives, an embodiment of the present invention provides a refrigerator, comprising a storage module and a processing module. The storage module stores a computer program executable on the processing module. The processing module obtains the most recent n shopping history information stored in the storage module. Each shopping history information is represented by Ai = {a1, a2…aj}, where i represents the i-th shopping history, i∈[1,n], aj represents food information, and a larger value of n indicates a closer shopping time.

[0023] The processing module aggregates the food information of the n-times historical shopping information A1, A2...An to generate food summary information B = {a1, a2...aj...am};

[0024] The processing module calculates the recommendation coefficient kj of the ingredient aj by combining the weight of the number of times the ingredient aj appears in the n times of the historical shopping information and the weight of the time when the ingredient aj appears;

[0025] The processing module generates shopping summary information C = {k1a1, k2a2...kjaj...kmam};

[0026] The processing module sorts each element in the shopping summary information C according to the size of kj to generate a recommended food list.

[0027] As a further improvement of the present invention, the processing module is based on the formula Calculate the recommendation coefficient kj of ingredient aj, where

[0028] As a further improvement of the present invention, when m is less than or equal to x, the processing module sorts each element in the shopping recommendation list B from large to small according to the size of kj to generate a recommended ingredient list;

[0029] When m is greater than x, the processing module sorts each element in the shopping recommendation list B from large to small according to the size of kj, and takes the first x elements to generate a food recommendation list.

[0030] As a further improvement of the present invention, when m is greater than x, the processing module takes the first x elements in {k1a1, k2a2…kjaj…kmam} as the undetermined set D, D={k1a1, k2a2…kxax};

[0031] The processing module sequentially compares kx+1, kx+1…kx+y…km to see if they are greater than all elements in {k1, k2…kx}. If kx+y is greater than any element kz in {k1, k2…kx}, kzaz in the pending set D is replaced with kx+yax+y.

[0032] The processing module uses all the food information in the set D after the comparison as the food recommendation list.

[0033] To achieve one of the above-mentioned objects of the invention, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps in the above-mentioned method for generating a recommended food list when executed by a processing module.

[0034] Compared with the prior art, the present invention has the following beneficial effects: by calculating the recommendation coefficient for each ingredient in the historical shopping information, the recommendation coefficient is adjusted based on the number of times the corresponding ingredient appears in the historical shopping information and the time of appearance. The more times an ingredient appears and the closer it appears, the greater the recommendation coefficient is assigned to the ingredient. Different ingredients are sorted according to the recommendation coefficient to generate a recommendation list, making the refrigerator more intelligent and the user experience better. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 1 is a flow chart of a method for generating a food recommendation list according to an embodiment of the present invention;

[0036] Figure 2 is a schematic diagram of a control module according to an embodiment of the present invention;

[0037] Among them, 1. refrigerator; 11. processing module; 12. storage module; 13. communication bus. DETAILED DESCRIPTION

[0038] The present invention will be described in detail below with reference to the specific embodiments shown in the accompanying drawings. However, these embodiments do not limit the present invention, and any structural, methodological, or functional changes made by those skilled in the art based on these embodiments are all within the scope of protection of the present invention.

[0039] An embodiment of the present invention provides a method for generating a recommended food list, a refrigerator, and a computer-readable storage medium, which implement the recommendation of a personalized food shopping list based on user habits, facilitate the user's grocery shopping and diet to better meet their needs, and meet the needs of smart refrigerators and smart homes.

[0040] The method for generating a food recommendation list is applied to a refrigerator 1, and the refrigerator 1 recommends food that a user needs to purchase, including the following steps:

[0041] Get the most recent n shopping history information, where each shopping history information is Ai = {a1, a2…aj}, where i represents the i-th shopping history, i∈[1,n], and aj represents the food information. The larger the value of n, the closer the shopping time is to the current one.

[0042] Aggregate the food information of the n-times historical shopping information A1, A2…An to generate food summary information B = {a1, a2…aj…am};

[0043] Calculate the recommendation coefficient kj of ingredient aj by combining the weight of the number of times ingredient aj appears in the n times of historical shopping information and the weight of the time when ingredient aj appears;

[0044] Generate shopping summary information C = {k1a1, k2a2…kjaj…kmam};

[0045] Sort each element in the shopping summary information C by the size of kj to generate a recommended ingredient list.

[0046] Ingredients that appear more frequently or more recently are given a higher recommendation coefficient, giving them priority in recommendations, meeting the needs of each customer. The value of n can be set by the system or the user.

