CN114547438A - Dish recommendation method and device - Google Patents

Abstract

The present application provides a method and device for recommending dishes. By acquiring a customer ID, the attributes of the customers are determined, and dishes are recommended to the customers according to the attributes of the customers. For old customers, the recommended dishes are determined according to their historical ordering dishes. The more times a customer orders a certain historical dish, the more satisfied the customer is with the dish, which means that the customer may order this one with a higher probability. dishes. Therefore, recommending the dishes with the most ordered dishes in history can improve the accuracy of pushing customers' satisfied dishes to a certain extent.

Description

Method and device for recommending dishes

technical field

The present application relates to the technical field of data processing, and in particular, to a method and device for recommending dishes.

Background technique

With the continuous maturity of Internet technology, more and more traditional industries have begun to adopt Internet technology to break the asymmetric pattern of information, and integrate and utilize the generated big data to maximize resource utilization.

For example, many restaurants are now ordering food online, which not only saves labor costs, but also improves customer experience.

However, when customers order online at offline restaurants, they are likely to be dissatisfied with the recommended dishes due to their unfamiliarity with the dishes, and the recommended dishes are often only the signature dishes in the store.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide a method and device for recommending dishes, which can solve the problem of how to improve the accuracy of pushing dishes that customers are satisfied with.

In order to realize the above-mentioned purpose of the invention, the present invention provides the following technical solutions:

In the first aspect, a method for recommending dishes is provided, including:

Get customer ID;

Determine whether the customer is an old customer according to the ID;

If so, obtain the customer's historical ordering records, the historical ordering records include: ordered dishes, the number of ordered dishes, and the historical ordering records include: the historical ordering records of the restaurant or the history of the ordering platform meal ordering records;

Matching the dishes to be ordered with the dishes to be ordered to obtain matching dishes, and the dishes to be ordered are dishes on the menu;

Among the matching dishes, the dish with the highest order times is selected as the recommended dish, and the recommended dish is recommended to the customer.

In the above method for recommending dishes, the attributes of the customers are determined by obtaining the customer IDs, and dishes are recommended to the customers according to the attributes of the customers. For old customers, the recommended dishes are determined according to their historical ordering dishes. When a customer orders a certain historical dish more times, it means that the customer is more satisfied with the dish, which means that the customer may order this one with a higher probability. dishes. Therefore, recommending the dishes with the most ordered dishes in history can improve the accuracy of pushing customer satisfaction dishes to a certain extent.

In a possible implementation manner of the first aspect, the historical meal ordering record further includes: a dish evaluation, and the method further includes: judging whether the dish evaluation is positive; recommending the dish with the positive dish evaluation to the customer.

In a possible implementation manner of the first aspect, the method further includes: calculating the similarity between the dish to be ordered and the dish to be ordered; selecting the dish for which the similarity is within a preset range as a candidate dish; selecting the dish to be ordered Among the candidate dishes, the dish to be ordered corresponding to the dish with the most order times is regarded as a similar dish; the similar dish is recommended to the customer.

In a possible implementation manner of the first aspect, the historical ordering record further includes: the price of the ordered dish, and the method further includes: calculating an average price of the dish according to the ordered dish and the ordered dish price; The customer recommends dishes in the same price range or adjacent price range as the average price.

In a possible implementation manner of the first aspect, if not, obtain geographic information corresponding to the customer ID; and recommend corresponding dishes according to the geographic information.

In a second aspect, a dish recommendation device is provided, the device comprising:

The first acquisition module is used to acquire the customer ID;

Judging module, for judging whether the customer is an old customer according to the ID;

The second acquisition module is used to acquire the customer's historical ordering records when the customer is an old customer, the historical ordering records include: ordering dishes and the number of times of ordering dishes, and the historical ordering records include: in this restaurant The historical ordering records or the historical ordering records on the ordering platform;

a matching module, configured to match the dishes to be ordered with the dishes to be ordered to obtain matching dishes, and the dishes to be ordered are dishes on the menu;

The first recommendation module is configured to select the dish with the highest ordering times among the matching dishes as the recommended dish, and recommend the recommended dish to the customer.

The above-mentioned dish recommendation device determines the attributes of the customers by acquiring the customer IDs, and recommends dishes to the customers according to the attributes of the customers. For old customers, the recommended dishes are determined according to their historical ordering dishes. When a customer orders a certain historical dish more times, it means that the customer is more satisfied with the dish, which means that the customer may order this one with a higher probability. dishes. Therefore, recommending the dishes with the most ordered dishes in history can improve the accuracy of pushing customers' satisfied dishes to a certain extent.

