Ordering recommendation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an ordering recommendation method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: in response to an ordering recommendation request triggered by a to-be-recommended object, obtaining and analyzing ordering demand input of the to-be-recommended object, and obtaining demand information; generating each candidate set meal based on the demand information and the dish information of each dish contained in the real-time dish database; based on the demand information and dish information of dishes contained in the candidate packages, calculating recommendation matching degrees between the candidate packages and the to-be-recommended object; and taking the candidate package with the recommendation matching degree meeting the recommendation condition as a target package, and recommending the target package to the to-be-recommended object. In this way, the target set meal with the demand information recommendation matching degree meeting the recommendation condition is automatically generated, ordering recommendation can be carried out objectively, the accuracy of ordering recommendation is improved, the consumed time is short, the efficiency is improved, and the accuracy is further improved by adopting the real-time dish database.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device, electronic device, and storage medium for ordering recommendations. Background Art

[0002] In modern life, dining out has gradually become a daily choice for the public. When ordering food out, customers usually browse the dishes on a paper menu or electronic terminal. The catering staff then matches the dish information with the customer's dining preferences based on their personal experience and recommends dishes to the customer.

[0003] However, the above-mentioned order recommendation method is highly subjective, and the personal experience of catering service personnel varies, which may lead to inaccurate recommended dishes. In addition, it relies on manual operation and has low recommendation efficiency. Summary of the Invention

[0004] The embodiments of the present application provide a method, device, electronic device, and storage medium for recommending food orders, so as to improve the accuracy and efficiency of recommending food orders.

[0005] In a first aspect, an embodiment of the present application provides a method for ordering recommendations, the method comprising:

[0006] In response to a meal recommendation request triggered by a person to be recommended, obtaining and parsing a meal request input from the person to be recommended to obtain request information;

[0007] Generate candidate meal sets based on the demand information and the dish information of each dish contained in the real-time dish database;

[0008] Based on the demand information and the dish information of each dish included in each candidate set meal, the recommendation matching degree between each candidate set meal and the object to be recommended is calculated;

[0009] The candidate packages that meet the recommendation conditions are recommended as target packages, and the target packages are recommended to the recommended objects.

[0010] In an optional embodiment, obtaining and parsing the ordering demand input of the object to be recommended to obtain demand information includes:

[0011] When the order demand input is in the form of voice, obtaining the order demand voice input by the person to be recommended, converting the order demand voice into text data, and parsing the text data to extract demand information;

[0012] When the order demand input is in text form, the order demand text input by the object to be recommended is obtained, the order demand voice is converted into the order demand text, and the order demand text is parsed to extract the demand information.

[0013] In an optional embodiment, the demand information includes: one or a combination of: taboo ingredients, taste preferences, demand scenarios, and budget;

[0014] The dish information includes one or a combination of: dish inventory, dish scene, dish price, dish taste, dish ingredients and dish sales.

[0015] In an optional embodiment, each candidate meal set is generated based on the demand information and the dish information of each dish contained in the real-time dish database, including:

[0016] Filtering available dishes based on the inventory of each dish contained in the real-time dish database;

[0017] Based on the demand information, select candidate dishes that meet the demand conditions from all available dishes;

[0018] Based on each candidate dish, construct each candidate set meal.

[0019] In an optional embodiment, based on the demand information, candidate dishes that meet the demand conditions are screened from the available dishes, including:

[0020] Filter out the dietary taboo dishes whose ingredients match the dietary taboo ingredients among all available dishes;

[0021] From the remaining available dishes, select candidate dishes whose taste matches the taste preference and whose dish scene matches the demand scene.

[0022] In an optional embodiment, based on the demand information and the dish information of each dish included in each candidate set meal, the recommendation matching degree between each candidate set meal and the to-be-recommended object is calculated, including:

[0023] For each candidate package, perform the following operations:

[0024] Determining the taste matching degree between a candidate meal and the recommended object based on the matching degree between the taste of each dish included in the candidate meal and the taste preference;

[0025] Determine the scene matching degree between a candidate meal and the object to be recommended based on the matching degree between the dish scene of each dish included in the candidate meal and the demand scene;

[0026] Determine the budget matching degree between a candidate meal and the recommended object based on the matching degree between the total price of a candidate meal and the budget, wherein the total price is: the sum of the prices of the dishes included in a candidate meal;

[0027] The taste matching degree, scene matching degree, budget matching degree between a candidate meal and the object to be recommended, as well as the sales index of a candidate meal, are weightedly summed to obtain the recommendation matching degree between the candidate meal and the object to be recommended. The sales index is the mapping value corresponding to the sum of the sales of each dish included in a candidate meal.

[0028] In an optional embodiment, recommending a target package to a to-be-recommended object includes:

[0029] Generate recommendation reasons for the target package;

[0030] The target package and the reasons for recommendation are displayed through a visual interface; and / or the target package and the reasons for recommendation are announced through voice.

