Dish settlement processing method and device based on identity recognition

Abstract

The embodiment of the invention provides a dish settlement processing method and device based on identity recognition, and the method comprises the steps: obtaining a dish image of a to-be-recognized dish combination collected by a dish machine tool, and a user identity image; identifying a settlement user corresponding to the user identity image, and associating the dish image to the settlement user; inputting the dish image and the historical behavior data of the settlement user into a dish identification model to carry out dish type identification, and obtaining the dish type of each selected dish in the dish combination; and calculating to-be-settled fees of the dish combination according to the dish types, and performing settlement processing of the to-be-settled fees based on the payment token of the settlement user.

Description

[0001] This patent application is a divisional application of the Chinese patent application with application number CN202210212033.7, application date March 4, 2022, and invention name “Method and device for processing food settlement based on identity recognition”. Technical Field

[0002] This document relates to the field of data processing technology, and in particular to a method and device for processing dish settlement based on identity recognition. Background Art

[0003] As people's daily necessities, the development of dish varieties is constantly developing and the variety of dishes is also increasing. Users can usually only distinguish a few varieties of dishes with the naked eye. For the scenario of users dining at their own table, helping users to identify dishes has become a demand. Moreover, dish recognition can also be applied to a variety of different application scenarios, such as the checkout process of restaurants, the voice introduction of dishes by smart plates, the detection of different dishes stored in smart refrigerators, etc. Summary of the invention

[0004] One or more embodiments of the present specification provide a method for processing dish settlement based on identity recognition, comprising: obtaining a dish image and a user identity image of a dish combination to be identified that are collected by a dish machine. Identifying the settlement user corresponding to the user identity image, and associating the dish image with the settlement user. Inputting the dish image and the historical behavior data of the settlement user into a dish recognition model to identify the dish category, and obtaining the dish category of each selected dish in the dish combination. Calculating the pending fees of the dish combination based on the dish category, and performing settlement processing of the pending fees based on the payment token of the settlement user.

[0005] One or more embodiments of the present specification provide a dish settlement processing device based on identity recognition, including: an image acquisition module, configured to acquire a dish image and a user identity image of a dish combination to be identified, which are collected by a dish machine. A settlement user identification module, configured to identify the settlement user corresponding to the user identity image, and associate the dish image with the settlement user. A dish category identification module, configured to input the dish image and the historical behavior data of the settlement user into a dish recognition model to perform dish category identification, and obtain the dish category of each selected dish in the dish combination. A settlement processing module, configured to calculate the pending fees of the dish combination according to the dish category, and perform settlement processing of the pending fees based on the payment token of the settlement user.

[0006] One or more embodiments of the present specification provide a dish settlement processing device based on identity recognition, comprising: a processor; and a memory configured to store computer executable instructions, wherein when the computer executable instructions are executed, the processor: obtains a dish image and a user identity image of a dish combination to be identified that are collected by a dish machine. Identifies the settlement user corresponding to the user identity image, and associates the dish image with the settlement user. Inputs the dish image and the historical behavior data of the settlement user into a dish recognition model to identify the dish category, and obtains the dish category of each selected dish in the dish combination. Calculates the pending fees of the dish combination based on the dish category, and performs settlement processing of the pending fees based on the payment token of the settlement user.

[0007] One or more embodiments of the present specification provide a storage medium for storing computer-executable instructions, which implement the following process when executed by a processor: Acquire a dish image and a user identity image of a dish combination to be identified that are collected by a dish machine. Identify the settlement user corresponding to the user identity image, and associate the dish image with the settlement user. Input the dish image and the historical behavior data of the settlement user into a dish recognition model to identify the dish category, and obtain the dish category of each selected dish in the dish combination. Calculate the pending fees of the dish combination based on the dish category, and perform settlement processing of the pending fees based on the payment token of the settlement user. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate one or more embodiments of the present specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present specification. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative labor. Figure 1 A processing flow chart of a method for processing dish settlement based on identity recognition provided in one or more embodiments of this specification; Figure 2 A schematic diagram of a dish combination provided for one or more embodiments of this specification; Figure 3 A processing flow chart of a method for processing dish settlement based on identity recognition applied to a group dining scenario provided in one or more embodiments of this specification; Figure 4 A schematic diagram of a dish settlement processing device based on identity recognition provided in one or more embodiments of this specification; Figure 5A schematic diagram of the structure of a dish settlement processing device based on identity recognition provided in one or more embodiments of this specification. DETAILED DESCRIPTION

[0009] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0010] This specification provides an embodiment of a method for processing dish settlement based on identity recognition: Reference Figure 1 The present embodiment provides a method for processing dish settlement based on identity recognition, and the method specifically includes steps S102 to S108.

