Automatic ordering method and device for catering service, electronic equipment and storage medium

Abstract

The invention relates to the field of data request processing, and discloses an automatic ordering method for catering service, which comprises the following steps: receiving a reservation ordering request of a user for a take-out commodity; acquiring historical behavior data, calculating preferred dishes of the user according to the historical behavior data, and determining a first feature vector of the user's preferred take-out commodity according to the preferred dishes; obtaining take-out commodities sold in a preset range, extracting key words of each take-out commodity from the commodity description information of each take-out commodity, determining take-out commodities which are the same as or similar to the preferred dishes according to the key words, and generating a corresponding second feature vector for each determined take-out commodity; and calculating the similarity between the first feature vector and each second feature vector, selecting the take-out commodity with the maximum similarity value as a target take-out commodity of the ordering reservation request, and ordering. According to the preference dishes of the user and the reservation time, the user is automatically helped to complete the ordering service.

Description

Technical Field

[0001] The present invention relates to the field of data request processing, and in particular to a method, device, electronic equipment and storage medium for automatic ordering of catering services. Background Art

[0002] With the rapid development of cities, online food ordering has become an indispensable part of modern life, meeting people's basic dining needs in a fast-paced life.

[0003] Although existing food delivery platforms provide a wide variety of dishes for users to choose from, the following problems still exist:

[0004] 1. Users are usually required to manually select dishes from a large number of dishes, and the system cannot make accurate recommendations based on users' dietary preferences and special requirements (such as dietary taboos).

[0005] 2. In their busy work schedules, users may forget to order food, and food delivery platforms lack an effective automatic ordering mechanism, which not only affects the user's dining experience but also brings inconvenience to their daily plans.

[0006] Therefore, how to make personalized recommendations based on user preferences and automatically help users complete their orders, thereby solving the inconvenience caused by users forgetting to order, has become a technical problem that needs to be solved urgently. Summary of the invention

[0007] In view of the above, it is necessary to provide an automatic ordering method for catering services, the purpose of which is to automatically help users complete the ordering service according to the user's preferences.

[0008] The automatic ordering method for catering services provided by the present invention comprises:

[0009] Receive a reservation order request for takeaway goods submitted by a user on the online platform, wherein the reservation order request includes the scheduled order time, delivery address, and type of takeaway goods;

[0010] Acquire historical behavior data of the user on the network platform, calculate the user's preferred dishes according to the historical behavior data, and determine a first feature vector of the user's preferred takeaway products according to the preferred dishes;

[0011] According to the coordinate information of the delivery address and the type of takeaway goods, takeaway goods on sale within a preset range are obtained, key words of each takeaway product are extracted from the product description information of each takeaway product, takeaway products that are the same as or similar to the preferred dishes are determined according to the key words, and a corresponding second feature vector is generated for each determined takeaway product;

[0012] Calculate the similarity between the first feature vector and the second feature vector of each determined takeaway product, select the takeaway product with the largest similarity value as the target takeaway product of the reservation order request, and place an order for the target takeaway product according to the order time and the delivery address.

[0013] Optionally, the historical behavior data is historical ordering data, and the historical ordering data includes ordering frequency, post-meal ratings, and dish prices. The calculating the user's preferred dishes based on the historical behavior data includes:

[0014] Identify each dish ordered by the user from the historical ordering data;

[0015] Substitute the ordering frequency, post-meal rating and price of each dish into a predetermined calculation formula to calculate the preference intensity value corresponding to each dish;

[0016] The dishes whose preference strength values ​​are greater than a preset threshold are determined as the user's preferred dishes.

[0017] Optionally, the historical behavior data of the user on the network platform includes browsing behavior, search behavior and interactive behavior, and the calculating the user's preferred dishes based on the historical behavior data includes:

[0018] Extracting keywords associated with dishes from the browsing behavior, the search behavior, and the interactive behavior;

[0019] The user's part-of-speech definition for each keyword is analyzed, and the user's preferred dishes are determined according to the word frequency and part-of-speech definition of each keyword.

[0020] Optionally, the product description information includes a product picture, and extracting key words of each takeaway product from the product description information of each takeaway product includes:

[0021] Identify the name of each food in the product image, and obtain description information of each food from a preset label record table according to the food name;

[0022] Keywords of the product image are extracted from the description information, and all the keywords are collected to obtain the key words.

[0023] Optionally, the product description information includes a product video, and extracting key words for each takeaway product from the product description information of each takeaway product includes:

[0024] Extracting key frames of the product video and identifying the name of each food in the key frames;

[0025] The description information of each food is obtained from a preset label record table according to the food name, the keywords of the product video are extracted from the description information, and all the keywords are collected to obtain the key words.

[0026] Optionally, the order time includes a scheduled order time, and placing an order for the target takeaway product according to the order time and the delivery address includes:

[0027] In response to the scheduled order time, obtaining a link to the target takeaway product;

[0028] The address item in the link fills in the delivery address and generates an order for the target takeaway product.

[0029] Optionally, the order time includes a delivery time, and placing an order for the target takeaway product according to the order time and the delivery address includes:

[0030] Calculating a first distance between the merchant address corresponding to the target takeaway product and the delivery address;

[0031] Calculate the time taken to reach the delivery address from the merchant address according to the first distance, and calculate the time to place an order for the target takeaway product according to the delivery time and the time taken;

[0032] When the time for placing an order for the target takeaway product is reached, obtaining a link to the target takeaway product;

[0033] The address item in the link fills in the delivery address and generates an order for the target takeaway product.

[0034] In order to solve the above problems, the present invention also provides an automatic order placing device for catering services, the device comprising:

[0035] A receiving module, used to receive a reservation order request for takeaway goods submitted by a user on a network platform, wherein the reservation order request includes a scheduled order time, a delivery address, and a type of takeaway goods;

[0036] A calculation module, used to obtain the historical behavior data of the user on the network platform, calculate the user's preferred dishes according to the historical behavior data, and determine the first feature vector of the user's preferred takeaway products according to the preferred dishes;

[0037] an extraction module, configured to obtain takeaway products on sale within a preset range according to the coordinate information of the delivery address and the type of takeaway products, extract key words of each takeaway product from the product description information of each takeaway product, determine takeaway products that are the same as or similar to the preferred dishes according to the key words, and generate a corresponding second feature vector for each determined takeaway product;

[0038] An ordering module is used to calculate the similarity between the first feature vector and the second feature vector of each determined takeaway product, select the takeaway product with the largest similarity value as the target takeaway product of the reservation order request, and place an order for the target takeaway product according to the order time and the delivery address.

