Restaurant food recommendation system based on artificial intelligence

Abstract

The invention discloses a restaurant food recommendation system based on artificial intelligence, and relates to the technical field of service management, the system discloses an order recording module, a food recommendation module and a recommendation judgment module, through setting the order recording module and the food recommendation module, statistics is performed on food ordered by a customer each time, comprehensive analysis is performed on the ordered food, and a recommendation result is obtained. According to the method, food products with potential demands of customers are further analyzed, the food products are intelligently sorted and recommended to the customers, on the basis of ensuring food product recommendation precision, the ordering efficiency of the customers is improved, a recommendation judgment module is arranged, the ordering process of the customers can be continuously supervised, the acceptability of the customers to food product recommendation is dynamically analyzed, food product recommendation is interrupted in time, and the customer experience is improved. And the ordering experience of customers is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of service management, and more specifically, to an artificial intelligence-based restaurant food recommendation system. Background Art

[0002] The current restaurant ordering method is increasingly dependent on terminal devices. Customers can order through the tablets provided by the restaurant, or they can order on their mobile phones by scanning QR codes. At present, the display order of restaurant dishes on terminal devices is fixed, either sorted and displayed according to the sales volume of dishes or sorted and displayed according to the type of dishes. It is impossible to display dishes and recommend dishes adaptively to customers, resulting in low ordering efficiency for customers, and it is difficult for customers to quickly select the dishes they need, which in turn causes poor ordering experience for customers. How to enable customers to quickly select the dishes they need while ensuring their ordering experience is a problem that needs to be solved urgently. Summary of the invention

[0003] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a restaurant food recommendation system based on artificial intelligence.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] An AI-based restaurant food recommendation system, including an order record module, a food recommendation module, and a recommendation evaluation module;

[0006] The order record module is used to generate a meal order record when a customer orders a meal;

[0007] When generating a meal order record, the meal recommendation module marks the meal corresponding to the meal order record as a target meal, obtains a pre-recommended meal based on the target meal, and selects recommended meals based on the pre-recommended meals for sorting and recommendation;

[0008] The recommendation judging module is used to judge whether the subsequent ordering process needs to continue with food recommendation.

[0009] Furthermore, when a customer uses a terminal device to order a meal, and when the customer clicks on the name of a meal, the customer enters the information interface of the meal, and when the customer places an order on the meal information interface, a meal order record is generated.

[0010] Furthermore, the food order record includes the order quantity, order time, and number of diners.

[0011] Furthermore, the relationship between the target meal and the rest of the meals in the restaurant is obtained. Through knowledge graph association analysis, the meals associated with the target meal are marked as pre-recommended meals, and the meals not associated with the target meal are marked as non-recommended meals. The order frequency, order interval, and total number of fluctuations in the number of diners of the target meal are obtained and marked as A=[A1, A2, A3]. The order frequency, order interval, and total number of fluctuations in the number of diners of the pre-recommended meals are obtained and marked as B=[B1, B2, B3]. The cosine similarity algorithm is used to obtain the order approximation value of the target meal and the pre-recommended meal, and an order approximation threshold is set. When the order approximation value is greater than or equal to the order approximation threshold, the pre-recommended meal is marked as a recommended meal. When the order approximation value is less than the order approximation threshold, the pre-recommended meal is marked as a non-recommended meal.

[0012] Furthermore, all recommended dishes are sorted from large to small according to the approximate order values, and the names of the sorted recommended dishes are displayed on the customer's terminal device.

[0013] Furthermore, the order frequency is obtained in the following manner: all order records of the meal within T time periods before the current system time are obtained, and the total number of order records is the order frequency.

[0014] Furthermore, the order interval is obtained in the following manner: obtain all meal order records before the current system time of the meal, sort all meal order records in chronological order time, calculate the time difference between the order times of two adjacent meal order records after sorting to obtain adjacent intervals, sum up all adjacent intervals and take the average to obtain the order interval.

[0015] Furthermore, the total number of fluctuations in the number of diners is obtained in the following way: obtain all meal order records before the current time of the system, sort all meal order records in chronological order time, calculate the difference between the number of diners in two adjacent meal order records after sorting and take the absolute value to obtain the difference in the number of diners, set a threshold difference in the number of diners, and when the difference in the number of diners is greater than or equal to the threshold difference in the number of diners, increase the number of fluctuations in the number of diners by one, sum the number of fluctuations in the number of diners, and obtain the total number of fluctuations in the number of diners.