[0011] Step S102, obtaining the dish image of the dish combination to be identified and the user identity image collected by the dish machine.

[0012] The dish settlement processing method based on identity recognition provided in the present embodiment, through the configured dish machine, simultaneously collects the dish image to be identified and the user identity image, associates the collected dish image with the settlement user determined based on the user identity image, and then combines the historical behavior data of the settlement user with the dish image to identify the dish category corresponding to the dish image, obtains the dish category of each selected dish in the dish image, calculates the total cost of each selected dish based on the dish category, and uses the payment token of the settlement user to settle the total cost, enhances the accuracy of dish recognition through identity recognition technology and big data behavior preference analysis, reduces human contact with the help of dish intelligent recognition technology, and can reduce costs compared with dish recognition completed with the help of smart plates.

[0013] The dish machine described in this embodiment refers to a machine configured by a dining institution or an internal organization of the institution (such as a school cafeteria or a restaurant) for dish identification, user identity identification, dish settlement or other functions. The dish combination refers to a combination of dishes of one or more dish categories, such as a dish combination consisting of dish A, dish B, and dish C. It should be noted that the dishes included in the dish combination can not only be various types of dishes in the traditional sense, but also coarse grains, fine grains, and beverages. The dish image refers to an image collected for the dish combination, and the user identity image includes a contactless biometric image, that is, a contactless feature image, such as a face image and an iris image. This embodiment is for contactless feature images such as face images and iris images, which can reduce personnel contact in group dining scenarios and protect the health of users in the context of public health events.

[0014] In the actual group dining scenario, users can select dishes by themselves or through waiters in the centralized dining canteen, and the selected dishes to be identified (such as Figure 2 An image sensor (such as a camera) is placed on the dish machine to collect the dish image. While collecting the dish image, the dish machine also collects the user identity image of the user (for example, the front and rear cameras of the dish machine cooperate to collect the user identity image and the dish image at the same time). After the dish machine completes image collection, the dish image and user identity image of the dish combination to be identified collected by the dish machine are obtained.

[0015] Step S104, identifying the settlement user corresponding to the user identity image, and associating the dish image with the settlement user.

[0016] The settlement user in this embodiment refers to the user who settles the fees for the dish combination to be identified.

[0017] Based on the above-mentioned acquisition of the dish image and user identity image of the dish combination to be identified collected by the dish machine, in this step, image recognition is performed on the user identity image, the settlement user corresponding to the user identity image is obtained, and the dish image is associated with the settlement user, and the dish and the settlement user are data-bound, so as to facilitate the settlement user to make subsequent payments for each selected dish in the dish combination.

[0018] In actual applications, in the process of identifying the settlement user corresponding to the user identity image, poor network conditions may be encountered. In order to avoid the user identity image recognition taking too long, resulting in poor user experience and improving recognition efficiency, local recognition and remote recognition can be performed in combination. Specifically, the user identity image is first recognized locally, and when no result is obtained in the local recognition, remote recognition (such as cloud recognition) is performed. In an optional implementation manner provided in this embodiment, the user identity image is recognized in the following manner: Input the user identity image into the identity recognition model stored in the food processing machine for offline identity recognition, and use the user corresponding to the user identification output by the identity recognition model as the settlement user; If the user identifier output by the identity recognition model is empty, a remote identity recognition interface is called to perform identity recognition processing on the user identity image, and the user corresponding to the user identifier returned by the remote identity recognition interface is used as the settlement user.

[0019] Specifically, an identity recognition model is stored in the food processing machine. After obtaining the user identity image, the user identity image is first input into the identity recognition model for offline identity recognition, and the user corresponding to the user identifier (such as the user identity identifier) ​​output by the identity recognition model is used as the settlement user. Due to the incompleteness of offline data, when the user identifier output by the identity recognition model is empty, it means that there is no result in local recognition, and the remote identity recognition interface is called to perform identity recognition processing on the user identity image, and the user corresponding to the user identifier returned by the remote identity recognition interface is used as the settlement user; wherein, the remote identity recognition interface includes a cloud identity recognition interface.