[0039] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0040] at least one processor; and,

[0041] a memory communicatively connected to the at least one processor; wherein,

[0042] The memory stores an automatic catering service ordering program executable by the at least one processor, and the automatic catering service ordering program is executed by the at least one processor so that the at least one processor can execute the automatic catering service ordering method described above.

[0043] In order to solve the above problems, the present invention also provides a computer-readable storage medium, on which an automatic catering service ordering program is stored. The automatic catering service ordering program can be executed by one or more processors to implement the above-mentioned automatic catering service ordering method.

[0044] Compared with the prior art, the present invention receives a reservation order request for takeaway goods submitted by a user on a network platform, the reservation order request includes a scheduled order time, a delivery address and a type of takeaway goods; obtains historical behavior data of the user on the network platform, calculates the user's preferred dishes based on the historical behavior data, and determines a first feature vector of the user's preferred takeaway goods based on the preferred dishes; obtains takeaway goods on sale within a preset range based on the coordinate information of the delivery address and the type of takeaway goods, extracts key words for each takeaway product from the product description information of each takeaway product, determines takeaway products that are the same or similar to the preferred dishes based on the key words, and generates a corresponding second feature vector for each determined takeaway product; calculates the similarity between the first feature vector and the second feature vector of each determined takeaway product, selects the takeaway product with the largest similarity value as the target takeaway product of the reservation order request, and places an order for the target takeaway product based on the order time and the delivery address.

[0045] The present invention obtains the user's preferred dishes by analyzing historical behavior data, obtains the first feature vector of the user's preferred takeaway products based on the user's preferred dishes, and obtains the coordinate information of the delivery address to obtain the second feature vector of the takeaway products on sale within a preset range, and calculates the similarity between the first feature vector and each second feature vector, thereby selecting the takeaway product with the largest similarity value as the target takeaway product for the reservation order request, and automatically selecting the target takeaway product at a specified time to complete the order process, thereby solving the technical problems that users are prone to forget to order and that existing takeaway platforms are difficult to make accurate recommendations based on users' dietary preferences. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic diagram of a flow chart of a method for automatically placing an order for catering services provided in one embodiment of the present invention;

[0047] Figure 2 A schematic diagram of a module of an automatic order placing device for catering services provided by an embodiment of the present invention;

[0048] Figure 3 A schematic diagram of the structure of an electronic device for implementing an automatic ordering method for catering services provided by an embodiment of the present invention;

[0049] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0051] It should be noted that the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0052] Reference Figure 1 FIG. 1 is a flow chart of a method for automatically placing an order for a catering service provided by an embodiment of the present invention. The method is executed by an electronic device.

[0053] In this embodiment, the automatic ordering method for catering services includes:

[0054] S1. Receive a reservation order request for takeaway goods submitted by a user on a network platform, wherein the reservation order request includes a scheduled order time, a delivery address, and a type of takeaway goods.

[0055] In this embodiment, the user submits a reservation order request in the ordering system of the network platform (eg, a food delivery service platform, a merchant's application).

[0056] A network platform refers to an online service system built through Internet technology, which is used to connect users and service providers and provide various online services and information exchange functions. In the network platform, users can access and use these services through web pages, mobile applications or other digital terminals. The network platform of the present invention refers to an online platform that provides takeaway services.

[0057] User refers to the user who initiates a reservation order request and uses the ordering system to automatically place an order.

[0058] The reservation order request is used to reserve future takeaway orders. The reservation order request must contain at least two key information: the scheduled order time and the delivery address:

[0059] The scheduled order time is the specific time the user chooses to place an order in the ordering system. The scheduled order time includes the scheduled order time or the delivery time.

[0060] The scheduled order time is the time when the ordering system automatically places an order for the user (for example, automatically placing an order for the user at 5 pm every day), and the delivery time is the time when the takeaway items selected by the user are delivered to the delivery address (for example, if the user wants to receive the takeaway at 12:30 pm the next day, the ordering system may need to automatically place an order at 12 noon the next day based on the ordering distance and traffic congestion).

[0061] The types of takeaway products refer to the broad categories of food or drinks that users wish to order. The types of takeaway products can help online platforms understand users' dietary preferences more accurately, thereby providing more personalized services. Specifically, the types of takeaway products may include, but are not limited to, the following categories:

[0062] Cuisine: Such as Sichuan cuisine, Cantonese cuisine, Hunan cuisine, Northeastern cuisine, etc. Different cuisines have their own unique flavors and cooking methods.

[0063] Food types: such as fast food, pasta, barbecue, hot pot, dessert, vegetarian food, etc., covering various types of food.

[0064] Special needs: such as sugar-free, low-fat, gluten-free, organic food, etc., for users with specific health or dietary requirements.

[0065] Beverages: such as coffee, tea, juice, milk tea, etc., specifically refers to various types of beverages.

[0066] In other embodiments, the reservation order request may also include the amount pre-charged by the user in the ordering system, or the payment method bound to the payment order (for example, the payment method includes electronic payment tools, bank cards, third-party payment platforms, etc.).

[0067] In the present invention, Example H is used as a specific usage scenario for full description and understanding, and is not intended to be a limitation on all scenarios:

[0068] For example, suppose there is a user A who often uses food delivery platform B to order food and has installed the corresponding mobile application. User A is a busy office worker who often forgets to order food due to busy work. Recently, user A discovered that food delivery platform B has released a new automatic ordering feature, so he decided to use this new feature to help himself order food automatically.

[0069] User A sets up a reservation order request through the application of food delivery platform B, specifying that the order will be automatically placed at 5 pm on Friday so that he can receive dinner around 7 pm. The delivery address set is his apartment address, and the type of food to be delivered is Sichuan cuisine.

[0070] In step S1, users can arrange their dining time in advance through a simple reservation order request, without having to be distracted to order food during busy hours, thereby solving the problem that busy work schedules may cause users to forget to order food, affecting dining experience and daily plans.

[0071] S2. Obtain the historical behavior data of the user on the network platform, calculate the user's preferred dishes based on the historical behavior data, and determine the first feature vector of the user's preferred takeaway products based on the preferred dishes.

[0072] In this embodiment, historical behavior data of users within a preset time period (eg, the past 10 days or 30 days) on the network platform is collected, and the historical behavior data includes historical ordering data.

[0073] Perform data cleaning on the historical ordering data to obtain cleaned historical ordering data. For example, data cleaning includes deleting invalid data (such as duplicate data) and abnormal data (such as obviously erroneous data points), etc., to ensure the accuracy of subsequent analysis.

[0074] Historical ordering data refers to the data records generated by users in the process of using catering services on the online platform, including ordering frequency, post-meal ratings, dish prices and other information, which records the actual ordering behavior and feedback of users. By analyzing the ordering frequency and preferences of users, it is possible to more accurately recommend dishes that users may like. The ordering frequency refers to the average number of orders within a preset time; the post-meal rating refers to the average rating within a preset time; and the dish price refers to the average price within a preset time.