[0031] In a second aspect, an embodiment of the present application further provides a device for recommending food orders, the device comprising:

[0032] An acquisition module is used to respond to an order recommendation request triggered by a to-be-recommended object, acquire and parse the order demand input of the to-be-recommended object, and obtain demand information;

[0033] A first processing module, configured to generate candidate meal sets based on the demand information and the dish information of each dish contained in the real-time dish database;

[0034] The second processing module is used to calculate the recommendation matching degree between each candidate meal and the to-be-recommended object based on the demand information and the dish information of each dish included in each candidate meal;

[0035] The generation module is used to select the candidate packages that meet the recommendation conditions as the target packages and recommend the target packages to the recommended objects.

[0036] In an optional embodiment, when obtaining and parsing the ordering demand input of the object to be recommended and obtaining the demand information, the acquisition module is further configured to:

[0037] When the order demand input is in the form of voice, the order demand voice input by the object to be recommended is obtained, and the order demand voice is converted into text data, and the text data is parsed to extract demand information.

[0038] When the order demand input is in text form, the order demand text input by the object to be recommended is obtained, the order demand voice is converted into the order demand text, and the order demand text is parsed to extract the demand information.

[0039] In an optional embodiment, the demand information includes: one or a combination of: taboo ingredients, taste preferences, demand scenarios, and budget;

[0040] The dish information includes one or a combination of: dish inventory, dish scene, dish price, dish taste, dish ingredients and dish sales.

[0041] In an optional embodiment, when generating each candidate meal based on the demand information and the dish information of each dish contained in the real-time dish database, the first processing module is further configured to:

[0042] Filtering available dishes based on the inventory of each dish contained in the real-time dish database;

[0043] Based on the demand information, select candidate dishes that meet the demand conditions from all available dishes;

[0044] Based on each candidate dish, construct each candidate set meal.

[0045] In an optional embodiment, when screening candidate dishes that meet the demand conditions from available dishes based on the demand information, the first processing module is further configured to:

[0046] Filter out the dietary taboo dishes whose ingredients match the dietary taboo ingredients among all available dishes;

[0047] From the remaining available dishes, select candidate dishes whose taste matches the taste preference and whose dish scene matches the demand scene.

[0048] In an optional embodiment, when calculating the recommendation matching degree between each candidate meal and the to-be-recommended object based on the demand information and the dish information of each dish included in each candidate meal, the second processing module is further configured to:

[0049] For each candidate package, perform the following operations:

[0050] Determining the taste matching degree between a candidate meal and the recommended object based on the matching degree between the taste of each dish included in the candidate meal and the taste preference;

[0051] Determine the scene matching degree between a candidate meal and the object to be recommended based on the matching degree between the dish scene of each dish included in the candidate meal and the demand scene;

[0052] Determine the budget matching degree between a candidate meal and the recommended object based on the matching degree between the total price of a candidate meal and the budget, wherein the total price is: the sum of the prices of the dishes included in a candidate meal;

[0053] The taste matching degree, scene matching degree, budget matching degree between a candidate meal and the object to be recommended, as well as the sales index of a candidate meal, are weightedly summed to obtain the recommendation matching degree between the candidate meal and the object to be recommended. The sales index is the mapping value corresponding to the sum of the sales of each dish included in a candidate meal.

[0054] In an optional embodiment, when recommending a target package to a to-be-recommended object, the generating module is further configured to:

[0055] Generate recommendation reasons for the target package;

[0056] The target package and the reasons for recommendation are displayed through a visual interface; and / or the target package and the reasons for recommendation are announced through voice.

[0057] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0058] processor; and

[0059] Memory for storing programs,

[0060] The program includes instructions, which, when executed by a processor, cause the processor to execute the meal ordering recommendation method as described in the first aspect.

[0061] In a fourth aspect, an embodiment of the present application further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the order recommendation method as described in the first aspect.

[0062] In a fifth aspect, the present application provides a computer program product, which, when called by a computer, enables the computer to execute the steps of the ordering recommendation method as described in the first aspect.

[0063] The beneficial effects of this application are as follows:

[0064] In the meal recommendation method provided in the embodiment of the present application, when the subject to be recommended triggers a meal recommendation request, the meal request input of the subject to be recommended is obtained and parsed to obtain the request information. Then, based on the request information and the dish information of each dish contained in the real-time dish database, each candidate meal is generated. Then, based on the request information and the dish information of each dish contained in each candidate meal, the recommendation matching degree between each candidate meal and the subject to be recommended is calculated. Finally, the candidate meal whose recommendation matching degree meets the recommendation criteria is selected as the target meal and recommended to the subject to be recommended. In this way, by interactively obtaining the request information of the subject to be recommended, and based on the request information and the dish information of each dish contained in the real-time dish database, the target meal whose recommendation matching degree meets the recommendation criteria is automatically generated. This method does not rely on manual experience and can objectively perform meal recommendations, thereby improving the accuracy of meal recommendations, shortening the processing time, improving the efficiency of meal recommendations, and comprehensively enhancing the user experience of the subject to be recommended. Moreover, the use of the real-time dish database ensures the synchronization of dish information, which can avoid inaccurate recommendation results caused by asynchronous dish information, further improving the accuracy of recommendations.