[0016] Furthermore, it is determined whether it is necessary to continue recommending meals in the subsequent ordering process. Specifically, each time a new meal order record is generated in the ordering, the customer recommendation value of the order is obtained, a customer recommendation record is generated, and a customer recommendation threshold is set. When the customer recommendation value of the order is less than the customer recommendation low value, the subsequent recommendations for meals are cancelled. When the customer recommendation value of the order is greater than the customer recommendation high value, the recommendation floating value of the order is obtained, and a recommendation floating threshold is set. When the recommendation floating value is greater than or equal to the recommendation floating threshold, the subsequent recommendations for meals are cancelled. When the recommendation floating value is less than the recommendation floating threshold, the subsequent recommendations for meals are maintained.

[0017] Furthermore, the customer recommendation record includes the customer recommendation value and the customer recommendation time;

[0018] The customer recommendation value of the order is obtained in the following way: obtain all the order records of the order, sort all the order records in the order of order time, mark the food in the next order record after sorting as the next ordered food, mark the food in the previous order record after sorting as the previous ordered food, and when the next ordered food is the recommended food of the previous ordered food, increase the effective number of recommendations by one. times, and calculate the time difference between the order time of the next order and the order time of the previous order to get the recommended order interval. When the next order is not a recommended item for the previous order, no corresponding processing is performed. The effective number of recommendations for this order is summed up to get the total effective number of recommendations, which is marked as LMS. The total number of order records for this order is marked as RGH. All recommended order intervals are summed up and averaged to get the average recommended order interval, which is marked as TWY. Using the formula Get the customer recommendation value APL for this order, where a1 is the total effective recommendation coefficient, a2 is the number of food order records coefficient, and a3 is the average recommendation order interval coefficient;

[0019] The floating value of the recommendation for this order is obtained in the following way: obtain all the customer recommendation records for this order, sort the customer recommendation values ​​of all customer recommendation records in the order of customer recommendation time, calculate the difference between the previous customer recommendation value and the next customer recommendation value after sorting to obtain the customer recommendation change value, set the customer recommendation threshold change value, when the customer recommendation change value is greater than or equal to the customer recommendation threshold change value, increase the number of recommendation super-changes by one, sum the number of recommendation super-changes for this order to obtain the total number of recommendation super-changes, and mark it as ZKE, sum the customer recommendation values ​​of all customer recommendation records and take the average to obtain the customer recommendation mean, and mark it as WGR, use the formula The floating value of recommendation and review JYS is obtained, where b1 is the total number of super-variable recommendation and review coefficients, and b2 is the mean coefficient of customer recommendation and review.

[0020] Compared with the prior art, the present invention has the following beneficial effects:

[0021] 1. Set up an order record module and a food recommendation module to count the food ordered by customers each time, conduct a comprehensive analysis of the ordered food, further analyze the food that customers have potential demand for, and intelligently recommend food to customers in order, thereby improving customers' ordering efficiency while ensuring the accuracy of food recommendations;

[0022] 2. Setting up a recommendation and evaluation module can continuously monitor the customer's ordering process, dynamically analyze the customer's acceptance of food recommendations, and promptly interrupt food recommendations to ensure the customer's ordering experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A flowchart for screening and ranking recommended dishes;

[0024] Figure 2 A flowchart for judging whether food recommendations need to be continued in the subsequent ordering process. DETAILED DESCRIPTION

[0025] Example 1

[0026] Reference Figure 1 , an artificial intelligence-based restaurant food recommendation system, including an order record module and a food recommendation module.

[0027] Order record module: Customers use terminal devices to order food. When customers click on the name of a dish, they enter the information interface of the dish. When customers place an order on the dish information interface, a dish order record is generated.

[0028] Food recommendation module: When a food order record is generated, the food corresponding to the food order record is marked as the target food. The food order record includes the order quantity (i.e. the number of orders placed by the customer on the food information interface), the order time (i.e. the corresponding time when the customer places the order on the food information interface), and the number of diners.