[0075] Analyze the cleaned historical ordering data, which includes but is not limited to the ordering frequency, post-meal score and price of each dish. Define a corresponding dimension for one or more of the ordering frequency, post-meal score and price of each dish, record the ordering frequency, post-meal score and price of each dish in the corresponding dimension, determine the user's preferred dishes according to the numerical value of each dimension, and determine the first eigenvector of the user's preferred takeaway products according to the preferred dishes.

[0076] Continuing with the above example H: Get the historical ordering data of user A in the past period of time, assign a dimension to the ordering frequency, post-meal rating and price of each dish from the historical ordering data, and record the preference intensity of user A for the dish at the corresponding position of the corresponding dimension. Analyze that user A often orders spicy chicken and scrambled eggs with tomatoes. For example, user A ordered spicy chicken 15 times and scrambled eggs with tomatoes 10 times in the past 30 days. The average rating for spicy chicken is 4.7 stars, and the average rating for scrambled eggs with tomatoes is 4.6 stars. The average price of spicy chicken is 20 yuan, and the average price of scrambled eggs with tomatoes is 15 yuan.

[0077] Use a preset calculation formula to calculate the preference strength (for example, the preference strength calculation formula for spicy chicken can be: preference strength = (ordering frequency × w1 + post-meal score × w2 + dish price × w3) / (w1 + w2 + w3) = (15 / 30) × w1 + 4.7 × w2 + 20 × w3, where w1, w2, and w3 are weight coefficients of ordering frequency, post-meal score and dish price, respectively), select dishes with preference strength greater than a threshold to determine the user's preferred dishes, and generate a corresponding first eigenvector based on the historical ordering data of the determined preferred dishes (for example, the first eigenvector corresponding to spicy chicken can be [0.5, 4.7, 20]).

[0078] The present invention only lists two dishes, spicy chicken and tomato scrambled eggs, as examples, and may actually include information about more dishes. In this way, a personal user preference model can also be constructed based on the user's historical ordering data, thereby better providing personalized services to the user.

[0079] In one embodiment, the method further comprises:

[0080] The historical ordering data is cleaned, and the data cleaning at least includes removing invalid data and abnormal data.

[0081] Perform data cleaning on historical ordering data to obtain cleaned historical ordering data, such as deleting invalid data (such as duplicate data) and abnormal data (such as obviously erroneous data points), etc., to ensure the accuracy of subsequent analysis.

[0082] In one embodiment, the historical behavior data is historical ordering data, and the historical ordering data includes ordering frequency, post-meal ratings, and dish prices. The step of calculating the user's preferred dishes based on the historical behavior data includes:

[0083] Identify each dish ordered by the user from the historical ordering data;

[0084] Substitute the ordering frequency, post-meal rating and price of each dish into a predetermined calculation formula to calculate the preference intensity value corresponding to each dish;

[0085] The dishes whose preference strength values ​​are greater than a preset threshold are determined as the user's preferred dishes.

[0086] Corresponding dimensions are defined for the ordering frequency, post-meal rating, and price of each dish. These dimensions are used to represent the different attributes of each dish.

[0087] Collect the specific values ​​of each dish in these three dimensions. For example: Order frequency: the number of times a dish is ordered per week or per month. Post-meal rating: the user's satisfaction rating of the dish, usually 1 to 5 stars. Dish price: the unit price of the dish.

[0088] For each dish, a vector containing the values ​​of the three dimensions is constructed based on the values ​​of the three dimensions. For example, if the ordering frequency of a dish is 3 times a week, the rating is 4.5 stars, and the price is 25 yuan, then the vector representation of the dish can be (3, 4.5, 25). The comprehensive score of each dish is calculated based on the vector representation of each dish, and the dishes are sorted according to the comprehensive score. The first few dishes with higher ranking scores (for example, the first 5) are selected as the user's preferred dishes.

[0089] In other embodiments, a weight may be assigned to each dimension of the dishes, and the weight may be set according to actual conditions. For example, if the post-meal score is considered more important, a higher weight may be given to the post-meal score. Finally, the comprehensive score of each dish is calculated based on the vector representation and weight of each dish. Each dish is ranked according to its comprehensive score, and the top few dishes with higher ranking scores (e.g., the top 5) are selected as the user's preferred dishes.

[0090] In one embodiment, the method further comprises:

[0091] Input the historical ordering data into a preset user preference model, analyze the ordering frequency, post-meal rating and dish price of each dish, and obtain a feature vector for each dish;

[0092] The feature vectors of all dishes are aggregated according to a preset aggregation rule to obtain a first feature vector of the user's preference for takeaway products.

[0093] The ordering frequency, post-meal ratings, and price information of each dish are extracted from the historical order data and preprocessed, such as removing invalid data or outliers in the data to ensure data quality.

[0094] Input the preprocessed data into the user preference model, define three features for each dish (ordering frequency, post-meal rating, and dish price), and convert the above three features into specific values. Based on these specific values, construct a vector containing ordering frequency, post-meal rating, and dish price for each dish. For example, for dish X, assuming the ordering frequency is 2 times / week, the post-meal rating is 4.5 stars, and the dish price is 25 yuan, the vector can be expressed as (2,4.5,25).

[0095] Get the preset aggregation rule. The preset aggregation rule is to define how to aggregate the feature vectors of individual dishes into the overall preference feature vector of the user according to business requirements. For example, the preset aggregation rule can be a weighted average of the feature vectors of each dish according to the ordering frequency of the dish.

[0096] The weighted average of the feature vectors of all dishes is calculated according to the defined aggregation rules to obtain the first feature vector of the user's preference for takeaway products.

[0097] Historical ordering data refers to various data records generated when users use catering services on the online platform. These data records reflect the user's catering consumption habits and preferences. Historical ordering data includes the following aspects:

[0098] 1. Order frequency: The number of times a user orders each dish. For example, user A has ordered Kung Pao Chicken several times in the past month.

[0099] 2. Post-meal rating: The user's evaluation of the ordered dishes, usually in the form of star ratings. For example, user A rated Kung Pao Chicken 4.5 stars.

[0100] 3. Dish price: the amount paid by user A for the ordered dish. Dish price can reflect user A’s attitude towards price, such as whether he tends to choose dishes with high cost performance or whether he is willing to pay a higher price for high-quality dishes.

[0101] 4. Dish preference: The types of dishes preferred by user A, such as whether he prefers vegetarian or meat dishes, light or heavy flavors, etc.

[0102] 5. Ordering time: The time of day when user A usually orders food, such as lunch time, dinner time, or midnight snack time.

