Meal recommendation method and device, storage medium, electronic equipment and product

Abstract

The invention relates to a food recommendation method and device, a storage medium, electronic equipment and a product. The method comprises the steps of obtaining user demand information through a preset interface, wherein the user demand information at least comprises user feature information and dining demand information of a user; generating a question description text according to the user demand information and database information; the question description text is input to a target model, so that the target model generates an output result based on a target food database indicated by the database information, the target model is a large model, and the output result at least comprises recommended food and recommendation information of the recommended food; and displaying the output result through the preset interface.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, in particular, to a meal recommendation method and device, a storage medium, an electronic device and a product. BACKGROUND

[0002] At present, restaurants generally adopt two ways of manual ordering or code scanning ordering. When manual ordering, the service personnel may not be able to respond to the user's ordering in time due to busy business, and the service personnel may not be able to recommend the most suitable meal for the user due to insufficient understanding and recommendation ability of the meal provided by the restaurant. When code scanning ordering, the ordering interface only displays basic information such as name, price and thumbnail, which needs to be browsed and filtered by the customer. In the case that the user is not familiar with the meal of the restaurant, the user is difficult to quickly locate the meal or meal combination that meets his own needs. Therefore, whether manual ordering or code scanning ordering, the meal cannot be recommended in combination with the personal needs of the user, resulting in low efficiency of user ordering and poor ordering experience. SUMMARY

[0003] The purpose of the present disclosure is to provide a meal recommendation method, device, storage medium, electronic device and product.

[0004] In order to achieve the above purpose, according to a first aspect of the present disclosure, a meal recommendation method is provided, the method comprising: obtaining user demand information through a preset interface, the user demand information at least comprising user characteristic information and user meal demand information; generating a question description text according to the user demand information and database information; inputting the question description text into a target model to make the target model generate an output result based on a target meal database indicated by the database information, the target model being a large model, and the output result at least comprising a recommended meal and recommendation information of the recommended meal; displaying the output result through the preset interface.

[0005] Optionally, the obtaining user demand information through a preset interface comprises: displaying a first sub-interface and a second sub-interface through the preset interface, the first sub-interface displaying a plurality of preset characteristic items and a first content input area corresponding to each of the preset characteristic items, and the second sub-interface displaying a second content input area; generating the user characteristic information according to the content input by the user in the first content input area; generating the meal demand information according to the content input by the user in the second content input area.

[0006] Optionally, the database information is used to indicate an access manner of the target food database. The question description text is generated according to the user demand information and the database information, and includes: A question description template is obtained, the question description template including a first placeholder for filling a user feature, a second placeholder for filling a dining demand, a third placeholder for filling an access manner of the target food database, and a preset instruction text; The user feature information is filled into the first placeholder, the dining demand information is filled into the second placeholder, and the database information is filled into the third placeholder, so as to generate the question description text.

[0007] Optionally, the target food database is generated by: An original food data table is obtained, the original food data table including food information of a plurality of foods, each food information including a first field for recording food identification information and a plurality of second fields for describing food features; For each food in the original food data table, a food description text corresponding to the food is generated according to field contents corresponding to the plurality of second fields, and the food description text is stored in association with the food identification information of the food in the target food database.

[0008] Optionally, the user demand information further includes question information of the user. The output result further includes answer information generated by the target model for the question information.

[0009] Optionally, the method further includes: Multimedia information for representing a restaurant feature is obtained; In a case where the output result is displayed through the preset interface, the multimedia information is displayed in a preset area of the preset interface.

[0010] Optionally, the displaying of the output result through the preset interface includes: For each recommended food, recommendation summary information of the recommended food is generated according to recommendation information of the recommended food; For each recommended food, display content containing the recommendation summary information of the recommended food, a first trigger component and a second trigger component is generated, the first trigger component being used to display the recommendation information of the recommended food when triggered, and the second trigger component being used to add the recommended food to an ordered food list when triggered; The display content of each recommended food is displayed on the preset interface.

[0011] According to a second aspect of the present disclosure, a meal recommendation device is provided, the device comprising: a first obtaining module configured to obtain user demand information through a preset interface, the user demand information comprising at least user characteristic information and user meal demand information; a first generating module configured to generate a question description text according to the user demand information and database information; a processing module configured to input the question description text into a target model, so that the target model generates an output result based on a target meal database indicated by the database information, the target model being a large model, and the output result comprising at least a recommended meal and recommendation information of the recommended meal; a first display module configured to display the output result through the preset interface.