[0065] In addition, other features and advantages of the present application will be described in the following description, and in part will become apparent from the description, or may be understood by practicing the present application. The objectives and other advantages of the present application can be realized and obtained through the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described here are used to provide a further understanding of the present application, constitute a part of the present application, and do not constitute an improper limitation of the present application. In the drawings:

[0067] Figure 1 A schematic diagram of an optional system architecture applicable to the embodiments of the present application;

[0068] Figure 2 A schematic diagram of an implementation flow of a meal ordering recommendation method provided in an embodiment of the present application;

[0069] Figure 3 A schematic diagram of an input interface provided in an embodiment of the present application;

[0070] Figure 4 A schematic diagram of generating recommendation results provided in an embodiment of the present application;

[0071] Figure 5 A schematic diagram of the structure of a device for recommending food orders provided in an embodiment of the present application;

[0072] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0073] The following describes embodiments of the present application in more detail with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are for illustrative purposes only and are not intended to limit the scope of protection of the present application.

[0074] It should be understood that the various steps described in the method embodiments of the present application can be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0075] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc. mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0076] It should be noted that the modifications of "one" and "multiple" mentioned in this application are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0077] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0078] The following is a brief introduction to the design concept of the embodiment of this application:

[0079] In modern life, dining out has become a daily routine for many. When ordering food, customers typically browse the menu on paper or via an electronic device and then ask the catering staff for recommendations. The catering staff then matches the menu information with the customer's preferences based on their personal experience and recommends dishes to the customer.

[0080] However, the above-mentioned order recommendation method is highly subjective, and the personal experience of catering service staff varies, which may lead to inaccurate recommended dishes. In addition, catering service staff need to manually check the inventory of dishes and customer dining preferences, which is time-consuming and leads to low recommendation efficiency.

[0081] In view of this, in an embodiment of the present application, a meal order recommendation method, device, electronic device and storage medium are provided. When the object to be recommended triggers a meal order recommendation request, the meal order demand input of the object to be recommended is obtained and parsed to obtain demand information. Then, based on the demand information and the dish information of each dish contained in the real-time dish database, each candidate meal set is generated. Then, based on the demand information and the dish information of each dish contained in each candidate meal set, the recommendation matching degree between each candidate meal set and the object to be recommended is calculated. Finally, the candidate meal set with the recommendation matching degree that meets the recommendation conditions is used as the target meal set, and the target meal set is recommended to the object to be recommended. In this way, the demand information of the object to be recommended is obtained interactively, and the target meal set with the recommendation matching degree that meets the recommendation conditions is automatically generated based on the demand information and the dish information of each dish contained in the real-time dish database. This does not rely on manual experience, and can objectively perform meal order recommendations, thereby improving the accuracy of meal order recommendations and taking less time, thereby improving the efficiency of meal order recommendations, and comprehensively improving the user experience of the object to be recommended. Moreover, the use of a real-time dish database ensures the synchronization of dish information, which can avoid inaccurate recommendation results caused by asynchronous dish information, and further improve the accuracy of recommendations.

[0082] In particular, the preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application and are not used to limit the present application. In addition, the embodiments of the present application and the features in the embodiments may be combined with each other if there is no conflict.

[0083] See Figure 1As shown, it is a schematic diagram of an optional system architecture applicable to an embodiment of the present application, and the system architecture may include: a terminal device (101a, 101b) and a server 102. The terminal device (101a, 101b) and the server 102 can exchange information through a communication network, wherein the communication mode adopted by the communication network may include: a wireless communication mode and a wired communication mode. Exemplarily, the terminal device (101a, 101b) can access the network through cellular mobile communication technology and communicate with the server 102. The cellular mobile communication technology, for example, includes the fifth generation mobile communication (5th generation mobile networks, 5G) technology or the next generation mobile communication technology. Optionally, the terminal device (101a, 101b) can access the network through a short-range wireless communication mode and communicate with the server 102. The short-range wireless communication mode, for example, includes wireless fidelity (Wi-Fi) technology.

[0084] The embodiment of the present application does not impose any restrictions on the number of communication devices involved in the above system architecture. For example, the above system architecture may include more terminal devices, or may include fewer terminal devices, or may also include other network devices. Figure 1 As shown, only the terminal devices (101a, 101b) and the server 102 are described as examples, and the above communication devices and their respective functions are briefly introduced below.

[0085] The terminal device (101a, 101b) is a device that can provide voice and / or data connectivity to users, and can be a device that supports wired and / or wireless connection.

[0086] Exemplarily, the terminal devices (101a, 101b) may include, but are not limited to: mobile phones, tablet computers, laptop computers, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminal devices in industrial control, wireless terminal devices in unmanned driving, wireless terminal devices in smart grids, wireless terminal devices in transportation safety, wireless terminal devices in smart cities, or wireless terminal devices in smart homes, etc.

[0087] In addition, a related client may be installed on the terminal device (101a, 101b), which may be software, such as an application (APP), a browser, etc., or a web page, a mini-program, etc.; it should be noted that the terminal device (101a, 101b) in the embodiment of the present application may be the above-mentioned client related to ordering recommendations.