[0029] Get the relationship between the target meal and the rest of the meals in the restaurant, and through knowledge graph association analysis, mark the meals associated with the target meal as recommended meals, and mark the meals not associated with the target meal as unrecommended meals. Get the target meal's order frequency, order interval, and the total number of diners' fluctuations, and mark them as A=[A1, A2, A3]. Get the order frequency, order interval, and the total number of diners' fluctuations, and mark them as B=[B1, B2, B3]. Use the cosine similarity algorithm to get the order approximation value of the target meal and the recommended meal, and set the order approximation threshold. The order approximation threshold is a system-set threshold that can be modified according to actual needs. When the order approximation value is greater than or equal to the order approximation threshold, mark the recommended meal as a recommended meal. When the order approximation value is less than the order approximation threshold, mark the recommended meal as an unrecommended meal.

[0030] All recommended dishes are sorted from large to small according to the approximate order values, and the names of the sorted recommended dishes are displayed on the customer's terminal device.

[0031] If the order frequency, order interval, and total number of diners of the target dishes are 12, 5, and 28 respectively, and the order frequency, order interval, and total number of diners of the recommended dishes are 14, 6, and 33 respectively, then

[0032] The order frequency is obtained in the following way: obtain all order records of the meal within T time before the current system time, and the total number of order records is the order frequency.

[0033] The order interval is obtained in the following way: obtain all meal order records before the current system time, sort all meal order records in chronological order time, calculate the time difference between the order times of two adjacent meal order records after sorting to obtain adjacent intervals, sum up all adjacent intervals and take the average to obtain the order interval.

[0034] The total number of fluctuations in the number of diners is obtained in the following way: obtain all order records of the meal before the current time of the system, sort all order records in chronological order of the order time, calculate the difference between the number of diners in two adjacent order records after sorting and take the absolute value to obtain the difference in the number of diners, set the threshold difference in the number of diners, which is a system-set threshold and can be modified according to actual needs. When the difference in the number of diners is greater than or equal to the threshold difference in the number of diners, the number of fluctuations in the number of diners is increased by one. When the difference in the number of diners is less than the threshold difference in the number of diners, no corresponding processing is performed. The number of fluctuations in the number of diners is summed to obtain the total number of fluctuations in the number of diners.

[0035] The names of dishes such as Kung Pao Chicken, Corn Spareribs, and Curry Chicken are displayed on the terminal device interface. When the customer clicks on the Scallion-fried Sea Cucumber, the Scallion-fried Sea Cucumber information interface is entered (introducing sample photos, ingredients, prices, portions, and other information of the Scallion-fried Sea Cucumber). The customer can choose whether to place an order for the Scallion-fried Sea Cucumber on the Scallion-fried Sea Cucumber information interface. When the customer chooses to place an order for the Scallion-fried Sea Cucumber on the Scallion-fried Sea Cucumber information interface, a meal order record is generated, and the Scallion-fried Sea Cucumber is marked as a target meal. Through knowledge graph association analysis, it is found that the restaurant's blanched shrimps, braised clams, and stir-fried clams are all associated with the Scallion-fried Sea Cucumber, and the blanched shrimps, braised clams, and stir-fried clams are marked as pre-recommended meals.

[0036] The restaurant's dishes are represented in the form of a knowledge graph. For example, the relationships in the knowledge graph represent the associations between the dishes, such as cuisine relationships, taste relationships, etc. The knowledge graph can accurately reflect the relationships between the dishes.

[0037] Set up an order record module and a meal recommendation module, count the meals ordered by customers each time, and conduct a comprehensive analysis of the ordered meals. Further analyze the meals that customers have potential demand for, and intelligently recommend meals to customers in order. On the basis of ensuring the accuracy of meal recommendations, improve customers' ordering efficiency.

[0038] Example 2

[0039] Reference Figure 2 On the basis of Example 1, it also includes a recommendation and evaluation module, which: when a new meal order record is generated in this ordering, the customer recommendation value of the order is obtained, and a customer recommendation record is generated. The customer recommendation record includes the customer recommendation value and the customer recommendation time (the time corresponding to the generation of the new meal order record). A customer recommendation threshold is set. The customer recommendation threshold is a system preset threshold and can be modified according to actual needs. When the customer recommendation value of the ordering is less than the customer recommendation low value, the subsequent recommendation of the meal is cancelled. When the customer recommendation value of the ordering is greater than the customer recommendation high value, the recommendation floating value of the ordering is obtained, and a recommendation floating threshold is set. The recommendation floating threshold is a system preset threshold and can be modified according to actual needs. When the recommendation floating value is greater than or equal to the recommendation floating threshold, the subsequent recommendation of the meal is cancelled. When the recommendation floating value is less than the recommendation floating threshold, the subsequent recommendation of the meal is maintained.