[0012] According to a third aspect of the present disclosure, a computer readable storage medium is provided, which stores a computer program, the program being executed by a processor to implement the steps of the method according to the first aspect of the present disclosure.

[0013] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a memory storing a computer program; a processor configured to execute the computer program in the memory to implement the steps of the method according to the first aspect of the present disclosure.

[0014] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, the computer program being executed by a processor to implement the steps of the method according to the first aspect of the present disclosure.

[0015] According to the above technical solution, the question description text is generated according to the user demand information provided by the user on the preset interface and the database information about the target meal database. Since the user demand information comprises user characteristic information and user meal demand information, the question description text can contain the personal situation of the user and the meal demand of the user. Then, the question description text is input into the target model, and based on the intelligent analysis capability of the target model as a large model, the meal or meal combination that meets the personal situation and meal demand of the user can be determined from the meals provided in the existing target meal data. Therefore, by providing the personal characteristics and personal demands of the user when ordering, the user can be intelligently positioned to the appropriate meal or meal combination for recommendation in the meals of the restaurant, realizing personalized meal recommendation for the user when eating, and further improving the ordering efficiency.

[0016] Other features and advantages of the present disclosure will be described in detail in the following specific embodiments section. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following detailed description, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings: Figure 1 is a flow chart of a meal recommendation method provided according to an embodiment of the present disclosure; Figure 2 is an exemplary schematic diagram of the preset interface in the step of obtaining user demand information through the preset interface in the meal recommendation method provided by the present disclosure; Figure 3 is an exemplary schematic diagram of a preset interface in the step of displaying output results through a preset interface in the meal recommendation method provided by the present disclosure; Figure 4 is an exemplary flow chart of the meal recommendation method provided by the present disclosure; Figure 5 is a block diagram of a meal recommendation device provided according to an embodiment of the present disclosure; Figure 6 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0018] The following describes the specific embodiments of the present disclosure in detail with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure and are not intended to limit the present disclosure.

[0019] Figure 1 This is a flowchart of a meal recommendation method according to an embodiment of the present disclosure. Optionally, the method provided by the present disclosure can be applied to electronic devices serving as ordering terminals, such as restaurant ordering terminals (e.g., tablet computers for ordering), mobile terminals (e.g., a user's mobile phone serving as an ordering terminal by accessing the ordering interface provided by the restaurant), etc. Figure 1 As shown, the method provided by the present disclosure may include steps 11 to 14.

[0020] In step 11, user demand information is obtained through a preset interface.

[0021] The user demand information at least includes user characteristic information and user meal demand information. The user characteristic information can be a characteristic related to the user's meal habit, i.e., a characteristic that can affect the user's meal, such as taste preference (e.g., preference for sour and sweet, spicy, light taste, etc.), dietary taboo (e.g., vegetarian, seafood allergy, no coriander, etc.), health demand (e.g., weight loss, high blood pressure, etc.). The meal demand information can be the user's demand for this meal, such as the total number of people for this meal, the total budget for this meal, etc.

[0022] The present disclosure can provide a preset interface for users to order meals. Optionally, the preset interface can be displayed through a meal ordering terminal (e.g., a tablet computer for ordering meals) in the restaurant. Optionally, the preset interface can be accessed through a network link, an applet, etc. For example, the restaurant can provide a two-dimensional code or a meal ordering website, and the user can access the preset interface by scanning the two-dimensional code or accessing the meal ordering website through a mobile phone, etc.

[0023] In the preset interface, an entry for the user to input user demand information can be provided, and the user can input the user demand information by accessing the entry.

[0024] In one possible implementation, the preset interface can provide a first interactive component (e.g., a text input box, a voice input button, etc.) for the user to input, and the user can input the user demand information through interaction with the first interactive component. For example, in the case where the preset interface provides a text input box, the user can input text information about his / her own characteristics and meal demand in the text input box. In response to the user's text input action, the user demand information can be obtained based on the user's input text. For another example, in the case where the preset interface provides a voice input button, the user can input information about his / her own characteristics and meal demand through the voice input button. In response to the user's voice input action, the user demand information can be obtained based on the user's input audio through audio-to-text processing.

[0025] In another possible implementation, step 11 can include the following steps: The first sub-interface and the second sub-interface are displayed through the preset interface, the first sub-interface displays a plurality of preset characteristic items and a first content input area corresponding to each preset characteristic item, and the second sub-interface displays a second content input area; The user characteristic information is generated according to the content input by the user for the first content input area; The meal demand information is generated according to the content input by the user for the second content input area.