In a possible implementation manner of the second aspect, the historical ordering record further includes: a dish evaluation, and the device further includes: a judgment module for judging whether the dish evaluation is positive; a second recommendation module for adding The dishes with a positive evaluation of the dishes are recommended to customers.

In a possible implementation manner of the second aspect, the apparatus further includes: a first calculation module, configured to calculate the similarity between the dishes to be ordered and the dishes to be ordered; a first selection module, configured to select the similarity in a predetermined level. Set the ordered dishes within the range as the candidate dishes; the second selection module is used to select the dishes to be ordered corresponding to the dishes with the most orders among the candidate dishes as similar dishes; the third recommendation module is used to select the said dishes Similar dishes are recommended to customers.

In a possible implementation manner of the second aspect, the historical ordering record further includes: the price of the ordered dish, and the apparatus further includes: a second calculation module configured to calculate the ordered dish according to the ordered dish and the ordered dish price Calculate the average price of the dishes; the fourth recommendation module is used for recommending dishes in the same price range or adjacent price range as the average price to customers.

In a possible implementation manner of the second aspect, the apparatus further includes: a third obtaining module, configured to obtain geographic information corresponding to the customer ID when the customer is a new customer; and a fifth recommending module, configured to obtain geographic information according to the geographic information Recommend corresponding dishes.

Description of drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative effort.

in:

1 is a flowchart of a method for recommending dishes in one embodiment;

Fig. 2 is a system block diagram in one embodiment;

FIG. 3 is a diagram of the internal structure of a computer device in one embodiment.

Detailed ways

It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the implementations. example. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

It should be noted that the terms "comprising", "comprising" and "having" in the description and claims of the present application and the above-mentioned drawings, as well as any modifications thereof, are intended to cover non-exclusive inclusion. For example, a process, method, terminal, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes unlisted steps or units, or optionally also includes For other steps or units inherent to these processes, methods, products or devices. Terms in the claims, description, and drawings of this application, relational terms such as "first" and "second", etc., are only used to associate one entity/operation/object with another entity/operation/ Objects are distinguished without necessarily requiring or implying any such actual relationship or ordering between these entities/operations/objects.

Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification is not necessarily all referring to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

At present, many restaurants use the method of online ordering. Customers place orders by scanning the QR code and do not need to order through the waiter, which can save costs and provide a better customer experience. However, when many customers go to a restaurant to eat, they often do not know which dishes are more suitable for their taste. Usually, the system will recommend the restaurant's signature dishes, but customers may not like to eat the signature dishes, resulting in dissatisfaction with the recommended dishes, and they do not know what to do. Which dishes in the restaurant suit your taste. Based on this problem, the present application proposes a method for recommending dishes. By obtaining the historical order records of customers, we can understand the dishes that customers often order. Usually, the more times a customer orders the same dish, the more the customer likes to eat the dish. Matching the dishes with high order times in the customer's historical order records with the dishes sold by the restaurant, and recommending the matching dishes to customers, can improve the accuracy of pushing customers' satisfied dishes to a certain extent.

As shown in Figure 1, a dish recommendation method is proposed, including:

Step 101, the terminal obtains the customer ID.

Among them, when customers order food through offline restaurants, they scan the QR code on the table to enter the ordering page. Before a customer orders, if it is a new customer, it needs to register and generate a customer ID. If it is an old customer, the terminal obtains the customer ID. The customer's information, such as historical order records, customer information, etc., can be queried through the customer's ID. Terminals include computers, tablet computers, and the like.

Step 102, the terminal determines whether the customer is an old customer according to the ID.

Step 103, if yes, the terminal obtains the customer's historical ordering records, the historical ordering records include: ordering dishes, the number of times of ordering dishes, and the historical ordering records include: the historical ordering records in the restaurant or the ordering records in the restaurant. The historical ordering records of the meal platform.

Wherein, when the terminal determines that the customer is an old customer, it indicates that the customer has ordered meals in the restaurant before, and the dishes ordered by the user in the past are of reference significance, and the terminal queries the customer's historical ordering records according to the customer ID.

In step 104, the terminal matches the dishes to be ordered with the dishes to be ordered to obtain matching dishes, and the dishes to be ordered are dishes on the menu.