[0047] Furthermore, the step of "calculating the recommendation coefficient kj of ingredient aj based on the weight of the number of times ingredient aj appears in the n times of historical shopping information and the weight of the time when ingredient aj appears" includes:

[0048] Calculate the recommendation coefficient kj of ingredient aj, in,

[0049] This function expresses the following meaning in two aspects:

[0050] On the one hand, when calculating each kj, we take into account whether the ingredient appears from the first purchase to the nth purchase. If the ingredient does not appear, The value of is 0. When accumulating, the i-th accumulation adds less of this value relative to other ingredients, and its weight is reduced. If this ingredient appears for the i-th time, the value becomes That is, the weight of this appearance is accumulated and reflected in the final kj. This function reflects the weight of the number of times the ingredient aj appears in the n times of historical shopping information.

[0051] On the other hand, when calculating each kj, if the first occurrence occurs, the value of the first occurrence accumulated to the final kj is If it occurs for the 10th time, the accumulated value becomes Obviously, the value accumulated in kj for the 10th appearance is greater than the value accumulated for the first appearance, especially when it appears for the nth time, the value accumulated in kj is 1. That is to say, the closer the time is to the most recent appearance, the larger the value accumulated in kj. This function reflects the weight of the time when ingredient aj appears.

[0052] To more intuitively illustrate the calculation principle of the recommendation coefficient kj, let's use a simple example. Assume that the user's first shopping history is A1 = {apple, banana}, i.e., a1 = apple and a2 = banana. The second shopping history is A2 = {apple, orange}, and the third shopping history is A3 = {orange, banana}. The generated ingredient summary is B = {apple, banana, orange}, corresponding to a1 = apple, a2 = banana, and a3 = orange, respectively.

[0053] Generate shopping summary information C = {k1 apple, k2 banana, k3 orange};

[0054] At this time, k1 represents Apple’s recommendation coefficient.

[0055] K2 represents the recommendation coefficient of banana.

[0056] K3 represents the recommendation coefficient of orange.

[0057] Comparing the above recommendation coefficients k1, k2 and k3, we can conclude that k3>k2>k1, that is, the recommendation list generated at this time is {orange, banana, apple}.

[0058] The recommendation result shows the operating logic of the method for generating the food recommendation list. Although the three fruits appear twice in the three historical purchase records, oranges appear the two most recent times, so they need to be recommended first. The recommendation coefficient k3 of oranges is the largest. Apples appear the first and second times, and bananas appear the first and third times. Therefore, the number of times bananas appear most recently is greater than the number of times apples appear. Therefore, the recommendation coefficient k2 of bananas is second, and apples are last.

[0059] When the user has used refrigerator 1 for a long time, there may be a lot of historical purchase information. In order to avoid unnecessary calculations for purchase information that is too old, a suitable value can be selected (of course, if the value of n is too large, the value of historical purchase information that is too old will be reflected in the final kj calculation very small. Here it does not mean that a large n will affect the calculation result of kj, but it is just that the accumulated value is too small. For example, when n is 1000, even if it appears 10 times in the first 10 times, it is not as large as the value accumulated in kj if it appears once in the most recent 10 times). That is, only the most recent n shopping times are considered, and the shopping preferences of appropriate historical time can be combined to achieve more real-time shopping list recommendations.

[0060] Furthermore, the step of “sorting each element in the shopping recommendation list B by the size of kj to generate a recommended ingredient list” includes:

[0061] Each element in the shopping recommendation list B is sorted from largest to smallest according to the value of kj to generate a recommended ingredient list. The higher the ranking of the ingredients in the recommended ingredient list, the greater the recommendation coefficient. The specific sorting algorithm can adopt methods such as bubble algorithm, insertion sort, merge sort, etc., so that the higher the ranking, the higher the recommendation priority.

[0062] Furthermore, the step of "sorting each element in the shopping recommendation list B from large to small according to the size of kj to generate a recommended ingredient list" includes:

[0063] When m is less than or equal to x, sort each element in the shopping recommendation list B from large to small according to the size of kj to generate a recommended ingredient list;

[0064] When m is greater than x, each element in the shopping recommendation list B is sorted from large to small according to the size of kj, and the first x elements are taken to generate a food recommendation list.

[0065] When the value of n is large, or the content of each purchase by the user is very different, the value of m may become very large, but the user does not need an overly long list of recommended ingredients. Therefore, a maximum length x of the recommended list content is set. That is, when m>x, only the first x ingredients are recommended for the user to choose.