[0026] The first sub-screen allows users to enter user profile information. It displays multiple preset profile items and a corresponding first content input area for each. Preset profile items are user-related, typically referring to user characteristics that may affect a user's dining experience. Preset profile items can be flexibly configured based on actual needs.

[0027] Optionally, the preset feature items may include, but are not limited to, taste preferences, dietary taboos, and health needs. Taste preferences may include, for example, preference for sweet and sour flavors, preference for spicy flavors, or preference for light flavors. Dietary taboos may include, for example, a vegetarian diet, seafood allergy, or aversion to cilantro. Health needs may include, for example, weight loss needs and needs for hypertensive patients. The first content input area corresponds one-to-one with the preset feature items and is used for the user to input user characteristics corresponding to the specified preset feature items.

[0028] The display area corresponding to each preset feature item can display descriptive information about the preset feature item, as well as the first content input area corresponding to the preset feature item. The descriptive information for the preset feature item can provide a prompt to the user, making it easier for the user to know what content to enter in the first content input area. For each first content input area, the first content input area can display a second interactive component, which may include, but is not limited to, a text input box, a drop-down menu, a checkbox, etc. The text input box allows the user to directly enter text, the drop-down menu provides multiple options for the user to select, and the checkbox provides multiple options for the user to select. The first content input area can determine the second interactive component to use based on the actual needs of the corresponding preset feature item. The second interactive components used in the first content input areas of different preset feature items do not need to be the same. For example, for the preset feature item of taste preference, a drop-down menu with options such as sweet and sour, spicy and hot, and light can be provided. For the preset feature item of dietary taboos, checkboxes with options such as vegetarian only, seafood allergy, and no cilantro can be provided. In addition, the first content input area may also provide a voice input button for the user to trigger the voice input button. In response to the user's voice input, the user's voice input may be converted into text through voice-to-text processing and used as the content input by the user through the first content input area. Optionally, the first sub-interface may be displayed in the form of a questionnaire.

[0029] In this way, based on the content displayed on the first sub-interface, the user can enter information for each preset feature item. After receiving the user input, the user input information can be associated with the corresponding preset feature item, and the information obtained based on each preset feature item can be integrated into user feature information. It should be noted that the preset feature items do not require input content. The user can indicate that the user has no relevant features by not entering any information in the first content input area. If the received user input information is empty, the preset feature item can be directly ignored when generating user feature information.

[0030] The second sub-interface allows users to enter dining requirements. This information may include the user's dining needs, such as the total number of people dining, the total budget, and so on. The second content input area may include a third interactive component (e.g., a text input box, a voice input button, etc.) for user input. The user can interact with the third interactive component to enter dining requirements. For example, if the second sub-interface provides a text input box, the user can enter text information about their dining needs. In response to the user's text input, the dining requirements information can be obtained based on the text input. For another example, if the second sub-interface provides a voice input button, the user can trigger the voice input button to voice-enter their dining needs. In response to the user's voice input, audio-to-text processing can be performed based on the user's input to obtain the dining requirements information. For example, the text information or voice input content entered by the user may include: "A people dining together, budget B yuan, please recommend C dishes."

[0031] In this way, based on the content displayed on the second sub-interface, the user can input his or her own dining needs. After receiving the information input by the user, the information input by the user can be used as dining demand information.

[0032] For example, in step 11, the preset interface can be as follows Figure 2 As shown, the upper dotted line frame of the preset interface is the first sub-interface, and the lower dotted line frame of the preset interface is the second sub-interface. Figure 2 In the first sub-interface shown, the preset feature item of taste preference provides a drop-down menu, providing multiple options for the user to select one of them, the preset feature item of dietary taboo provides a check box for the user to select one or more of them, and the preset feature item of health needs provides a text input box for the user to input as needed. Figure 2 In the second sub-interface shown, a text input box is provided for the user to input dining demand information.

[0033] Thus, the user characteristic information and the meal demand information of the user can be acquired through two sub-interfaces of the preset interface at the initial stage of the user ordering, and the two sub-interfaces are displayed in different forms according to the characteristics of the content to be input. The first sub-interface displays a plurality of characteristic items and a first content input area for the user to input the related content of the user characteristic information, and the second sub-interface displays a second content input area for the user to input the related content of the meal demand information at one time, so that the user demand information can be quickly acquired.