Among them, the terminal obtains the ordered dishes in the historical ordering records, and matches the dishes to be ordered, that is, the dishes on the menu, and the dishes to be ordered are pre-stored in the system. That is, the two are the same dish, and the dish is regarded as a matching dish.

Step 105: The terminal selects the dish with the highest ordering times among the matching dishes as the recommended dish, and recommends the recommended dish to the customer.

Among them, the more times of ordering, the more customers like this dish, so the dish with the highest ordering times among the matching dishes is used as the recommended dish and recommended to the customer. In addition, according to the actual needs of the number of recommended dishes, it can be recommended to customers in order of ordering times, rather than only recommending only the ordering dishes with the highest ordering times.

In the above method for recommending dishes, the attributes of the customers are determined by obtaining the customer IDs, and dishes are recommended to the customers according to the attributes of the customers. For old customers, the recommended dishes are determined according to their historical ordering dishes. When a customer orders a certain historical dish more times, it means that the customer is more satisfied with the dish, which means that the customer may order this one with a higher probability. dishes. Therefore, recommending the dishes with the most ordered dishes in history can improve the accuracy of pushing customer satisfaction dishes to a certain extent.

In one embodiment, the historical meal ordering record further includes: dish evaluation, and the method further includes: the terminal judges whether the dish evaluation is positive; recommending the dish with the positive evaluation to the customer.

Among them, customers will comment on the dishes after consumption, and when customers make positive comments, it means that customers have a high probability of liking the dishes. Therefore, when customers dine next time, recommend this dish to customers, and customers will most likely be satisfied with this dish. After the terminal determines that the customer is an old customer according to the ID, it obtains the customer's historical order records, which include the dish evaluation. The terminal obtains the user's dish evaluation, and uses a keyword extraction algorithm to extract keywords in the dish evaluation. Keywords determine whether the review is positive or not. For example, a user's evaluation of a certain dish is "This restaurant has a very good environment, very clean and tidy, the food is not only beautiful in appearance, but most importantly, it tastes very good, with good color and taste. The method retains the original taste of the ingredients, Fresh and refreshing. And there are many choices of dishes, the price is not high, it is suitable to take the family together.", through the keyword extraction algorithm, "the environment is very good", "clean and tidy", "good color and taste", "taste is very good" Keywords such as "price is not high", the terminal judges that the customer's evaluation of the dish is positive according to these keywords, indicating that the customer is likely to be satisfied with the dish. If a user's evaluation of a certain dish is "the food in this restaurant is not delicious at all, it is expensive, and the price-performance ratio is very low. Key words such as "not delicious", "expensive", and "not fresh" are displayed, and the terminal judges that the customer's evaluation of the dish is negative based on these keywords, indicating that the customer is not satisfied with the dish, so it will not tell the customer any more This dish is recommended so as not to cause dissatisfied customers. Therefore, recommend dishes that are rated as positive to customers, and there is a high probability that customers will be more satisfied.

In one embodiment, the method further includes: the terminal calculates the similarity between the dishes to be ordered and the ordered dishes; selects the ordered dishes whose similarity is within a preset range as the candidate dishes; selects one of the candidate dishes The dish to be ordered corresponding to the dish with the most orders is regarded as a similar dish; the similar dish is recommended to the customer.

Among them, when customers order food in other restaurants or ordering platforms, historical order records are also generated, and the terminal obtains the ordered dishes in these historical order records. Through quantitative analysis of the dishes, the similarity between the dishes to be ordered and the dishes to be ordered is calculated. The similarity screening is performed on the food to be ordered, and the ordered dishes with the similarity within a preset range are selected as candidate dishes. The preset range can be set according to actual needs, such as 70-100%. Selecting the dish to be ordered corresponding to the dish with the most order times among the candidate dishes as a similar dish; recommending the similar dish to the customer. The candidate dishes are the dishes whose similarity between the ordered dishes and the dishes to be ordered in this restaurant is within the preset range. Select the dishes with the highest ordering times among the candidate dishes. The more times customers order the dishes, the more satisfied the customers are. Dishes means that customers at this meal may also order this dish with a higher probability, which can improve the accuracy of pushing customer satisfaction dishes to a certain extent. In addition, by reading and analyzing the historical order data, even if the customer has not eaten at the restaurant, it is possible to recommend the customer's satisfactory dishes to the customer.

In one embodiment, the historical order record further includes: the price of the ordered dish, and the method further includes: the terminal calculates the average price of the dish according to the ordered dish and the ordered dish price; The average price is for dishes in the same price range or adjacent price ranges.