[0088] Server 102 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0089] It is worth mentioning that the server 102 in the embodiment of the present application can parse the order demand input of the object to be recommended and obtain demand information; then, based on the demand information and the dish information of each dish contained in the real-time dish database, generate each candidate meal; based on the demand information and the dish information of each dish contained in each candidate meal, calculate the recommendation matching degree between each candidate meal and the object to be recommended; finally, the candidate meal whose recommendation matching degree meets the recommendation conditions is used as the target meal, and the target meal is recommended to the object to be recommended.

[0090] Optionally, a pre-trained AI big model can be deployed on the server 102. In this way, after obtaining the order demand input of the object to be recommended, the server 102 can input the order demand into the AI ​​big model to determine the target package to be recommended to the object to be recommended.

[0091] The above-mentioned AI large model can be a DeepSeek model, which is not limited in this application.

[0092] The following describes the order recommendation method provided by the exemplary embodiment of the present application in combination with the above-mentioned system architecture and reference to the accompanying drawings. It should be noted that the above-mentioned system architecture is only shown to facilitate understanding of the spirit and principles of the present application, and the implementation of the present application is not limited in this respect.

[0093] See Figure 2 As shown, it is a schematic diagram of the implementation process of a meal order recommendation method provided in an embodiment of the present application. The execution subject takes the server as an example. The specific implementation process of the method is as follows:

[0094] S20: In response to the order recommendation request triggered by the object to be recommended, obtain and parse the order demand input of the object to be recommended to obtain demand information.

[0095] Among them, the object to be recommended can be a customer or a catering service staff, which is not limited in the embodiment of the present application. The demand information includes: one or a combination of taboo ingredients, taste preferences, demand scenarios and budget.

[0096] The data format of the demand information can be structured JSON data, which is not limited in the embodiments of the present application. For example, the JSON data is: {"scene":"Family dinner","budget":500,"flavor":"Non-spicy","exclusions":"Peanuts"}, then the taboo ingredient in the demand information is peanuts, the taste preference is non-spicy, the demand scene is family dinner, and the budget is 500 yuan.

[0097] In an embodiment of the present application, an input interface is displayed on a terminal device. When the person to be recommended inputs an order requirement on the input interface, an order recommendation request is triggered. The server responds to the order recommendation request, obtains the order requirement input entered by the person to be recommended, and parses the order requirement input to obtain the order requirement information of the person to be recommended.

[0098] The input forms of ordering requirements include voice and text.

[0099] Optionally, in an embodiment of the present application, when the ordering demand input is in the form of voice, the ordering demand voice input by the object to be recommended is obtained, and the ordering demand voice is converted into text data, and the text data is parsed to extract the demand information.

[0100] For example, see Figure 3 As shown, this is a schematic diagram of an input interface in an embodiment of the present application. When the recommended object wants to order food, he clicks the voice recognition button 31 of the input interface and inputs the voice of the ordering demand. The server uses speech-to-text technology (such as automatic speech recognition (ASR)) to convert the voice of the ordering demand into text data, and then uses the AI ​​big model to parse the text data, extract the demand information according to each demand dimension, and finally output the structured demand information.

[0101] Optionally, in an embodiment of the present application, when the order demand input is in the form of text, the order demand text input by the object to be recommended is obtained, the order demand text is parsed, and the demand information is extracted.

[0102] For example, Figure 3As shown, when the recommended object wants to order food, he / she can click the input box of the input interface to enter the text of the order requirement. For example, the recommended object clicks the input box of S32 and enters: "Family dinner, budget 500 yuan, no spicy food, peanut allergy", and then clicks the S33 confirmation button to trigger the order recommendation request. The server directly uses the AI ​​large model to parse the text data, extracts the demand information according to each demand dimension, and finally outputs the structured demand information.

[0103] In this way, by presenting an input interface to interact with the person to be recommended, the person to be recommended can input their ordering needs, which provides convenience for the person to be recommended. Voice input is also possible, making the interaction more convenient, saving input time, and improving recommendation efficiency.

[0104] S21: Generate candidate meal sets based on the demand information and the dish information of each dish included in the real-time dish database.

[0105] Among them, the real-time dish data includes: real-time dish information of each dish, the dish information includes: one or a combination of dish inventory, dish scene, dish price, dish taste, dish ingredients and dish sales, and the dish information also includes: dish recommendation index, which is not limited in the embodiment of the present application.

[0106] Optionally, before generating each candidate meal set based on demand information and the dish information of each dish contained in the real-time dish database, it is necessary to access the backend database to obtain the real-time dish database to ensure real-time synchronization of dish information that needs to be updated, such as dish inventory or price changes, so as to make order recommendations based on the latest dish information and improve the accuracy of order recommendations.

[0107] Specifically, in an embodiment of the present application, data update information is obtained in real time, and the dish information of the corresponding dishes contained in the current dish database is updated based on the data update information to obtain an updated real-time dish database.