[0034] In addition, the user demand information can further include question information of the user. For example, the question information can be "What are the special dishes of this store?". Optionally, the fourth interactive component (for example, a text input box, a voice input button, etc.) for the user to input the question information can be provided in the preset interface, and the user can input the question information through the interaction with the fourth interactive component (for example, inputting text into the text input box, triggering the voice input button to input voice, etc.).

[0035] In step 12, a question description text is generated according to the user demand information and the database information.

[0036] The database information can be information related to a target dish database, and the target dish database stores information related to dishes in the restaurant. The generated question description text can be used to indicate that the dishes or combinations of dishes that meet the user characteristic information and the meal demand information are screened out from the dishes in the target dish database according to the meal demand of the user. The question description text can be used as the input of the subsequent model.

[0037] Optionally, the database information can be used to indicate the access method of the target dish database, such as the access path of the target dish database.

[0038] In one possible implementation, step 12 can include the following steps: obtaining a question description template, the question description template including a first placeholder for filling the user characteristic, a second placeholder for filling the meal demand, a third placeholder for filling the access method of the target dish database, and a preset instruction text; filling the user characteristic information into the first placeholder, filling the meal demand information into the second placeholder, and filling the database information into the third placeholder to generate the question description text.

[0039] The problem description template can be pre-set according to actual needs. The problem description template is usually provided with a first placeholder for filling in user characteristics, a second placeholder for filling in dining needs, a third placeholder for filling in an access manner of a target meal database, and preset instruction text. The preset instruction text is text indicating how the model processes input information and returns results, which is equivalent to a prompt word provided to the large model. For example, the preset instruction text can indicate that a meal or meal combination that meets user characteristic information and dining need information is found in the target meal database according to the dining need information, a recommended meal is formed, a recommended reason is explained, and detailed information of the recommended meal is provided. In this way, according to the set problem description template, the relevant information obtained in the foregoing steps is filled into the corresponding positions, and a problem description text can be generated.

[0040] For example, the problem description template can be "The user's characteristics are: XXXXXX; the user's dining needs are: YYYYY; the access path of the restaurant meal database is: ZZZZZZ; please recommend suitable meals or meal combinations for the user in the meal database, and provide recommended reasons and detailed information of the recommended meals". Among them, "please recommend suitable meals or meal combinations for the user in the meal database, and provide recommended reasons and detailed information of the recommended meals" is the preset instruction text. Based on this, the user characteristic information can be filled into the XXXXXX position, the dining need information can be filled into the YYYYY position, and the access path of the target meal database can be filled into the ZZZZZZ position to generate a problem description text.

[0041] Alternatively, if the user need information further includes user question information, the problem description template can further include a fourth placeholder for filling in the question information in addition to the first placeholder for filling in the user characteristics, the second placeholder for filling in the dining needs, the third placeholder for filling in the access manner of the target meal database, and the preset instruction text. Accordingly, after obtaining the problem description template, the problem description text can also be generated in the following manner: The user characteristic information is filled into the first placeholder, the dining need information is filled into the second placeholder, the database information is filled into the third placeholder, and the user question information is filled into the fourth placeholder to generate a problem description text.

[0042] For example, the question description template can be "the user's characteristics are: MMMMMM; the user's dining demand is: NNNNNN; the access path of the restaurant menu database is: PPPPPP, the user raises the following question: QQQQQQ; please answer the user's question, recommend suitable dishes or dish combinations for the user in the menu database, and feedback the recommendation reasons and detailed information of the recommended dishes". Among them, "please answer the user's question, recommend suitable dishes or dish combinations for the user in the menu database, and feedback the recommendation reasons and detailed information of the recommended dishes" is a preset instruction text. Based on this, the question description text can be generated by filling the user characteristic information into the MMMMMM position, filling the dining demand information into the NNNNNN position, filling the access path of the target menu database into the PPPPPP position, and filling the user's question information into the QQQQQQ position.

[0043] In a possible implementation, the target menu database can be generated in the following manner: An original menu data table is obtained, the original menu data table including menu information of a plurality of dishes, each dish information including a first field for recording dish identification information and a plurality of second fields for describing dish characteristics; For each dish in the original menu data table, a dish description text corresponding to the dish is generated according to the field content corresponding to the plurality of second fields, and the dish description text is stored in association with the dish identification information of the dish in the target menu database.

[0044] The original menu data table is an original data table of the restaurant menu, which can be recorded by the restaurant for each dish provided by the restaurant to form a data table containing all dishes provided by the restaurant. In the original menu data table, the dish information is stored in the form of row data as an information entry in the data table, and each information entry is composed of a plurality of column data. The original menu data table provides a plurality of columns, each column being used to store a type of information related to the dish, and the plurality of columns respectively include a first field for recording dish identification information and a plurality of second fields for describing dish characteristics.