Among them, when customers order food, they usually order dishes with prices within their acceptable range. Therefore, the price range of the dishes that customers often order is calculated, and the dishes in this range are recommended to customers, which is easier for customers to accept. In this embodiment, the historical ordering record further includes the price of the ordered dish, and the terminal calculates the average price of the dish according to the ordered dish and the ordered dish price. The terminal defines the price range, for example, it is divided into 0-30 yuan, 30-50 yuan, 50-100 yuan, and more than 100 yuan. When the average price of the user's order is calculated to be 25 yuan, dishes in the range of 0-30 yuan or dishes in the range of 30-50 yuan are recommended to the customer. By calculating the average order price of customers, and recommending dishes in the same price range or adjacent price range to customers, it is easier for customers to accept, and it can improve the accuracy of pushing customers' satisfied dishes to a certain extent.

In one embodiment, the method further includes: if not, obtaining geographic information corresponding to the customer ID; and recommending corresponding dishes according to the geographic information.

Among them, for new customers, it is accurate to a certain extent to judge the customer's taste according to the region where the customer is located. When the terminal determines that the customer is a new customer, the terminal obtains the user's geographic information according to the user ID, pre-stores the taste corresponding to each identity in the system, and also pre-stores the taste of the dishes to be ordered, and recommends the corresponding dishes according to the geographic information. For example, the geographic information of the customer is Hunan, and the corresponding flavors in the system are: spicy, heavy oil. Therefore, a dish that should taste is recommended to customers. Compared with random recommendations, customers have a higher probability of being satisfied with the dish.

As shown in Figure 2, a dish recommendation device is proposed, including:

The first obtaining module 201 is used to obtain the customer ID;

Judging module 202, for judging whether the customer is an old customer according to the ID;

The second obtaining module 203 is configured to obtain the customer's historical ordering records when the customer is an old customer, the historical ordering records include: ordering dishes and the number of times of ordering dishes, and the historical ordering records include: The historical ordering records of the restaurant or the historical ordering records of the ordering platform;

The matching module 204 is configured to match the dishes to be ordered with the dishes to be ordered to obtain matching dishes, and the dishes to be ordered are dishes on the menu;

The first recommendation module 205 is configured to select the dish with the highest order times among the matching dishes as the recommended dish, and recommend the recommended dish to the customer.

The above-mentioned dish recommendation device determines the attributes of the customers by acquiring the customer IDs, and recommends dishes to the customers according to the attributes of the customers. For old customers, the recommended dishes are determined according to their historical ordering dishes. When a customer orders a certain historical dish more times, it means that the customer is more satisfied with the dish, which means that the customer may order this one with a higher probability. dishes. Therefore, recommending the dishes with the most ordered dishes in history can improve the accuracy of pushing customers' satisfied dishes to a certain extent.

In one embodiment, the historical ordering record further includes: dish evaluation, and the device further includes: a judgment module for judging whether the dish evaluation is positive; a second recommendation module for evaluating the dish Recommended to customers for positive dishes.

In one embodiment, the apparatus further includes: a first calculation module, configured to calculate the similarity between the dishes to be ordered and the dishes to be ordered; a first selection module, configured to select the similarity within a preset range. The ordered dishes are used as candidate dishes; the second selection module is used to select the dishes to be ordered corresponding to the dishes with the most orders among the candidate dishes as similar dishes; the third recommendation module is used to recommend the similar dishes to client.

In one embodiment, the historical ordering record further includes: the price of the ordered dish, and the apparatus further includes: a second calculation module configured to calculate the average of the dish according to the ordered dish and the price of the ordered dish Price; the fourth recommendation module is used for recommending dishes in the same price range or adjacent price range as the average price to customers.

In one embodiment, the device further includes: a third acquisition module, configured to acquire geographic information corresponding to the customer ID when the customer is a new customer; and a fifth recommendation module, configured to recommend corresponding dishes according to the geographic information .

As shown in FIG. 3, in one embodiment, a computer device is presented, the computer device including a processor, a memory, and a network interface connected by a terminal bus. Wherein, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device includes a storage operation terminal, and may also store a computer program. When the computer program is executed by the processor, the processor can implement the above-mentioned method for recommending dishes. A computer program may also be stored in the internal memory, and when the computer program is executed by the processor, the processor may execute the above-mentioned method for recommending dishes. Those skilled in the art can understand that the structure shown in FIG. 3 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the equipment to which the solution of the present application is applied. More or fewer components are shown in the figures, either in combination or with different arrangements of components.