[0020] Step S106, inputting the dish image and the historical behavior data of the settlement user into a dish recognition model to perform dish category recognition, and obtaining the dish category of each selected dish in the dish combination.

[0021] The historical behavior data in this embodiment refers to data related to the historical behavior preferences of the settlement user. Optionally, the historical behavior data includes at least one of the following: dish consumption records, user portrait data, and behavior characteristic data. The dish consumption records include historical dish consumption records, such as the dish combination in the settlement user's previous dish consumption record is a combination of "dish A", "dish B", and "dish C". The behavior characteristic data refers to behavior preference data, such as preference for spicy food and love of fast food.

[0022] The above-mentioned identification identifies the settlement user corresponding to the user identity image, and associates the dish image with the settlement user. On this basis, this embodiment uses a dish recognition model to input the dish image and the historical behavior data of the settlement user into the dish recognition model to perform dish category recognition, and obtain the dish category of each selected dish in the dish combination.

[0023] In actual applications, after the dish recognition model is used to obtain the dish category of each selected dish in the dish combination, since the output result of the dish recognition model cannot completely match the actual situation, in order to solve the recognition errors that may occur in the dish recognition model, this embodiment provides an optional implementation method, in which the dish image and the historical behavior data of the settlement user are input into the dish recognition model to perform dish category recognition, and after the dish category of each selected dish in the dish combination is obtained, the misidentified dish category can be corrected in the following way: Obtain a list of similar dishes to each of the selected dishes and display the list through the dish machine; If a replacement instruction is detected to replace any selected dish in the dish combination based on any similar dish in the similar dish list, the any selected dish is updated to the any similar dish.

[0024] The similar dishes list includes a list of dishes similar to the selected dishes in the dish combination.

[0025] Specifically, in order to provide users with a good user experience, in the process of correcting the misidentified dish types of each selected dish, a list of similar dishes for each selected dish can be obtained and displayed on the dish machine. On this basis, the settlement user or the dish machine operator can replace any selected dish in the dish combination with any similar dish in the similar dish list. That is, upon detecting the settlement user or the dish machine operator's replacement instruction to replace any selected dish in the dish combination with any similar dish in the similar dish list, any selected dish will be updated to any similar dish. By having the machine operator operate the dish machine, the user does not need to operate, and for public health event scenarios, human contact can be reduced.

[0026] In addition, an error correction access interface can be set up for misidentification of dish categories. When the dish categories of the selected dishes in the dish combination output by the dish recognition model do not match the actual ones, the settlement user or the dish machine operator triggers the error correction access interface, and displays a list of similar dishes for each selected dish through the dish machine. Then, any similar dish from the list of similar dishes can be selected to replace any selected dish, thereby improving the efficiency of error correction for misidentification of dish categories.

[0027] In specific implementation, on the basis of realizing dish category correction through a list of similar dishes, optionally, the dish category identification includes: splitting the dish image to obtain a feature image of each selected dish in the dish combination; calculating the similarity between each selected dish and each candidate dish in the dish library based on the feature image and the historical behavior data, and determining the dish category of each selected dish according to the similarity calculation result.

[0028] Specifically, the dish images are split according to the dish categories, and the feature images of each selected dish in the dish combination are obtained. The feature images of each selected dish are combined with the historical behavior data of the settlement user, and each selected dish is matched with each candidate dish in the dish library. In short, each selected dish in the selected dishes is matched with each candidate dish in the dish library, that is, the similarity between each selected dish and each candidate dish in the dish library is calculated, and the dish category of each selected dish is determined with the help of the calculated similarity.

[0029] Furthermore, on the basis of realizing dish category correction through a similar dish list and determining the dish category of each selected dish by calculating the similarity between each selected dish in the dish combination and each candidate dish in the dish library, in order to increase the accuracy of dish identification and the flexibility of dish identification, optionally, the output of the dish identification model includes the dish category of each selected dish, and the similar dish category of each selected dish; wherein the similar dish category is the dish category of each candidate dish in the dish library whose similarity with the each selected dish meets a preset condition, and the similar dish list is composed of each candidate dish of the similar dish category.