[0045] Optionally, since the name of the dish can serve as a unique identifier of the dish, the first field can be used to record the name of the dish. Optionally, the dish characteristics can include but are not limited to the ingredient composition of the dish, the cooking method, the taste characteristics, the dish picture, the dish price, the ingredient source, whether it is a signature dish, whether it is a recommended dish of the day, etc. Correspondingly, the second field can be a field for representing the ingredient composition of the dish, a field for representing the cooking method of the dish, a field for representing the taste characteristics of the dish, a field for representing the dish picture of the dish, a field for representing the dish price of the dish, a field for representing the ingredient source of the dish, a field for representing whether the dish is a signature dish, a field for representing whether the dish is a recommended dish of the day, etc.

[0046] For each dish in the original dish database, a dish description text corresponding to the dish can be generated according to the field content of the multiple second fields corresponding to the dish. Optionally, the meanings represented by the multiple second fields corresponding to the dish and the field content can be input into the large model, and then, by means of the preset prompt word, relying on the powerful natural language understanding, reasoning generation and context modeling capabilities of the large model, the large model can be instructed to generate the dish description text corresponding to the dish according to the meanings represented by the multiple second fields corresponding to the dish and the field content. The large model can directly call an existing large model, such as ChatGPT, etc.

[0047] In this way, a corresponding dish description text can be generated for each dish in the original dish data table, and then the dish description text and the dish identification information of the dish can be stored in the target dish database. In this way, in the target dish database, the related information of each dish is stored in the form of row data as an information entry, and the dish database maintains two columns of data, one is the dish identification information (such as the name of the dish), and the other is the dish description information of the dish. Moreover, the target dish database can be updated regularly, i.e. the original dish data table is reacquired and the subsequent steps are performed, so as to ensure that the dish information in the target dish database is always up-to-date.

[0048] In step 13, the question description text is input into the target model to make the target model generate an output result based on the target dish database indicated by the database information.

[0049] The target model is a large model, which can generate an output result by directly calling an existing large model. The selected target model can be ChatGPT, etc.

[0050] By inputting the question description text into the target model, the target model can filter out the dish or dish combination that meets the user characteristic information and dining demand information in the target dish database based on the input question description text according to the user demand information, as the output result.

[0051] The output result at least includes the recommended dish and the recommendation information of the recommended dish. The form of the recommendation information can be indicated in the question description text. Optionally, the recommendation information can include, but is not limited to, a recommendation reason, a detailed introduction of the recommended dish, etc. The detailed introduction of the recommended dish can include, but is not limited to, food material details, cooking methods, suitable population, nutritional components, etc.

[0052] Optionally, as described above, the user demand information can further include question information of the user, and accordingly, the question description text can include the question information, and the preset instruction text can indicate that the question information is answered. Accordingly, the output result generated by the target model can further include answer information generated by the target model for the question information. Since the target model is a large model, based on its natural language understanding ability and reasoning generation ability, etc., the answer information can be generated for the question information.

[0053] Optionally, the output result can be formatted and typeset so as to be displayed in a format easy for the user to understand. The standard of the formatting and typesetting can be pre-set according to actual needs.

[0054] In step 14, the output result is displayed through a preset interface.

[0055] After obtaining the output result including the recommended dish and the recommendation information, the output result can be displayed through a preset interface to show the user the recommendation for the user to select the dish.

[0056] In one possible implementation, the recommended dish and the recommendation information can be directly outputted and displayed in association.

[0057] In another possible implementation, step 14 can include the following steps: For each recommended dish, recommendation summary information of the recommended dish is generated according to the recommendation information of the recommended dish; For each recommended dish, display content including the recommendation summary information of the recommended dish, a first trigger component and a second trigger component is generated, the first trigger component is used to display the recommendation information of the recommended dish when triggered, and the second trigger component is used to add the recommended dish to the ordered dish list when triggered; The display content of each recommended dish is displayed on the preset interface.

[0058] The generation manner of the recommendation summary information can be pre-set according to requirements. For example, the basic information in the recommendation information is extracted as the recommendation summary information of the recommended dish. For example, the basic information can include but is not limited to dish pictures, dish names, introductions (such as dish taste characteristics and prices), and the like.