[0108] Optionally, in an embodiment of the present application, a possible embodiment is provided for generating candidate meal sets based on demand information and dish information of each dish contained in a real-time dish database, and the following operations are specifically performed:

[0109] S210: Filter out available dishes based on the inventory of each dish contained in the real-time dish database.

[0110] In the embodiment of the present application, dishes with a dish inventory greater than 0 are screened out from the real-time dish database as available dishes.

[0111] In addition, before obtaining the real-time dish database, the dish information of the dishes whose dish inventory is 0 in the real-time dish database can be deleted to ensure that the dishes recorded in the real-time dish database are all available dishes.

[0112] S211: Based on the demand information, select candidate dishes that meet the demand conditions from the available dishes.

[0113] In an embodiment of the present application, candidate dishes that meet the demand conditions are screened from the available dishes based on one or a combination of taboo ingredients, taste preferences, demand scenarios, and budget.

[0114] Optionally, in an embodiment of the present application, a possible embodiment is provided for screening candidate dishes that meet the demand conditions from available dishes based on a combination of taboo ingredients, taste preferences, and demand scenarios. Specifically, the following operations are performed:

[0115] S2110: Filter out the dietary restriction dishes whose ingredients match the dietary restriction ingredients among all available dishes.

[0116] In an embodiment of the present application, from each available dish, the taboo dishes whose ingredients include taboo ingredients are screened out, and the taboo dishes are deleted from each available dish to obtain the remaining available dishes, wherein the remaining available dishes do not include taboo ingredients. Whether the dish ingredients include taboo ingredients can be judged by the direct similarity between the feature vector of the dish ingredients and the feature vector of the taboo ingredients.

[0117] For example, suppose the food that the person to be recommended should avoid is peanuts, and the ingredients of dish A among the available dishes are peanuts, diced chicken, chili peppers, onions, ginger, and garlic. The ingredients of dish A include the food that should be avoided, so dish A is a food that should be avoided, and dish A will be deleted from all available dishes.

[0118] S2111: From the remaining available dishes, select candidate dishes whose taste matches the taste preference and whose dish scene matches the demand scene.

[0119] In an embodiment of the present application, candidate dishes are screened out from the remaining available dishes, the similarity between the dish taste and the taste preference being greater than a first similarity threshold, and the similarity between the dish scene and the demand scene being greater than a second similarity threshold.

[0120] For example, calculate the first similarity between the feature vector of the dish taste of dish B and the feature vector of the taste preference, and calculate the second similarity between the feature vector of the dish scene of dish B and the feature vector of the demand scene. If the first similarity is greater than the first similarity threshold and the second similarity is greater than the second similarity threshold, then dish B is selected as a candidate dish.

[0121] In this way, by considering demand information in multiple dimensions, candidate dishes that meet the demand conditions can be screened out.

[0122] S212: Construct candidate meal sets based on the candidate dishes.

[0123] In the embodiment of the present application, the candidate dishes are randomly combined to obtain candidate meal sets.

[0124] In this way, candidate meal packages that meet the needs of the recommended objects can be generated, and customized meal package recommendations can be made to the recommended objects, thereby improving the ordering experience of the recommended objects.

[0125] Optionally, in an embodiment of the present application, each candidate package may be constructed according to a preset combination rule.

[0126] Among them, the preset combination rule is: put the top N candidate dishes with high similarity between dish taste and taste preference into N candidate sets respectively, and then add the top N candidate dishes with high similarity between dish scene and demand scene among the remaining candidate dishes into N candidate sets respectively, and then add the remaining candidate dishes to the N candidate sets according to the budget, so that the total price of each candidate set does not exceed the budget, N is an integer greater than 1, and the combination rules are not restricted in the embodiment of the present application.

[0127] In this way, it is possible to avoid generating candidate packages with low recommendation matching degrees, reduce the number of candidate packages for which the recommendation matching degrees need to be calculated, and save computing resources.

[0128] S22: Based on the demand information and the dish information of each dish included in each candidate meal, the recommendation matching degree between each candidate meal and the object to be recommended is calculated.

[0129] Optionally, in an embodiment of the present application, a possible embodiment is provided for calculating the recommendation matching degree between each candidate meal and the to-be-recommended object based on the demand information and the dish information of each dish included in each candidate meal. For each candidate meal in each candidate meal, the following operations are performed:

[0130] S220: Based on the matching degree between the taste of each dish included in the candidate meal and the taste preference, determine the taste matching degree between the candidate meal and the object to be recommended.

[0131] In an embodiment of the present application, the sum of the matching degrees between the taste of each dish included in a candidate meal and the taste preference of the object to be recommended is calculated to obtain the taste matching degree between the candidate meal and the object to be recommended.

[0132] For example, suppose that candidate package a includes: dish B, dish C and dish D, the matching degree between the taste of dish B and the taste preference of the object to be recommended is 0.6, the matching degree between the taste of dish C and the taste preference of the object to be recommended is 0.8, and the matching degree between the taste of dish D and the taste preference of the object to be recommended is 0.6, then the taste matching degree between candidate package a and the object to be recommended is 0.6+0.8+0.6=2.2.