[0040] The customer recommendation value of the order is obtained in the following way: obtain all the order records of the order, sort all the order records in the order of order time, mark the food in the next order record after sorting as the next ordered food, mark the food in the previous order record after sorting as the previous ordered food, and when the next ordered food is the recommended food of the previous ordered food, increase the effective number of recommendations by one. times, and calculate the time difference between the order time of the next order and the order time of the previous order to get the recommended order interval. When the next order is not a recommended item for the previous order, no corresponding processing is performed. The effective number of recommendations for this order is summed up to get the total effective number of recommendations, which is marked as LMS. The total number of order records for this order is marked as RGH. All recommended order intervals are summed up and averaged to get the average recommended order interval, which is marked as TWY. Using the formula The customer recommendation value APL of the order is obtained, where a1 is the total effective recommendation coefficient, a2 is the coefficient of the number of meal order records, and a3 is the average recommendation order interval coefficient. The value of a1 is 0.82, the value of a2 is 0.41, and the value of a3 is 0.57.

[0041] The floating value of the recommendation for this order is obtained in the following way: obtain all the customer recommendation records for this order, sort the customer recommendation values ​​of all customer recommendation records in the order of customer recommendation time, calculate the difference between the previous customer recommendation value and the next customer recommendation value after sorting, obtain the customer recommendation change value, set the customer recommendation threshold change value, the customer recommendation threshold change value is greater than 0, the customer recommendation threshold change value is the system set threshold, which can be modified according to actual needs, when the customer recommendation change value is greater than or equal to the customer recommendation threshold change value, increase the number of recommendation super-changes by one, sum the number of recommendation super-changes for this order, obtain the total number of recommendation super-changes, and mark it as ZKE, sum the customer recommendation values ​​of all customer recommendation records and take the average, obtain the customer recommendation average, and mark it as WGR, use the formula The floating value of recommendation and evaluation JYS is obtained, where b1 is the total number of super-variable times of recommendation and evaluation, b2 is the mean coefficient of customer recommendation and evaluation, the value of b1 is 1.83, and the value of b2 is 0.99.

[0042] By setting up a recommendation and evaluation module, you can continuously monitor the customer's ordering process, dynamically analyze the customer's acceptance of food recommendations, and promptly interrupt food recommendations to ensure the customer's ordering experience.

[0043] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0044] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0045] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0046] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0047] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0048] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0049] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0050] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. The restaurant food recommendation system based on artificial intelligence is characterized by: Including order record module, food recommendation module, and recommendation evaluation module; The order record module is used to generate a meal order record when a customer orders a meal; When generating a meal order record, the meal recommendation module marks the meal corresponding to the meal order record as a target meal, obtains a pre-recommended meal based on the target meal, and selects recommended meals based on the pre-recommended meals for sorting and recommendation; The recommendation judging module is used to judge whether the subsequent ordering process needs to continue with food recommendation.

2. The restaurant food recommendation system based on artificial intelligence according to claim 1, characterized in that: The customer uses the terminal device to order food. When the customer clicks on the name of a food, the customer enters the information interface of the food. When the customer places an order on the food information interface, a food order record is generated.

3. The restaurant food recommendation system based on artificial intelligence according to claim 1, characterized in that: The food order record includes the order quantity, order time, and number of diners.

4. The restaurant food recommendation system based on artificial intelligence according to claim 1, characterized in that: Obtain the relationship between the target meal and the rest of the meals in the restaurant. Through knowledge graph association analysis, mark the meals associated with the target meal as recommended meals, and mark the meals not associated with the target meal as unrecommended meals. Obtain the order frequency, order interval, and total number of fluctuations in the number of diners of the target meal, and mark them as A=A1, A2, A3. Obtain the order frequency, order interval, and total number of fluctuations in the number of diners of the unrecommended meals, and mark them as B=B1, B2, B3. Use the cosine similarity algorithm to obtain the order approximation value of the target meal and the unrecommended meal. Set an order approximation threshold. When the order approximation value is greater than or equal to the order approximation threshold, mark the unrecommended meal as a recommended meal. When the order approximation value is less than the order approximation threshold, mark the unrecommended meal as a unrecommended meal.