[0059] For each recommended dish, the display content corresponding to the recommended dish can be generated, and the display content includes the recommendation summary information of the recommended dish, a first trigger component, and a second trigger component. The first trigger component, when triggered, displays the recommendation information of the recommended dish, that is, displays the complete recommendation information. For example, the first trigger component can be an expansion button. The second trigger component, when triggered, adds the recommended dish to the ordered dish list. For example, the second trigger component can be a dish add-to-cart button.

[0060] In the above manner, the display content corresponding to each recommended dish can be generated, so that the display content of each recommended dish can be displayed in the preset interface, and the user can interact based on the content displayed in the preset interface. Optionally, the display content of each recommended dish can be displayed through a card layout, such as displaying card content of the recommended dish including pictures, names, and introductions, while providing an expansion button (first trigger component) and an order button (second trigger component). In response to the user clicking the expansion button, the complete recommendation information of the recommended dish corresponding to the first trigger component is displayed, and in response to the user triggering the order button, the recommended dish corresponding to the order button is added to the ordered dish list.

[0061] For example, in step 14, the preset interface can be as shown in Figure 3 , in which the card layout is used to display the information of each recommended dish.

[0062] In this way, based on the display of the display content in the preset interface, the user can view and order the recommended dish. The preset interface can also provide an order confirmation button for the user to submit the ordered dish. In response to the user triggering the order confirmation button, the dish in the ordered dish list is transmitted to the kitchen system of the restaurant as an ordered dish through the network, so that the kitchen system can start making the dish.

[0063] Optionally, while the preset interface displays the above-mentioned display content, a fifth interaction component can also be provided, and the user can start a new round of interaction through the fifth interaction component to re-trigger the recommendation process, that is, the user can input new user demand information at any time to obtain new recommendations. For example, the fifth interaction component can include the first interaction component. For another example, the fifth interaction component can include at least one of the second interaction component, the third interaction component, and the fourth interaction component. The implementation modes of the first interaction component, the second interaction component, the third interaction component, and the fourth interaction component have been provided in the foregoing, and will not be described here.

[0064] Optionally, in addition to steps 11 to 14, the method provided by the present disclosure can further include the following steps: Obtaining multimedia information for representing the characteristics of the restaurant; In the case of displaying the output result through the preset interface, the multimedia information is displayed in a preset area of the preset interface.

[0065] Optionally, the multimedia information about the characteristics of the restaurant can be stored in advance through a preset database. Optionally, the characteristics of the restaurant can include but are not limited to the main cuisine of the restaurant, the source of the food materials, the characteristic cooking skills of the chef, etc. The form of the multimedia information can include but is not limited to text, pictures, videos, etc.

[0066] After obtaining the multimedia information for representing the characteristics of the restaurant, the multimedia information can be displayed in a preset area of the preset interface in the case of displaying the output result through the preset interface. The position of the preset area in the preset interface can be set according to actual needs. For example, the multimedia information can be displayed above the display content of the recommended dishes in the preset interface, as shown in Figure 3 For another example, the multimedia information can be displayed in the sidebar of the preset interface.

[0067] Optionally, in the preset area, while the multimedia information is displayed, a sixth interaction component can also be displayed. The sixth interaction component can provide the same function as the fourth interaction component described in the foregoing, that is, for the user to input questions about the restaurant or the dishes, and the large model can call the answers to the questions based on the preset database or the target dish database according to the questions input by the user through the sixth interaction component, and display them through the preset interface. The implementation mode of the sixth interaction component is similar to that of the fourth interaction component, and will not be described here.

[0068] Optionally, the overall process of the dish recommendation method provided by the present disclosure can be as shown in Figure 4 As shown in Figure 4 The method process can include the following contents: The original meal data table is acquired, a meal description text corresponding to each meal is generated by using a large model, and the meal description text is stored in association with meal identification information of the meal to construct a target meal database. User demand information is acquired through a preset interface. A question description text is generated according to the user demand information and database information indicating the target meal database. The question description text is input into a target model to obtain an output result generated by the target model. According to the output result, display content corresponding to each recommended meal is generated, and the display content of each recommended meal is displayed on a preset interface, and multimedia information representing a feature of a restaurant is displayed in a preset area of the preset interface. According to the ordering operation and order confirmation operation of the user on the preset interface, the ordered meal of the user is transmitted to the kitchen system of the restaurant through a network.