[0103] By collecting historical ordering data and analyzing it using user preference models, the system can better understand users' dining preferences and habits, and thus provide more personalized services, such as accurately recommending dishes that users may like, or automatically placing orders for dishes that users typically order during specific time periods.

[0104] Building a user preference model includes the following steps:

[0105] 1. Collect users’ historical ordering data / online behavior data:

[0106] Collect users' historical ordering data: collect users' ordering records, ratings, comments, etc. on the platform. User information: includes users' personal information (such as age, gender, etc.), geographic location, etc.

[0107] Network behavior data: such as users’ browsing history and search history on the network platform.

[0108] 2. Preprocess the collected data (including data cleaning, data standardization and feature engineering):

[0109] Data cleaning: remove duplicate data, handle missing values, correct errors, etc. Data standardization: normalize or standardize numerical data to make data of different dimensions comparable. Feature engineering: construct new features, such as extracting date, time and other features from timestamps.

[0110] 3. Feature extraction from preprocessed data:

[0111] Extract ordering data features: ordering frequency, dish ratings, price sensitivity, etc. Extract network behavior features: number of views, search keywords, comment sentiment analysis scores, etc. Extract user attribute features: age, gender, occupation, etc. Context features: ordering time, weather conditions, holidays, etc.

[0112] 4. Select learning algorithms and deep learning models to build the initial user preference model:

[0113] Choose the appropriate machine learning algorithm: such as logistic regression, decision tree, random forest, support vector machine, etc. Deep learning model: such as convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory network (LSTM), Transformer, etc.

[0114] 5. Train the initial user preference model:

[0115] The dataset after feature extraction is divided into a training set and a validation set. The training set data is used to train the initial user preference model, and the validation set is used to validate the trained initial user preference model. The hyperparameters of the model are adjusted through methods such as cross-validation to optimize the performance.

[0116] The trained user preference model is integrated into the ordering system. Every time a user orders food, the ordering system updates the model prediction in real time based on the latest historical behavior data, and retrains the model regularly to maintain its effectiveness.

[0117] Through the above steps, an effective user preference model can be built to better understand and predict users' dining preferences and provide users with more personalized recommendation services.

[0118] For example, we collect the ordering data of users within 30 days, and analyze the ordering data to find that user A often orders spicy chicken and scrambled eggs with tomatoes, and gives high ratings. In this case, spicy chicken and scrambled eggs with tomatoes can be considered as user A's "preferred dishes". The ordering frequency, post-meal ratings, and prices of these two dishes, spicy chicken and scrambled eggs with tomatoes, are converted into numerical representations (i.e., representation vectors), thereby obtaining the first eigenvector of user A.

[0119] In one embodiment, the historical behavior data of the user on the network platform includes browsing behavior, search behavior, and interactive behavior, and calculating the user's preferred dishes based on the historical behavior data includes:

[0120] Extracting keywords associated with dishes from the browsing behavior, the search behavior, and the interactive behavior;

[0121] The user's part-of-speech definition for each keyword is analyzed, and the user's preferred dishes are determined according to the word frequency and part-of-speech definition of each keyword.

[0122] Obtain the user's network behavior data within a preset time period (e.g., the past 10 days or 30 days) on the network platform.

[0123] Online behavior data refers to data related to users' activities on online platforms (such as food delivery service platforms and merchants' applications), including browsing behavior, search behavior, interactive behavior, etc. Online behavior data reflects more of users' online exploration and interactive behavior rather than direct consumption behavior.

[0124] Specifically, in the present invention, network behavior data mainly includes the following categories:

[0125] 1. Browsing behavior: the food pages that users have browsed on the online platform, including the time, frequency, duration, etc. For example, the food categories or features that user A focused on when browsing, and browsed a certain type of food multiple times.

[0126] 2. Search behavior: Keywords that user A has searched for on the online platform, such as specific dish names or dining styles, as well as search frequency and clicks on search results.

[0127] 3. Interactive behavior: interactive activities conducted by users on the online platform, including comments, likes, and favorites on dishes or merchants. For example, user A’s positive or negative feedback on a specific dish or merchant.

[0128] By collecting and analyzing these online behavior data, we can more accurately understand users' eating preferences and habits, and provide users with more personalized and considerate services, such as calculating dishes that users may be interested in and automatically placing orders for dishes that users typically choose at specific times.

[0129] Extract keywords related to specific attribute information of dishes (e.g., cuisine (e.g., Hunan cuisine, Cantonese cuisine, Sichuan cuisine, etc.), main ingredients (e.g., chicken, duck, fish, meat, etc.), cooking methods (e.g., braised, steamed, fried, etc.), flavors (e.g., spicy, sweet, salty, etc.)) from network behavior data. The process of extracting keywords is to analyze the user's network behavior data to find out the words related to dishes that the user may be interested in or concerned about. For example, if the user often searches for the methods or comments of "spicy chicken" or "scrambled eggs with tomatoes" on the Internet, then these words will be extracted as keywords.

[0130] Analyze the user's part-of-speech definition of each keyword, and determine the user's preferred dishes based on the word frequency and part-of-speech definition of each keyword, as follows:

[0131] Analyze the user's part-of-speech definition of each keyword. For example, if user A has posted on the online platform that he suffers from high blood pressure and needs to avoid pickled dishes or mentioned in the comments that he does not like coriander, then the part-of-speech of "pickled dishes" and "coriander" is negative for user A. Or, if user A has posted on the online platform that he likes "scrambled eggs with tomatoes", then the part-of-speech of "scrambled eggs with tomatoes" is positive for user A.

[0132] The frequency of the extracted keywords is used to determine which dishes the user may like. For example, if the user searches for "spicy chicken" very frequently, it may be considered that the user likes the dish spicy chicken.

[0133] In other implementations, a user preference model (such as a GPT-4 model) may be constructed to analyze the association between keywords and each dish, thereby determining the preferred dishes that the user is interested in. For example, if the user searches for "spicy chicken" far more times than other dishes, the system will consider "spicy chicken" as a preferred dish of the user.

[0134] In step S2, by analyzing the user's historical ordering data and / or online behavior data on the online platform, the user's dietary preferences can be understood more accurately, thereby providing dish recommendations that are more in line with the user's taste, solving the problem that existing food delivery platforms are difficult to make accurate recommendations based on the user's dietary preferences and special requirements.

[0135] S3. According to the coordinate information of the delivery address and the type of takeaway goods, obtain the takeaway goods on sale within a preset range, extract key words for each takeaway product from the product description information of each takeaway product, determine the takeaway products that are the same as or similar to the preferred dishes according to the key words, and generate a corresponding second feature vector for each determined takeaway product.