[0066] Furthermore, the step of "sorting each element in the shopping summary information C by the size of kj to generate a recommended ingredient list" includes:

[0067] When m is greater than x, take the first x elements in {k1a1, k2a2…kjaj…kmam} as the undetermined set D, D = {k1a1, k2a2…kxax};

[0068] Compare kx+1, kx+1…kx+y…km in turn to see if they are greater than all elements in {k1,k2…kx}. If kx+y is greater than any element kz in {k1,k2…kx}, replace kzaz in the undetermined set D with kx+yax+y.

[0069] All the food information in the set D after the comparison is completed is used as the food recommendation list.

[0070] Similar to the above, to prevent the recommended ingredient list from being too long, a maximum length x is set for the recommended ingredient list. However, if all ingredients are included in the final sort, this will affect sorting efficiency. This is because when the recommendation coefficient rank is outside the range of x, its value is not actually important. Therefore, ignoring the size of the first x elements and only comparing from x+1 will speed up the calculation.

[0071] The refrigerator 1 of this embodiment includes a storage module 12 and a processing module 11. The storage module 12 stores a computer program that can be run on the processing module 11. The processing module 11 obtains the most recent n historical shopping information stored in the storage module 12. The historical shopping information for each time is Ai = {a1, a2…aj}, where i represents the i-th historical shopping, i∈[1,n], aj represents the food information, and the larger the value of n, the closer the shopping time is to the current time.

[0072] The processing module 11 aggregates the food information of the n-times historical shopping information A1, A2...An to generate food summary information B = {a1, a2...aj...am};

[0073] The processing module 11 calculates the recommendation coefficient kj of the ingredient aj by combining the weight of the number of times the ingredient aj appears in the n times of the historical shopping information and the weight of the time when the ingredient aj appears;

[0074] The processing module 11 generates shopping summary information C = {k1a1, k2a2...kjaj...kmam};

[0075] The processing module 11 sorts each element in the shopping summary information C according to the size of kj to generate a food recommendation list.

[0076] Furthermore, the processing module 11 is based on the formula Calculate the recommendation coefficient kj of ingredient aj, where

[0077] Furthermore, when m is less than or equal to x, the processing module 11 sorts each element in the shopping recommendation list B from large to small according to the size of kj to generate a recommended food list;

[0078] When m is greater than x, the processing module 11 sorts each element in the shopping recommendation list B from large to small according to the size of kj, and takes the first x elements to generate a food recommendation list.

[0079] Furthermore, when m is greater than x, the processing module 11 takes the first x elements in {k1a1, k2a2…kjaj…kmam} as the undetermined set D, D={k1a1, k2a2…kxax};

[0080] The processing module 11 sequentially compares kx+1, kx+1…kx+y…km to see if they are greater than all elements in {k1, k2…kx}. If kx+y is greater than any element kz in {k1, k2…kx}, kzaz in the pending set D is replaced with kx+yax+y.

[0081] The processing module 11 uses all the food information in the set D after comparison as the food recommendation list.

[0082] In addition, the refrigerator 1 may further include a communication bus 13, which is used to establish a connection between the processing module 11 and the storage module 12. The communication bus 13 may include a path to transmit information between the above-mentioned electrical components.

[0083] The processing modules 11 of the present application can be concentrated in one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0084] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium and includes a number of instructions for causing a computer system (which can be a personal computer, server, or network system, etc.) or a processing module (processor) to execute some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program code.

[0085] In addition, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by the processing module 11, any one of the steps in the above-mentioned method for generating a recommended food list can be implemented, that is, any one of the steps in the technical solutions of the above-mentioned method for generating a recommended food list can be implemented.

[0086] Compared with the prior art, this embodiment has the following beneficial effects:

[0087] By calculating the recommendation coefficient for each ingredient in the historical shopping information, the recommendation coefficient is adjusted based on the number of times the corresponding ingredient appears in the historical shopping information and the time of appearance. The more times an ingredient appears and the closer it appears, the greater the recommendation coefficient is given. Different ingredients are sorted according to the recommendation coefficient and a recommendation list is generated, making the refrigerator more intelligent and the user experience better.

[0088] It should be understood that although this specification is described in terms of implementation methods, not every implementation method contains only one independent technical solution. This narrative method of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each implementation method can also be appropriately combined to form other implementation methods that can be understood by those skilled in the art.