In one embodiment, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, causes the processor to execute the steps of the above-mentioned method for recommending dishes.

It can be understood that the above-mentioned method, apparatus, device and storage medium for dish recommendation belong to a general inventive concept, and the embodiments are applicable to each other.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium , when the program is executed, it may include the flow of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other medium used in the various embodiments provided in this application may include non-volatile and/or volatile memory. Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Road (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

The technical features of the above embodiments can be combined arbitrarily. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features It is considered to be the range described in this specification.

The above-mentioned embodiments only represent several embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but should not be construed as a limitation on the scope of the patent of the present application. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the patent of the present application shall be subject to the appended claims.

Claims (10)

1. a dish recommendation method, it is characterised in that the method comprises: Get customer ID; Determine whether the customer is an old customer according to the ID; If so, obtain the customer's historical ordering records, the historical ordering records include: ordered dishes, the number of ordered dishes, and the historical ordering records include: the historical ordering records of the restaurant or the history of the ordering platform meal ordering records; Matching the dishes to be ordered with the dishes to be ordered to obtain matching dishes, and the dishes to be ordered are dishes on the menu; Among the matching dishes, the dish with the highest order times is selected as the recommended dish, and the recommended dish is recommended to the customer. 2. The method for recommending dishes as claimed in claim 1, wherein the historical ordering record further comprises: evaluation of dishes, and the method further comprises: Determine whether the evaluation of the dish is positive; The dishes that are rated as positive are recommended to customers. 3. The method for recommending dishes as claimed in claim 1, wherein the method further comprises: Calculate the similarity between the dishes to be ordered and the dishes ordered; Selecting the ordered dishes with the similarity within a preset range as the candidate dishes; Select the dish to be ordered corresponding to the dish with the most order times among the candidate dishes as a similar dish; The similar dishes are recommended to customers. 4. The method for recommending dishes according to claim 1, wherein the historical ordering record further comprises: the price of the ordered dishes, and the method further comprises: Calculate the average price of the dishes according to the ordered dishes and the prices of the ordered dishes; Recommend dishes to customers in the same price range or adjacent price range as the average price. 5. The method for recommending dishes as claimed in claim 1, wherein the method further comprises: If not, obtain the geographic information corresponding to the customer ID; The corresponding dishes are recommended according to the geographic information. 6. A dish recommendation device, wherein the device comprises: The first acquisition module is used to acquire the customer ID; Judging module, for judging whether the customer is an old customer according to the ID; The second acquisition module is used to acquire the customer's historical ordering records when the customer is an old customer, the historical ordering records include: ordering dishes and the number of times of ordering dishes, and the historical ordering records include: in this restaurant The historical ordering records or the historical ordering records on the ordering platform; a matching module, configured to match the dishes to be ordered with the dishes to be ordered to obtain matching dishes, and the dishes to be ordered are dishes on the menu; The first recommendation module is configured to select the dish with the highest ordering times among the matching dishes as the recommended dish, and recommend the recommended dish to the customer. 7. The dish recommendation device according to claim 6, wherein the historical ordering record further comprises: dish evaluation, and the device further comprises: a judgment module for judging whether the evaluation of the dish is positive; The second recommendation module is used for recommending the dishes that are evaluated as positive to customers. 8. The dish recommendation device according to claim 6, wherein the device further comprises: The first calculation module is used to calculate the similarity between the dishes to be ordered and the dishes to be ordered; a first selection module, configured to select the ordered dishes whose similarity is within a preset range as the candidate dishes; The second selection module is used to select the dish to be ordered corresponding to the dish with the most order times among the candidate dishes as a similar dish; The third recommendation module is used for recommending the similar dishes to customers. 9 . The device for recommending dishes according to claim 6 , wherein the historical ordering record further comprises: the price of the ordered dishes, and the device further comprises: 10 . The second calculation module is configured to calculate the average price of the dishes according to the ordered dishes and the prices of the ordered dishes; The fourth recommendation module is used for recommending dishes in the same price range or adjacent price range as the average price to customers. 10. The dish recommendation device according to claim 6, wherein the device further comprises: The third acquisition module is used to acquire geographic information corresponding to the customer ID when the customer is a new customer; The fifth recommendation module is used for recommending corresponding dishes according to the geographic information.

Images