[0133] S221: Determine the scene matching degree between a candidate meal and the object to be recommended based on the matching degree between the dish scene of each dish included in the candidate meal and the demand scene.

[0134] In an embodiment of the present application, the sum of the matching degrees between the dish scenes of each dish included in a candidate meal and the demand scene of the object to be recommended is calculated to obtain the scene matching degree between the candidate meal and the object to be recommended.

[0135] For example, suppose that candidate package a includes: dish B, dish C and dish D, the matching degree between the dish scene and the demand scene of dish B is 0.9, the matching degree between the dish scene and the demand scene of dish C is 0.8, and the matching degree between the dish scene and the demand scene of dish D is 0.6, then the taste matching degree between candidate package a and the object to be recommended is 0.9+0.8+0.6=2.4.

[0136] S222: Based on the matching degree between the total price of a candidate package and the budget, determine the budget matching degree between a candidate package and the object to be recommended.

[0137] The total price is the sum of the prices of all dishes included in a candidate meal.

[0138] In an embodiment of the present application, the sum of the prices of the dishes included in a candidate meal is calculated to obtain the total price of the candidate meal, and then the matching degree between the total price of the candidate meal and the budget of the object to be recommended is calculated to obtain the budget matching degree between the candidate meal and the object to be recommended.

[0139] For example, suppose that candidate package a includes: dish B, dish C and dish D, the price of dish B is 100 yuan, the price of dish C is 120 yuan, and the price of dish D is 90 yuan, then the total price of candidate package a is 310 yuan, and then calculate the matching degree between the total price of 310 yuan and the budget of 500 yuan.

[0140] In addition, it is worth mentioning that the degree of matching between the total price and the budget can be determined based on the difference between the total price of the candidate packages and the budget.

[0141] S223: Perform weighted summation on the taste matching degree, scene matching degree, and budget matching degree between a candidate meal package and the object to be recommended, as well as the sales index of a candidate meal package, to obtain a recommendation matching degree between the candidate meal package and the object to be recommended.

[0142] The sales index is a mapping value corresponding to the sum of the sales of each dish included in a candidate meal.

[0143] Optionally, the sales index can be obtained by calculating the ratio of the total sales of each dish included in a candidate meal to the total sales of all dishes, and using the ratio as the sales index. It can also be obtained by determining the index value corresponding to the sales interval to which the total sales of each dish included in a candidate meal belongs according to the mapping relationship between the sales interval and the index value, and using the index value as the sales index. This is not limited in the embodiments of the present application.

[0144] In the embodiment of the present application, the calculation formula for the recommended matching degree is specifically: Y=α*I1+β*I2+γI3*+δ*I4.

[0145] Among them, Y represents the recommendation matching degree between a candidate package and the object to be recommended, I1 represents the budget matching degree between a candidate package and the object to be recommended, I2 represents the taste matching degree between a candidate package and the object to be recommended, I3 represents the scene matching degree between a candidate package and the object to be recommended, I4 represents the sales index of a candidate package, α represents the weight coefficient of budget matching, β represents the weight coefficient of taste matching, γ represents the weight coefficient of scene matching, δ represents the weight coefficient of sales index, and the sum of each weight coefficient is 1, for example, α=0.4, β=0.3, γ=0.2, δ=0.1.

[0146] In this way, by considering indicators under multiple dimensions, the recommendation matching degree between each candidate meal and the object to be recommended can be accurately calculated, thereby improving the accuracy of order recommendations.

[0147] S23: The candidate packages whose matching degree meets the recommendation conditions are selected as target packages, and the target packages are recommended to the recommended objects.

[0148] In an embodiment of the present application, after obtaining the recommended matching degree of each candidate package, the candidate package with the largest recommended matching degree is used as the target package, and then the target package is displayed to the to-be-recommended object through a visual interface, and / or the target package is voice-announced to the to-be-recommended object.

[0149] For example, see Figure 4As shown, this is a schematic diagram of generating recommendation results in an embodiment of the present application. When displayed on a visual interface, pictures and dish information of each dish in the target meal can be displayed. When broadcasted by voice, it can be broadcasted in a preset format, for example, "Based on your ordering needs, the following dishes are recommended to you, including: Dish B, Dish C, and Dish D."

[0150] Optionally, in an embodiment of the present application, after obtaining the target package, a recommendation reason for the target package is generated through an AI big model, and then the target package and the recommendation reason are displayed through a visual interface, and / or the target package and the recommendation reason are broadcast by voice.

[0151] For example, the reason for recommendation is "the total price of dish B, dish C and dish D is 400, which meets the budget limit and is suitable for family gatherings."

[0152] In this way, explainable recommendations are made to enhance user trust.

[0153] In addition, it is worth mentioning that in the embodiment of the present application, the visual interface supports one-click ordering or ordering after adjusting the target package, which improves the efficiency of ordering.