[0136] In this embodiment, based on the coordinate information of the delivery address (for example, 3 kilometers or 5 kilometers around) and the type of takeout food that the user has reserved and ordered (for example, Sichuan cuisine), a list of takeout food related to Sichuan cuisine provided by the merchant is obtained, and the key words of each takeout food in the takeout food list are obtained. If the preferred dish is "spicy chicken", and there are takeout food keywords associated with spicy chicken, then it is determined that the takeout food is the same as the preferred dish.

[0137] If the preferred dish is "spicy chicken", then the specific attribute information of "spicy chicken" is determined (for example, the cuisine (for example, Hunan cuisine, Cantonese cuisine, Sichuan cuisine, etc.), main ingredients (for example, chicken, duck, fish, meat, etc.), cooking methods (for example, braised, steamed, fried, etc.), taste (for example, spicy, sweet, salty, etc.)); if there is a takeaway product that corresponds to a keyword that is different from "spicy chicken" but has the same specific attribute information, then the takeaway product is determined to be similar to the preferred dish.

[0138] For example, if a certain takeaway product has been ordered 300 times in the past 30 days, a total of 140 customers have ordered it, the average rating of spicy chicken is 4.8 stars, and the average price of spicy chicken is 22 yuan. The second feature vector corresponding to the determined takeaway product can be [(140 / 300), 4.8, 22]).

[0139] According to the takeaway product list, the product description information of each takeaway product is obtained. The product description information usually includes text information, product pictures and product videos. The product description information records the name of the dish, main ingredients, cooking methods, price, etc. By obtaining the description information, the characteristics of each takeaway product can be understood.

[0140] The key words of each takeaway product are extracted from the product description information of each takeaway product, and the second feature vector of each takeaway product is determined according to the key words. Specifically:

[0141] When the product description information is text information, the text information is segmented to obtain a segmentation result, keywords of the text information are extracted from the segmentation result, and all keywords are collected to obtain key words.

[0142] When the product description information is a product picture, each food in the product picture is identified, the description information of each food is obtained from a preset label record table according to the name of the food, the keywords of the product picture are extracted from the description information, and all the keywords are collected to obtain key words.

[0143] When the product description information is a product video, extract the key frames of the product video, identify each food in the key frames, obtain the description information of each food from a preset label record table according to the name of the food, extract the keywords of the product video from the description information, and collect all the keywords to obtain key words.

[0144] Alternatively, the audio of the product video is converted into text information, the text information is segmented to obtain the segmentation result, the keywords of the product video are extracted from the segmentation result, and all the keywords are collected to obtain the key words.

[0145] Finally, each keyword of the key vocabulary is converted into a representation vector through word embedding technology (such as Word2Vec or BERT), and the second feature vector of each takeaway product is constructed based on the representation vector.

[0146] In one embodiment, the product description information includes text information, and extracting key words of each takeaway product from the product description information of each takeaway product includes:

[0147] Performing word segmentation on the text information to obtain a word segmentation result;

[0148] Keywords of the text information are extracted from the word segmentation results, and all the keywords are collected to obtain the key words.

[0149] Preprocess the text information (for example, replace punctuation marks and special characters in the text with spaces or delete them or convert the text to lowercase or uppercase to reduce repetition), and use the preset word segmentation tools (such as Jieba word segmentation, NLTK, etc.) to segment the preprocessed text information to obtain the word segmentation results. Use the preset keyword algorithm (such as TF-IDF, TextRank, etc.) to extract keywords from the word segmentation results, and collect all the keywords to obtain key words.

[0150] In one embodiment, the product description information includes a product picture, and extracting key words of each takeaway product from the product description information of each takeaway product includes:

[0151] Identify the name of each food in the product image, and obtain description information of each food from a preset label record table according to the food name;

[0152] Keywords of the product image are extracted from the description information, and all the keywords are collected to obtain the key words.

[0153] Perform image preprocessing on the product image (for example, perform necessary enhancement operations on the image, such as adjusting brightness, contrast, etc., and use image segmentation technology to separate different food areas in the product image), and use a preset food recognition model (for example, a food recognition model trained using a deep learning model (such as a convolutional neural network CNN)) to identify each food in the product image after image preprocessing to obtain the category or name of each food.

[0154] Obtain a label record table. The label record table is a mapping table for establishing food and description information. According to the name of the food, obtain the description information of each food from the label record table, and extract keywords of the product image from the description information.

[0155] In one embodiment, the product description information includes a product video, and extracting key words of each takeaway product from the product description information of each takeaway product includes:

[0156] Extracting key frames of the product video and identifying the name of each food in the key frames;

[0157] The description information of each food is obtained from a preset label record table according to the food name, the keywords of the product video are extracted from the description information, and all the keywords are collected to obtain the key words.

[0158] Extracting key words of takeaway products from product videos can be achieved by referring to the above-mentioned method of extracting key words of takeaway products from text information and product images.

[0159] In one embodiment, the method of determining the takeaway products that are the same as or similar to the preferred dishes according to the key words, and generating a corresponding second feature vector for each determined takeaway product, includes:

[0160] Each keyword of the key words is converted into a representation vector, and a second feature vector of each takeaway product is constructed according to the representation vector.

[0161] In one embodiment, constructing a second feature vector for each takeaway product according to the representation vector includes:

[0162] The representation vectors of the keywords are aggregated according to a preset aggregation rule, and the aggregated representation vectors are normalized to generate a second feature vector for each takeaway product.

[0163] The preset aggregation rule can be to calculate the average vector (for example, to average all keyword vectors) or to perform a weighted sum (for example, to assign a weight to each keyword, usually based on the importance of the keyword, such as a TF-IDF score).

[0164] The aggregated vectors are L2 normalized to become unit vectors, thereby keeping the distance between vectors unchanged. The normalized vectors are used as the second eigenvector of each takeaway product.

[0165] In one embodiment, the method further comprises:

[0166] Extracting user evaluation information of each takeaway product, and converting at least two of the user evaluation information of the takeaway product evaluation quantity score, the dish quality score, and the price satisfaction score into corresponding representation vectors;

[0167] The various representation vectors are collected to obtain the second feature vector of each takeaway product.

[0168] Extract multiple dimension scores of takeaway products from user evaluation information, and convert these scores into vectors represented by numerical values, and then obtain the second feature vector of each takeaway product. The specific process is as follows:

[0169] Feedback from users who have purchased takeaway products (including evaluation quantity scores, food quality scores, price satisfaction scores, etc.) is extracted, each score is represented as the performance of the takeaway product in one dimension, and converted into a vector in numerical form (representation vector), and the second eigenvector of each takeaway product is obtained by combining various representation vectors.