[0089] The series of detailed descriptions listed above are only specific descriptions of feasible implementation methods of the present invention. They are not intended to limit the scope of protection of the present invention. Any equivalent implementation methods or changes that do not deviate from the technical spirit of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for generating a food recommendation list, characterized in that: Including steps: Get the most recent n shopping history information, where each shopping history information is Ai={a1,a2…aj}, where i represents the i-th shopping history, i∈[1,n], and aj represents the food information. The larger the value of n, the closer the shopping time is to the current one. Aggregate the food information of the n-time historical shopping information A1, A2...An to generate food summary information B = {a1, a2...aj...am}; Combined with the weight of the number of times the ingredient aj appears in the n times of the historical shopping information and the weight of the time when the ingredient aj appears, the recommendation coefficient kj of the ingredient aj is calculated. The calculation formula of the recommendation coefficient kj is: ,in, ; Generate shopping summary information C={k1a1,k2a2…kjaj…kmam}; Sort each element in the shopping summary information C by the size of kj to generate a recommended ingredient list.

2. The method for generating a food recommendation list according to claim 1, wherein: The step of "sorting each element in the shopping recommendation list B by the size of kj to generate a recommended ingredient list" includes: Sort each element in the shopping recommendation list B from large to small according to the size of kj to generate a food recommendation list.

3. The method for generating a food recommendation list according to claim 2, characterized in that: The step of "sorting each element in the shopping recommendation list B from large to small according to the size of kj to generate a recommended food list" includes: When m is less than or equal to x, sort each element in the shopping recommendation list B from large to small according to the size of kj to generate a recommended ingredient list; When m is greater than x, each element in the shopping recommendation list B is sorted from large to small according to the size of kj, and the first x elements are taken to generate a food recommendation list.

4. The method for generating a food recommendation list according to claim 1, wherein: The step of "sorting each element in the shopping summary information C by the size of kj to generate a recommended ingredient list" includes: When m is greater than x, take the first x elements in {k1a1,k2a2…kjaj…kmam} as the undetermined set D, D={k1a1,k2a2…kxax}; Compare kx+1, kx+1…kx+y…km in turn to see if they are greater than all elements in {k1,k2…kx}. If kx+y is greater than any element kz in {k1,k2…kx}, replace kzaz in the undetermined set D with kx+yax+y. All the food information in the set D after the comparison is completed is used as the food recommendation list.

5. A refrigerator comprising a storage module and a processing module, wherein the storage module stores a computer program that can be run on the processing module, characterized in that: The processing module obtains the most recent n historical shopping information stored in the storage module, where each historical shopping information is Ai={a1, a2…aj}, where i represents the i-th historical shopping, i∈[1,n], aj represents the food information, and the larger the value of n, the closer the shopping time is to the current time; The processing module summarizes the food information of the n-time historical shopping information A1, A2 ... An to generate food summary information B = {a1, a2 ... aj ... am}; The processing module calculates the recommendation coefficient kj of the ingredient aj based on the weight of the number of times the ingredient aj appears in the n-time historical shopping information and the weight of the time when the ingredient aj appears. The processing module calculates the recommendation coefficient kj of the ingredient aj based on the formula Calculate the recommendation coefficient kj of ingredient aj, where ; The processing module generates shopping summary information C={k1a1, k2a2…kjaj…kmam}; The processing module sorts each element in the shopping summary information C according to the size of kj to generate a recommended food list.

6. The refrigerator according to claim 5, characterized in that When m is less than or equal to x, the processing module sorts each element in the shopping recommendation list B from large to small according to the size of kj to generate a recommended food list; When m is greater than x, the processing module sorts each element in the shopping recommendation list B from large to small according to the size of kj, and takes the first x elements to generate a food recommendation list.

7. The refrigerator according to claim 5, characterized in that When m is greater than x, the processing module takes the first x elements in {k1a1, k2a2…kjaj…kmam} as the undetermined set D, D={k1a1, k2a2…kxax}; The processing module sequentially compares kx+1, kx+1…kx+y…km to see if they are greater than all elements in {k1,k2…kx}. If kx+y is greater than any element kz in {k1,k2…kx}, replace kzaz in the pending set D with kx+yax+y. The processing module uses all the food information in the set D after the comparison as the food recommendation list.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processing module, the steps of the method for generating a recommended food list according to any one of claims 1 to 4 are implemented.

Images