[0069] According to the above technical solution, the question description text is generated according to the user demand information provided by the user on the preset interface and the database information about the target meal database. Since the user feature information and the meal demand information of the user are included in the user demand information, the question description text can include the personal situation and meal demand of the user. Then, the question description text is input into the target model, and based on the intelligent analysis capability of the target model as a large model, the meal or meal combination that meets the personal situation and meal demand of the user can be determined from the meals provided in the existing target meal data. Therefore, by providing the personal features and personal demands of the user when ordering, the user can be intelligently positioned to the appropriate meal or meal combination for recommendation in the meals of the restaurant, realizing personalized meal recommendation for the user, and improving the ordering efficiency.

[0070] Figure 5 is a block diagram of a meal recommendation device according to an embodiment of the present disclosure. As shown in Figure 5 the device 50 can include: A first acquisition module 51 is configured to acquire user demand information through a preset interface, wherein the user demand information at least includes user feature information and meal demand information of the user. A first generation module 52 is configured to generate a question description text according to the user demand information and database information. A processing module 53 is configured to input the question description text into a target model, so that the target model generates an output result based on a target meal database indicated by the database information. The target model is a large model, and the output result at least includes a recommended meal and recommendation information of the recommended meal. The first display module 54 is configured to display the output result through the preset interface.

[0071] Optionally, the first acquisition module 51 comprises: The first display sub-module is configured to display a first sub-interface and a second sub-interface through the preset interface, the first sub-interface displays a plurality of preset characteristic items and a first content input area corresponding to each of the preset characteristic items, and the second sub-interface displays a second content input area. The first generation sub-module is configured to generate the user characteristic information according to content input by a user in the first content input area. The second generation sub-module is configured to generate the dining demand information according to content input by the user in the second content input area.

[0072] Optionally, the database information is used to indicate an access mode of the target food database. The first generation module 52 comprises: The acquisition sub-module is configured to acquire a question description template, the question description template comprising a first placeholder used to fill in user characteristics, a second placeholder used to fill in dining demands, a third placeholder used to fill in an access mode of the target food database, and preset instruction text. The third generation sub-module is configured to fill the user characteristic information into the first placeholder, fill the dining demand information into the second placeholder, and fill the database information into the third placeholder, to generate the question description text.

[0073] Optionally, the target food database is generated by the following modules: The second acquisition module is configured to acquire an original food data table, the original food data table comprising food information of a plurality of foods, and each of the food information comprising a first field used to record food identification information and a plurality of second fields used to describe food characteristics. The second generation module is configured to, for each food in the original food data table, generate a food description text corresponding to the food according to field content corresponding to the plurality of second fields, and store the food description text and the food identification information of the food in the target food database in association.

[0074] Optionally, the user demand information further comprises question information of the user. The output result further comprises answer information generated by the target model for the question information.

[0075] Optionally, the apparatus 50 further comprises: A third acquisition module is used to acquire multimedia information for representing restaurant characteristics; The second display module is used to display the multimedia information in a preset area of ​​the preset interface when the output result is displayed through the preset interface.

[0076] Optionally, the first display module 54 includes: a fourth generating submodule, configured to generate, for each of the recommended dishes, recommendation summary information of the recommended dishes according to the recommendation information of the recommended dishes; a fifth generation submodule, for generating, for each of the recommended dishes, display content including recommendation summary information of the recommended dish, a first trigger component, and a second trigger component, wherein the first trigger component is configured to display recommendation information of the recommended dish when triggered, and the second trigger component is configured to add the recommended dish to the ordered dish list when triggered; The second display submodule is used to display the display content of each recommended meal on the preset interface.

[0077] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0078] Based on the same inventive concept, the present disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the meal recommendation method provided in any embodiment of the present disclosure.

[0079] Based on the same inventive concept, the present disclosure further provides an electronic device, including: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the steps of the meal recommendation method provided in any embodiment of the present disclosure.

[0080] Based on the same inventive concept, the present disclosure also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the meal recommendation method provided in any embodiment of the present disclosure.

[0081] Figure 6 FIG. 7 is a block diagram of an electronic device 700 according to an exemplary embodiment. Figure 6 As shown, the electronic device 700 may include: a processor 701 , a memory 702 , and may further include one or more of a multimedia component 703 , an input / output (I / O) interface 704 , and a communication component 705 .

[0082] The processor 701 is configured to control overall operations of the electronic device 700 to complete all or part of the steps of the meal recommendation method described above. The memory 702 is configured to store various types of data to support operations of the electronic device 700, which can include, for example, instructions for any application or method operating on the electronic device 700, and application-related data, such as contact data, transmitted and received messages, pictures, audio, video, and the like. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, or an optical disk. The multimedia component 703 can include a screen and an audio component. The screen can be, for example, a touch screen, and the audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory 702 or transmitted through the communication component 705. The audio component also includes at least one speaker configured to output audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 705 is configured to perform wired or wireless communication between the electronic device 700 and other devices. The wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so the corresponding communication component 705 can include a Wi-Fi module, a Bluetooth module, and an NFC module.