[0170] By analyzing user evaluation information, we can reflect multiple dimensions such as the number of dishes purchased, dish quality and price satisfaction, and more accurately understand the advantages and disadvantages of each dish, thereby improving the accuracy and personalization of recommendations.

[0171] For example, a list of takeaway products on sale in the area where user A is located is obtained, and several dishes are selected for analysis.

[0172] Dish 1: "Spicy Hot Pot"

[0173] User feedback: [evaluation quantity score = 4.5, food quality score = 4.7, price satisfaction score = 4.6], second eigenvector: [4.5, 4.7, 4.6].

[0174] Dish 2: “Tomato Scrambled Eggs”

[0175] User feedback: [evaluation quantity score = 4.3, food quality score = 4.4, price satisfaction score = 4.5], second eigenvector: [4.3, 4.4, 4.5].

[0176] In step S3, by extracting the second feature vector of each takeaway product, the characteristics of each dish can be understood more accurately, so as to better match the user's taste preferences and solve the problem that existing takeaway platforms may only provide limited product information and it is difficult to make accurate dish recommendations based on the user's specific needs and preferences.

[0177] S4. Calculate the similarity between the first feature vector and the second feature vector of each determined takeaway product, select the takeaway product with the largest similarity value as the target takeaway product of the reservation order request, and place an order for the target takeaway product according to the order time and the delivery address.

[0178] In this embodiment, after obtaining the user's first feature vector (representing the user's dining preference) and the second feature vector of each takeaway product (representing the characteristics of each dish), the similarity between the user's first feature vector and the second feature vector of each takeaway product is calculated. The higher the similarity, the more the takeaway product meets the user's taste preference, and the takeaway product with the highest similarity will be selected as the final target takeaway product.

[0179] Specifically, the first feature vector extracted from the user's historical ordering data represents the user's dining preferences. For example, in example H, user A's preferences may be spicy chicken and spicy hot pot.

[0180] The second feature vector extracted based on the description information and / or user evaluation information of each takeaway product represents the characteristics of each takeaway product. For example, the second feature vector of spicy chicken may include description information such as spiciness, chicken meat, taste, and user ratings of its quality, taste, freshness, and price satisfaction.

[0181] Calculate the similarity between the first feature vector and each second feature vector. Similarity calculation methods include cosine similarity, Euclidean distance, etc. In this embodiment, taking cosine similarity as an example, for the second feature vector of each takeaway product, calculate the cosine similarity between the second feature vector and the user's first feature vector. Cosine similarity is a measurement method for measuring the cosine value of the angle between two vector directions. The value range is usually between -1 and 1. The closer the value is to 1, the more similar the two vectors are. After calculating the similarity between all takeaway products and the user's feature vector, select the takeaway product with the largest similarity value as the final target takeaway product, which means that the dish best meets the user's preferences.

[0182] After the target takeaway product is determined, one of the following operations is automatically performed based on the order time and delivery address previously reserved by the user:

[0183] 1. If the order time is the designated scheduled order time, the ordering system will automatically access the link of the target takeaway product at that time, fill in the delivery address provided by the user in the address item in the link, and generate an order for the takeaway product.

[0184] 2. If the order time is a specified delivery time, the ordering system will first calculate the first distance between the merchant address corresponding to the target takeaway product and the delivery address, estimate the time required for delivery based on the first distance, and then reversely calculate the order time.

[0185] When the calculated order time is reached, the ordering system automatically accesses the link of the target takeaway product, fills in the delivery address provided by the user in the address item in the link, and generates an order for the takeaway product.

[0186] Finally, the merchant corresponding to the target takeaway product receives the takeaway product order, prepares the target takeaway product and delivers it according to the delivery address.

[0187] Continuing from Example H, user A has set up a reservation request to automatically place an order at 5pm every weekday so that he can receive dinner at around 7pm, with the delivery address being the address of his apartment.

[0188] Assume that the ordering system has determined that the target takeaway product is spicy chicken, and has calculated that the similarity between spicy chicken and the first feature vector of user A is the highest.

[0189] In one embodiment, the order time includes a scheduled order time, and placing an order for the target takeaway product according to the order time and the delivery address includes:

[0190] In response to the scheduled order time, obtaining a link to the target takeaway product;

[0191] The address item in the link fills in the delivery address and generates an order for the target takeaway product.

[0192] The link of the target takeaway product refers to the URL or identifier of a specific takeaway dish on the ordering system where it is located.

[0193] The user has set a scheduled order time in the ordering system. When this time comes, the ordering system will automatically obtain the link of the target takeaway product and generate a takeaway order using the user's pre-set address information. This function is very useful for users who want to automatically order food at a specific time, which can save users time and ensure that they will not miss meals.

[0194] In one embodiment, the order time includes the delivery time, and placing an order for the target takeaway product according to the order time and the delivery address includes:

[0195] Calculating a first distance between the merchant address corresponding to the target takeaway product and the delivery address;

[0196] Calculate the time taken to reach the delivery address from the merchant address according to the first distance, and calculate the time to place an order for the target takeaway product according to the delivery time and the time taken;

[0197] When the time for placing an order for the target takeaway product is reached, obtaining a link to the target takeaway product;

[0198] The address item in the link fills in the delivery address and generates an order for the target takeaway product.

[0199] In order to let users know when the food will be delivered, so as to better arrange other activities or eat fresh dishes, the present invention provides a setting method of setting the reservation time as the delivery time.

[0200] The actual distance (first distance) from the merchant to the delivery address specified by the user is determined through map services or GPS positioning, and the time required for delivery can be calculated based on the actual distance. The calculation of the time also needs to take into account traffic conditions, the speed of the delivery person, and the merchant's order acceptance situation.

[0201] The most suitable order time can be obtained by subtracting the time required for delivery from the delivery time. When the order time arrives, the ordering system automatically obtains the link of the target takeaway product and uses the user's pre-set address information to generate a takeaway order.

[0202] According to the user's expected delivery time, the order time for the target takeaway product is calculated, and the order is automatically placed when the target takeaway product order time is reached, thus ensuring that the food can be delivered at the time specified by the user. This method is very suitable for people who have fixed dining habits and have strict requirements on delivery time.

[0203] Continuing from Example H, user A has set up a reservation request to receive dinner at around 7pm every weekday, delivered to the address of his apartment.

[0204] Assume that the ordering system has determined that the target takeaway product is spicy chicken, and has calculated that the similarity between spicy chicken and the first feature vector of user A is the highest. The ordering system needs to calculate the distance between the merchant address and the address of user A's apartment. Assuming that the delivery takes about 1 hour, the ordering system will automatically access the order link for spicy chicken at 6 pm, fill in the address of user A's apartment in the address item in the link, and generate a takeaway product order.