[0154] Furthermore, based on the same technical concept, the embodiment of the present application provides a device for ordering recommendations, which is used to implement the above-mentioned method flow of the embodiment of the present application. Figure 5 As shown, the meal order recommendation device 500 may include: an acquisition module 501, a first processing module 502, a second processing module 503 and a generation module 504, wherein:

[0155] The acquisition module 501 is configured to obtain and analyze the ordering requirement input of the object to be recommended in response to the ordering recommendation request triggered by the object to be recommended, and obtain the requirement information;

[0156] The first processing module 502 is used to generate candidate meal sets based on the demand information and the dish information of each dish contained in the real-time dish database;

[0157] The second processing module 503 is used to calculate the recommendation matching degree between each candidate meal and the to-be-recommended object based on the demand information and the dish information of each dish included in each candidate meal;

[0158] The generating module 504 is configured to select the candidate packages whose matching degree meets the recommendation conditions as target packages and recommend the target packages to the recipients.

[0159] In an optional embodiment, when obtaining and parsing the ordering demand input of the object to be recommended and obtaining the demand information, the obtaining module 501 is further configured to:

[0160] When the order demand input is in the form of voice, obtaining the order demand voice input by the person to be recommended, converting the order demand voice into text data, and parsing the text data to extract demand information;

[0161] When the order demand input is in text form, the order demand text input by the object to be recommended is obtained, the order demand voice is converted into the order demand text, and the order demand text is parsed to extract the demand information.

[0162] In an optional embodiment, the demand information includes: one or a combination of: taboo ingredients, taste preferences, demand scenarios, and budget;

[0163] The dish information includes one or a combination of: dish inventory, dish scene, dish price, dish taste, dish ingredients and dish sales.

[0164] In an optional embodiment, when generating each candidate meal based on the demand information and the dish information of each dish contained in the real-time dish database, the first processing module 502 is further configured to:

[0165] Filtering available dishes based on the inventory of each dish contained in the real-time dish database;

[0166] Based on the demand information, select candidate dishes that meet the demand conditions from all available dishes;

[0167] Based on each candidate dish, construct each candidate set meal.

[0168] In an optional embodiment, when screening candidate dishes that meet the demand conditions from available dishes based on the demand information, the first processing module 502 is further configured to:

[0169] Filter out the dietary taboo dishes whose ingredients match the dietary taboo ingredients among all available dishes;

[0170] From the remaining available dishes, select candidate dishes whose taste matches the taste preference and whose dish scene matches the demand scene.

[0171] In an optional embodiment, when calculating the recommendation matching degree between each candidate meal and the to-be-recommended object based on the demand information and the dish information of each dish included in each candidate meal, the second processing module 503 is further configured to:

[0172] For each candidate package, perform the following operations:

[0173] Determining the taste matching degree between a candidate meal and the recommended object based on the matching degree between the taste of each dish included in the candidate meal and the taste preference;

[0174] Determine the scene matching degree between a candidate meal and the object to be recommended based on the matching degree between the dish scene of each dish included in the candidate meal and the demand scene;

[0175] Determine the budget matching degree between a candidate meal and the recommended object based on the matching degree between the total price of a candidate meal and the budget, wherein the total price is: the sum of the prices of the dishes included in a candidate meal;

[0176] The taste matching degree, scene matching degree, budget matching degree between a candidate meal and the object to be recommended, as well as the sales index of a candidate meal, are weightedly summed to obtain the recommendation matching degree between the candidate meal and the object to be recommended. The sales index is the mapping value corresponding to the sum of the sales of each dish included in a candidate meal.

[0177] In an optional embodiment, when recommending a target package to a to-be-recommended object, the generating module 504 is further configured to:

[0178] Generate recommendation reasons for the target package;

[0179] The target package and the reasons for recommendation are displayed through a visual interface; and / or the target package and the reasons for recommendation are announced through voice.

[0180] Based on the description of the above method embodiment and apparatus embodiment, the exemplary embodiments of the present invention further provide an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor, and when executed by the at least one processor, the computer program causes the electronic device to perform a method according to an embodiment of the present invention.

[0181] An embodiment of the present application further provides a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to execute a method according to an embodiment of the present application.

[0182] An embodiment of the present application further provides a computer program product, including a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to execute the method according to the embodiment of the present application.

[0183] See Figure 6As shown, the structural block diagram of the electronic device 600 that can be used as the server or client of the present application will now be described, which is an example of a hardware device that can be applied to various aspects of the present application. The electronic device is intended to represent various forms of digital electronic computer equipment, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0184] like Figure 6 As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the device 600 can also be stored in the RAM 603. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0185] Multiple components within electronic device 600 are connected to I / O interface 605, including an input unit 605, an output unit 606, a storage unit 608, and a communication unit 609. Input unit 605 can be any type of device capable of inputting information into electronic device 600. Input unit 605 can receive input numeric or character information and generate key input signals related to user settings and / or function control of the electronic device. Output unit 606 can be any type of device capable of presenting information and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. Storage unit 608 may include, but is not limited to, a magnetic disk or an optical disk. Communication unit 609 allows electronic device 600 to exchange information / data with other devices via computer networks such as the Internet and / or various telecommunication networks and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver and / or a chipset, such as a Bluetooth device, a WiFi device, a Worldwide Interoperability for Microwave Access (WiMax) device, a cellular communication device, and / or the like.