5. The restaurant food recommendation system based on artificial intelligence according to claim 1, characterized in that: All recommended dishes are sorted from large to small according to the approximate order values, and the names of the sorted recommended dishes are displayed on the customer's terminal device.

6. The restaurant food recommendation system based on artificial intelligence according to claim 4, characterized in that: The order frequency is obtained in the following way: obtain all order records of the meal within T time before the current system time, and the total number of order records is the order frequency.

7. The restaurant food recommendation system based on artificial intelligence according to claim 4, characterized in that: The order interval is obtained in the following way: obtain all meal order records before the current system time, sort all meal order records in chronological order time, calculate the time difference between the order times of two adjacent meal order records after sorting to obtain adjacent intervals, sum up all adjacent intervals and take the average to obtain the order interval.

8. The restaurant food recommendation system based on artificial intelligence according to claim 4, characterized in that: The total number of fluctuations in the number of diners is obtained in the following way: obtain all meal order records before the current time of the system, sort all meal order records in chronological order time, calculate the difference between the number of diners in two adjacent meal order records after sorting and take the absolute value to obtain the difference in the number of diners, set a threshold difference in the number of diners, and when the difference in the number of diners is greater than or equal to the threshold difference in the number of diners, increase the number of fluctuations in the number of diners by one, sum the number of fluctuations in the number of diners, and obtain the total number of fluctuations in the number of diners.

9. The restaurant food recommendation system based on artificial intelligence according to claim 1, characterized in that: Determine whether it is necessary to continue to recommend food in the subsequent ordering process, specifically: each time a new food order record is generated in the ordering, obtain the customer recommendation value of the order, generate a customer recommendation record, set a customer recommendation threshold, when the customer recommendation value of the order is less than the customer recommendation low value, cancel the subsequent food recommendations, when the customer recommendation value of the order is greater than the customer recommendation high value, obtain the recommendation floating value of the order, set the recommendation floating threshold, when the recommendation floating value is greater than or equal to the recommendation floating threshold, cancel the subsequent food recommendations, when the recommendation floating value is less than the recommendation floating threshold, maintain the subsequent food recommendations.

10. The restaurant food recommendation system based on artificial intelligence according to claim 9, characterized in that: Customer recommendation records include customer recommendation value and customer recommendation time; The customer recommendation value of the order is obtained in the following way: obtain all the order records of the order, sort all the order records in the order of order time, mark the food in the next order record after sorting as the next ordered food, mark the food in the previous order record after sorting as the previous ordered food, and when the next ordered food is the recommended food of the previous ordered food, increase the effective number of recommendations by one. times, and calculate the time difference between the order time of the next order and the order time of the previous order to get the recommended order interval. When the next order is not a recommended item for the previous order, no corresponding processing is performed. The effective number of recommendations for this order is summed up to get the total effective number of recommendations, which is marked as LMS. The total number of order records for this order is marked as RGH. All recommended order intervals are summed up and averaged to get the average recommended order interval, which is marked as TWY. Using the formula Get the customer recommendation value APL for this order, where a1 is the total effective recommendation coefficient, a2 is the number of food order records coefficient, and a3 is the average recommendation order interval coefficient; The floating value of the recommendation for this order is obtained in the following way: obtain all the customer recommendation records for this order, sort the customer recommendation values ​​of all customer recommendation records in the order of customer recommendation time, calculate the difference between the previous customer recommendation value and the next customer recommendation value after sorting to obtain the customer recommendation change value, set the customer recommendation threshold change value, when the customer recommendation change value is greater than or equal to the customer recommendation threshold change value, increase the number of recommendation super-changes by one, sum the number of recommendation super-changes for this order to obtain the total number of recommendation super-changes, and mark it as ZKE, sum the customer recommendation values ​​of all customer recommendation records and take the average to obtain the customer recommendation mean, and mark it as WGR, use the formula The floating value of recommendation and review JYS is obtained, where b1 is the total number of super-variable recommendation and review coefficients, and b2 is the mean coefficient of customer recommendation and review.

Images