[0205] In step S4, by calculating the similarity between the user's first feature vector and the second feature vector of each takeaway product, dishes that suit the user's taste can be recommended more accurately, and the ordering process can be automatically completed at a specified time.

[0206] This solves the problem that users no longer need to spend a lot of time browsing and selecting dishes, nor do they need to worry about forgetting to order due to their busy work schedules.

[0207] The present invention understands the user's dietary preference dishes by analyzing the user's historical ordering data, obtains the first feature vector of the user's preferred takeaway products according to the user's dietary preference dishes, and obtains the coordinate information of the delivery address to obtain the second feature vector of the takeaway products on sale within a preset range, and calculates the similarity between the first feature vector and each second feature vector, thereby selecting the takeaway product with the largest similarity value as the target takeaway product for the reservation order request, and automatically selecting the target takeaway product at a specified time to complete the order process, thereby solving the technical problems that users are prone to forget to order and that existing takeaway platforms are difficult to make accurate recommendations based on users' dietary preferences.

[0208] like Figure 2 , which is a schematic diagram of a module of an automatic order placing device for catering services provided in one embodiment of the present invention.

[0209] The automatic order placing device 100 for catering services of the present invention can be installed in an electronic device. According to the functions to be implemented, the automatic order placing device 100 for catering services can include a receiving module 110, a calculating module 120, an extracting module 130 and an order placing module 140. The module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, and is stored in the memory of the electronic device.

[0210] In this embodiment, the functions of each module / unit are as follows:

[0211] The receiving module 110 is used to receive a reservation order request for takeaway goods submitted by a user on the network platform, wherein the reservation order request includes the scheduled order time, delivery address and type of takeaway goods;

[0212] A calculation module 120 is used to obtain the historical behavior data of the user on the network platform, calculate the user's preferred dishes according to the historical behavior data, and determine a first feature vector of the user's preferred takeaway products according to the preferred dishes;

[0213] The extraction module 130 is used to obtain takeaway products on sale within a preset range according to the coordinate information of the delivery address and the type of takeaway products, extract key words of each takeaway product from the product description information of each takeaway product, determine the takeaway products that are the same as or similar to the preferred dishes according to the key words, and generate a corresponding second feature vector for each determined takeaway product;

[0214] The ordering module 140 is used to calculate the similarity between the first feature vector and the second feature vector of each determined takeaway product, select the takeaway product with the largest similarity value as the target takeaway product of the reservation order request, and place an order for the target takeaway product according to the order time and the delivery address.

[0215] In one embodiment, the historical behavior data is historical ordering data, and the historical ordering data includes ordering frequency, post-meal ratings, and dish prices. The step of calculating the user's preferred dishes based on the historical behavior data includes:

[0216] Identify each dish ordered by the user from the historical ordering data;

[0217] Substitute the ordering frequency, post-meal rating and price of each dish into a predetermined calculation formula to calculate the preference intensity value corresponding to each dish;

[0218] The dishes whose preference strength values ​​are greater than a preset threshold are determined as the user's preferred dishes.

[0219] In one embodiment, the historical behavior data of the user on the network platform includes browsing behavior, search behavior, and interactive behavior, and calculating the user's preferred dishes based on the historical behavior data includes:

[0220] Extracting keywords associated with dishes from the browsing behavior, the search behavior, and the interactive behavior;

[0221] The user's part-of-speech definition for each keyword is analyzed, and the user's preferred dishes are determined according to the word frequency and part-of-speech definition of each keyword.

[0222] In one embodiment, the product description information includes a product picture, and extracting key words of each takeaway product from the product description information of each takeaway product includes:

[0223] Identify the name of each food in the product image, and obtain description information of each food from a preset label record table according to the food name;

[0224] Keywords of the product image are extracted from the description information, and all the keywords are collected to obtain the key words.

[0225] In one embodiment, the product description information includes a product video, and extracting key words of each takeaway product from the product description information of each takeaway product includes:

[0226] Extracting key frames of the product video and identifying the name of each food in the key frames;

[0227] The description information of each food is obtained from a preset label record table according to the food name, the keywords of the product video are extracted from the description information, and all the keywords are collected to obtain the key words.

[0228] In one embodiment, the order time includes a scheduled order time, and placing an order for the target takeaway product according to the order time and the delivery address includes:

[0229] In response to the scheduled order time, obtaining a link to the target takeaway product;

[0230] The address item in the link fills in the delivery address and generates an order for the target takeaway product.

[0231] In one embodiment, the order time includes the delivery time, and placing an order for the target takeaway product according to the order time and the delivery address includes:

[0232] Calculating a first distance between the merchant address corresponding to the target takeaway product and the delivery address;

[0233] Calculate the time taken to reach the delivery address from the merchant address according to the first distance, and calculate the time to place an order for the target takeaway product according to the delivery time and the time taken;

[0234] When the time for placing an order for the target takeaway product is reached, obtaining a link to the target takeaway product;

[0235] The address item in the link fills in the delivery address and generates an order for the target takeaway product.

[0236] like Figure 3 , which is a schematic diagram of the structure of an electronic device for implementing an automatic ordering method for catering services provided by an embodiment of the present invention.

[0237] In this embodiment, the electronic device 1 includes, but is not limited to, a memory 11, a processor 12, and a network interface 13, which can be interconnected and communicated via a system bus. The memory 11 stores an automatic catering service ordering program 10, and the automatic catering service ordering program 10 can be executed by the processor 12. Figure 3 Only the electronic device 1 having components 11-13 and the automatic order placing program 10 for catering services is shown. It can be understood by those skilled in the art that Figure 3 The structure shown does not constitute a limitation on the electronic device 1 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0238] Among them, the memory 11 includes a memory and at least one type of readable storage medium. The memory provides a cache for the operation of the electronic device 1; the readable storage medium may be a non-volatile storage medium such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the readable storage medium may be an internal storage unit of the electronic device 1; in other embodiments, the non-volatile storage medium may also be an external storage device of the electronic device 1, such as a plug-in hard disk equipped on the electronic device 1, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), etc. In this embodiment, the readable storage medium of the memory 11 is generally used to store an operating system and various application software installed on the electronic device 1, such as storing the code of the automatic ordering program 10 for catering services in one embodiment of the present invention. In addition, the memory 11 may also be used to temporarily store various types of data that have been output or are to be output.

[0239] In some embodiments, the processor 12 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor 12 is generally used to control the overall operation of the electronic device 1, such as performing control and processing related to data interaction or communication with other devices. In this embodiment, the processor 12 is used to run the program code stored in the memory 11 or process data, such as running the automatic ordering program 10 for catering services.