[0083] In an exemplary embodiment, the electronic device 700 can be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors, or other electronic elements for performing the above-described meal recommendation method.

[0084] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the above-described meal recommendation method. For example, the computer-readable storage medium can be the above-described memory 702 including program instructions, which can be executed by the processor 701 of the electronic device 700 to complete the above-described meal recommendation method.

[0085] In another exemplary embodiment, a computer program product is also provided, which contains a computer program capable of being executed by a processor, which, when executed by the processor, implements the steps of the above-described meal recommendation method.

[0086] The preferred embodiments of the present disclosure are described in detail above with reference to the accompanying drawings, but the present disclosure is not limited to the specific details in the above-described embodiments. Various simple modifications can be made to the technical solutions of the present disclosure within the technical concept of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.

[0087] In addition, it should be noted that each specific technical feature described in the above-described specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, various possible combinations are not described again by the present disclosure.

[0088] Furthermore, any combination of the various different embodiments of the present disclosure can also be made, as long as it does not deviate from the idea of the present disclosure, and it should be considered as the disclosed content of the present disclosure.

Claims

1. A meal recommendation method, characterized in that: The method comprises: Obtaining user demand information through a preset interface, wherein the user demand information includes at least user feature information and user dining demand information; Generate a problem description text based on the user demand information and database information; Inputting the problem description text into a target model, so that the target model generates an output result based on the target meal database indicated by the database information, wherein the target model is a large model, and the output result includes at least a recommended meal and recommendation information of the recommended meal; The output result is displayed through the preset interface.

2. The method according to claim 1, characterized in that The obtaining of user demand information through a preset interface includes: Displaying a first sub-interface and a second sub-interface through the preset interface, wherein the first sub-interface displays a plurality of preset feature items and a first content input area corresponding to each of the preset feature items, and the second sub-interface displays a second content input area; generating the user characteristic information according to the content input by the user into the first content input area; The dining demand information is generated according to the content input by the user in the second content input area.

3. The method according to claim 1, characterized in that The database information is used to indicate the access method of the target food database; Generating a problem description text according to the user demand information and database information includes: Obtaining a question description template, the question description template including a first placeholder for filling in user characteristics, a second placeholder for filling in dining requirements, a third placeholder for filling in an access method for the target meal database, and a preset instruction text; The user feature information is filled into the first placeholder, the dining demand information is filled into the second placeholder, and the database information is filled into the third placeholder to generate the problem description text.

4. The method according to claim 1, wherein The target meal database is generated in the following manner: Obtaining an original meal data table, wherein the original meal data table includes meal information of a plurality of meals, each of the meal information including a first field for recording meal identification information and a plurality of second fields for describing meal characteristics; For each meal in the original meal data table, a meal description text corresponding to the meal is generated based on the field contents corresponding to the multiple second fields, and the meal description text is associated with the meal identification information of the meal and stored in the target meal database.

5. The method according to claim 1, wherein The user demand information also includes the user's problem information; The output result also includes answer information generated by the target model in response to the question information.

6. The method according to claim 1, characterized in that The method further comprises: Acquiring multimedia information for characterizing restaurant features; When the output result is displayed through the preset interface, the multimedia information is displayed in a preset area of ​​the preset interface.

7. The method according to claim 1, characterized in that The displaying of the output result through the preset interface includes: For each of the recommended dishes, generating recommendation summary information of the recommended dishes according to the recommendation information of the recommended dishes; For each recommended dish, generating display content including recommendation summary information of the recommended dish, a first trigger component, and a second trigger component, wherein the first trigger component is used to display recommendation information of the recommended dish when triggered, and the second trigger component is used to add the recommended dish to the ordered dish list when triggered; The display content of each recommended meal is displayed on the preset interface.

8. A food recommendation device, characterized in that: The device comprises: A first acquisition module is used to acquire user demand information through a preset interface, wherein the user demand information includes at least user feature information and user dining demand information; A first generating module is used to generate a problem description text according to the user demand information and database information; a processing module, configured to input the problem description text into a target model, so that the target model generates an output result based on the target meal database indicated by the database information, wherein the target model is a large model, and the output result includes at least a recommended meal and recommendation information about the recommended meal; The first display module is used to display the output result through the preset interface.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 7.

11. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images