[0186] The computing unit 601 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above. For example, in some embodiments, the above-mentioned order recommendation method can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 600 via the ROM 602 and / or the communication unit 609. In some embodiments, the computing unit 601 can be configured to execute the above-mentioned order recommendation method by any other appropriate means (for example, by means of firmware).

[0187] The program code for implementing the methods of the present application can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow charts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0188] In the context of the present application, a machine-readable medium can be a tangible medium that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a RAM, a ROM, an erasable programmable read-only memory (EPROM) or a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0189] As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and / or device (e.g., a magnetic disk, an optical disk, a memory, a programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including machine-readable media that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0190] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a cathode ray tube (CRT) or a liquid crystal display (LCD) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0191] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0192] Computer systems may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The client and server relationship arises through computer programs running on the respective computers and having a client-server relationship to each other.

[0193] Furthermore, it should be understood that what is disclosed above is merely a preferred embodiment of the present application and certainly cannot be used to limit the scope of rights of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope covered by the present application.

Claims

1. A method for recommending food orders, characterized in that: include: In response to a meal recommendation request triggered by a to-be-recommended object, acquiring and parsing a meal request input of the to-be-recommended object to obtain request information; generating candidate meal sets based on the demand information and the dish information of each dish contained in the real-time dish database; Calculating a recommendation matching degree between each candidate meal and the to-be-recommended object based on the demand information and the dish information of each dish included in each candidate meal; The candidate packages whose matching degree meets the recommendation conditions are selected as target packages, and the target packages are recommended to the recommended objects.

2. The method according to claim 1, wherein The step of obtaining and parsing the order demand input of the object to be recommended to obtain demand information includes: When the order demand input is in the form of voice, obtaining the order demand voice input by the person to be recommended, converting the order demand voice into text data, and parsing the text data to extract demand information; When the order demand input is in text form, the order demand text input by the object to be recommended is obtained, the order demand voice is converted into order demand text, and the order demand text is parsed to extract demand information.

3. The method according to claim 1, wherein The demand information includes: one or a combination of: taboo ingredients, taste preferences, demand scenarios, and budget; The dish information includes one or a combination of: dish inventory, dish scene, dish price, dish taste, dish ingredients and dish sales.

4. The method according to claim 3, wherein Based on the demand information and the dish information of each dish contained in the real-time dish database, each candidate set meal is generated, including: Filtering available dishes based on the inventory of each dish contained in the real-time dish database; Based on the demand information, screening candidate dishes that meet the demand conditions from the available dishes; Based on the candidate dishes, candidate meal sets are constructed.

5. The method according to claim 4, wherein The step of screening candidate dishes that meet the demand conditions from the available dishes based on the demand information includes: Filtering the dietary restriction dishes whose ingredients match the dietary restriction ingredients among the available dishes; From the remaining available dishes, candidate dishes are screened out whose dish taste matches the taste preference and whose dish scene matches the demand scene.

6. The method according to claim 3, wherein The calculating, based on the demand information and the dish information of each dish included in each candidate set meal, a recommendation matching degree between each candidate set meal and the to-be-recommended object includes: For each of the candidate packages, perform the following operations: Determining a taste matching degree between the candidate meal and the object to be recommended based on a matching degree between the taste of each dish included in the candidate meal and the taste preference; Determining a scene matching degree between the candidate meal and the to-be-recommended object based on a matching degree between a dish scene of each dish included in the candidate meal and the demand scene; Determining a budget matching degree between the candidate meal and the to-be-recommended item based on a matching degree between a total price of the candidate meal and the budget, wherein the total price is the sum of the prices of the dishes included in the candidate meal; The taste matching degree, scene matching degree and budget matching degree between the candidate meal package and the object to be recommended, as well as the sales index of the candidate meal package are weightedly summed to obtain the recommendation matching degree between the candidate meal package and the object to be recommended, wherein the sales index is: the mapping value corresponding to the sum of the sales volume of each dish included in the candidate meal package.

7. The method according to claim 1, wherein The step of recommending the target package to the person to be recommended includes: Generating a recommendation reason for the target package; The target package and the reason for recommendation are displayed through a visual interface; and / or the target package and the reason for recommendation are announced through voice.

8. A device for recommending food, characterized in that: include: An acquisition module, configured to respond to an order recommendation request triggered by a to-be-recommended object, acquire and analyze the order requirement input of the to-be-recommended object, and obtain requirement information; A first processing module, configured to generate candidate meal sets based on the demand information and the dish information of each dish contained in the real-time dish database; A second processing module is configured to calculate a recommendation matching degree between each candidate meal and the to-be-recommended object based on the demand information and the dish information of each dish included in each candidate meal; The generation module is used to select the candidate packages whose matching degree meets the recommendation conditions as target packages, and recommend the target packages to the object to be recommended.

9. An electronic device comprising: processor; as well as Memory for storing programs, The program includes instructions, which, when executed by the processor, cause the processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images