[0240] The network interface 13 may include a wireless network interface or a wired network interface, and the network interface 13 is used to establish a communication connection between the electronic device 1 and a terminal (not shown in the figure).

[0241] Optionally, the electronic device 1 may further include a user interface, which may include a display (Display), an input unit such as a keyboard (Keyboard), and the optional user interface may also include a standard wired interface and a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0242] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0243] The automatic order placing program 10 for catering services stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 12, it can achieve:

[0244] Receive a reservation order request for takeaway goods submitted by a user on the online platform, wherein the reservation order request includes the scheduled order time, delivery address, and type of takeaway goods;

[0245] Acquire historical behavior data of the user on the network platform, calculate the user's preferred dishes according to the historical behavior data, and determine a first feature vector of the user's preferred takeaway products according to the preferred dishes;

[0246] According to the coordinate information of the delivery address and the type of takeaway goods, takeaway goods on sale within a preset range are obtained, key words of each takeaway product are extracted from the product description information of each takeaway product, takeaway products that are the same as or similar to the preferred dishes are determined according to the key words, and a corresponding second feature vector is generated for each determined takeaway product;

[0247] Calculate the similarity between the first feature vector and the second feature vector of each determined takeaway product, select the takeaway product with the largest similarity value as the target takeaway product of the reservation order request, and place an order for the target takeaway product according to the order time and the delivery address.

[0248] Specifically, the specific implementation method of the processor 12 for the above-mentioned catering service automatic ordering program 10 can refer to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0249] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable medium can be non-volatile or non-volatile. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0250] The computer-readable storage medium stores an automatic catering service ordering program 10, which can be executed by one or more processors. The specific implementation method of the computer-readable storage medium of the present invention is basically the same as the above-mentioned embodiments of the automatic catering service ordering method, and will not be repeated here.

[0251] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0252] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0253] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0254] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0255] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0256] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The second and other words are used to indicate names, but not to indicate any particular order.

[0257] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for automatically placing an order for catering services, characterized in that: The method comprises: Receive a reservation order request for takeaway goods submitted by a user on the online platform, wherein the reservation order request includes the scheduled order time, delivery address, and type of takeaway goods; Acquire historical behavior data of the user on the network platform, calculate the user's preferred dishes according to the historical behavior data, and determine a first feature vector of the user's preferred takeaway products according to the preferred dishes; According to the coordinate information of the delivery address and the type of takeaway goods, takeaway goods on sale within a preset range are obtained, key words of each takeaway product are extracted from the product description information of each takeaway product, takeaway products that are the same as or similar to the preferred dishes are determined according to the key words, and a corresponding second feature vector is generated for each determined takeaway product; Calculate the similarity between the first feature vector and the second feature vector of each determined takeaway product, select the takeaway product with the largest similarity value as the target takeaway product of the reservation order request, and place an order for the target takeaway product according to the order time and the delivery address.

2. The automatic ordering method for catering services according to claim 1, characterized in that: The historical behavior data is historical ordering data, and the historical ordering data includes ordering frequency, post-meal ratings, and dish prices. The calculating the user's preferred dishes based on the historical behavior data includes: Identify each dish ordered by the user from the historical ordering data; Substitute the ordering frequency, post-meal rating and price of each dish into a predetermined calculation formula to calculate the preference intensity value corresponding to each dish; The dishes whose preference strength values ​​are greater than a preset threshold are determined as the user's preferred dishes.

3. The automatic ordering method for catering services according to claim 1, characterized in that: The historical behavior data of the user on the network platform includes browsing behavior, search behavior and interactive behavior, and the calculation of the user's preferred dishes based on the historical behavior data includes: Extracting keywords associated with dishes from the browsing behavior, the search behavior, and the interactive behavior; The user's part-of-speech definition for each keyword is analyzed, and the user's preferred dishes are determined according to the word frequency and part-of-speech definition of each keyword.

4. The automatic ordering method for catering services according to claim 1, characterized in that: The product description information includes product images, and the key words of each takeaway product are extracted from the product description information of each takeaway product, including: Identify the name of each food in the product image, and obtain description information of each food from a preset label record table according to the food name; Keywords of the product image are extracted from the description information, and all the keywords are collected to obtain the key words.

5. The automatic ordering method for catering services according to claim 1, characterized in that: The product description information includes a product video, and the key words of each takeaway product are extracted from the product description information of each takeaway product, including: Extracting key frames of the product video and identifying the name of each food in the key frames; The description information of each food is obtained from a preset label record table according to the food name, the keywords of the product video are extracted from the description information, and all the keywords are collected to obtain the key words.

6. The automatic ordering method for catering services according to claim 1, characterized in that: The order time includes a scheduled order time, and placing an order for the target takeaway product according to the order time and the delivery address includes: In response to the scheduled order time, obtaining a link to the target takeaway product; The address item in the link fills in the delivery address and generates an order for the target takeaway product.

7. The automatic ordering method for catering services according to claim 1, characterized in that: The order time includes the delivery time, and placing an order for the target takeaway product according to the order time and the delivery address includes: Calculating a first distance between the merchant address corresponding to the target takeaway product and the delivery address; Calculate the time taken to reach the delivery address from the merchant address according to the first distance, and calculate the time to place an order for the target takeaway product according to the delivery time and the time taken; When the time for placing an order for the target takeaway product is reached, obtaining a link to the target takeaway product; The address item in the link fills in the delivery address and generates an order for the target takeaway product.

8. An automatic order placing device for catering services, characterized in that: The device comprises: A receiving module, used to receive a reservation order request for takeaway goods submitted by a user on a network platform, wherein the reservation order request includes a scheduled order time, a delivery address, and a type of takeaway goods; A calculation module, used to obtain the historical behavior data of the user on the network platform, calculate the user's preferred dishes according to the historical behavior data, and determine the first feature vector of the user's preferred takeaway products according to the preferred dishes; an extraction module, configured to obtain takeaway products on sale within a preset range according to the coordinate information of the delivery address and the type of takeaway products, extract key words of each takeaway product from the product description information of each takeaway product, determine takeaway products that are the same as or similar to the preferred dishes according to the key words, and generate a corresponding second feature vector for each determined takeaway product; An ordering module is used to calculate the similarity between the first feature vector and the second feature vector of each determined takeaway product, select the takeaway product with the largest similarity value as the target takeaway product of the reservation order request, and place an order for the target takeaway product according to the order time and the delivery address.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores an automatic catering service ordering program that can be executed by the at least one processor, and the automatic catering service ordering program is executed by the at least one processor so that the at least one processor can execute the automatic catering service ordering method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an automatic ordering program for catering services, and the automatic ordering program for catering services can be executed by one or more processors to implement the automatic ordering method for catering services as described in any one of claims 1 to 7.

Images