[0030] Specifically, after calculating the similarity between each selected dish and each candidate dish in the dish library, and determining the dish category of each selected dish with the help of the calculated similarity, the dish recognition model outputs the dish category of each selected dish, that is, after calculating the similarity between any one of the selected dishes and each candidate dish in the dish library, the calculated similarities are sorted, and the candidate dish category corresponding to the similarity whose sorting position is at a preset position is the dish category of the any one selected dish. In order to facilitate the correction of misidentification of dish categories, the dish recognition model outputs the dish category of each selected dish and also outputs similar dish categories of each selected dish. The similar dish categories are dish categories whose sorting position of the similarity calculated above is after the preset position but meet the preset conditions (for example, the similarity is greater than or equal to the similarity threshold of 85%). For example, there are 5 candidate dish categories whose similarity is greater than or equal to the similarity threshold 85%. The dish category with the highest similarity is selected as the dish category of any of the selected dishes, and the remaining 4 dish categories are selected as similar dish categories of the any of the selected dishes.

[0031] On the basis of correcting dish categories through a list of similar dishes and determining the dish categories of selected dishes by calculating the similarities between each selected dish in the dish combination and each candidate dish in the dish library, optionally, the historical behavior data includes at least one of the following: dish consumption records, user portrait data, and behavior characteristic data; the dish consumption records include historical dish consumption records, such as the dish combination in the previous dish consumption record of the settlement user is a combination of "dish A", "dish B", and "dish C", and the behavior characteristic data refers to behavior preference data, such as preference for spicy food and love of fast food.

[0032] In addition, in addition to the above-mentioned implementation method of implementing dish type correction through a similar dish list, this embodiment can also directly input dish keywords, use keyword search to determine corresponding candidate dishes, and then replace any selected dish in the dish combination according to the candidate dishes, so as to adapt to a variety of dish type correction scenarios and meet the diverse needs of users. In an optional implementation method provided by this embodiment, the execution process of implementing dish type correction through dish keywords specifically includes: According to the dish keyword input through the dish machine, the candidate dishes corresponding to the dish keyword are retrieved from the dish library and displayed through the dish machine; If a replacement instruction to replace any selected dish in the dish combination based on the candidate dish is detected, the any selected dish is updated to the candidate dish.

[0033] The dish keywords include category keywords and ingredient keywords.

[0034] For example, the dish keyword input through the dish machine is the ingredient keyword, and the candidate dish corresponding to the ingredient keyword retrieved in the dish library is "dish A", and the retrieved candidate dish "dish A" is displayed on the dish machine. If a replacement instruction is detected to replace any selected dish in the dish combination based on the candidate dish "dish A", it means that error correction is performed on the dish type, and any selected dish is updated to a candidate dish. It should be noted that the candidate dishes retrieved from the dish library according to the dish keyword can be one or more. For example, the corresponding candidate dishes retrieved from the dish library according to the ingredient keyword include "dish A" and "dish B". In this case, by displaying "dish A" and "dish B" through the dish machine, any selected dish can be replaced with any one of "dish A" and "dish B".

[0035] It should be added that the dish keywords and replacement instructions entered through the dish machine can be input by the settlement user on the one hand, and by the operator of the dish machine on the other hand, to provide assistance to some users who do not know how to use the dish machine, and at the same time, reduce human contact in the context of public health events.

[0036] Step S108, calculating the pending fees of the dish combination according to the dish types, and performing settlement processing of the pending fees based on the payment token of the settlement user.

[0037] The settlement fees described in this embodiment refer to the fees that need to be settled for each selected dish in the dish combination; the payment token is generated after the settlement user registers in the target subprogram, or after the institution where the settlement user is located (such as an enterprise) registers for the enterprise employees in the target subprogram, and is issued to the settlement user.

[0038] The above-mentioned input of dish images and historical behavior data of the settlement user into the dish recognition model is used to identify the dish category, and the dish category of each selected dish in the dish combination is obtained. This embodiment calculates the settlement fee of the dish combination according to the dish category, and uses the payment token of the settlement user to settle the settlement fee of the dish combination to ensure the account security of the settlement user.

[0039] In specific implementation, during the process of settling pending fees based on the payment token of the settlement user, the following operations are performed: a settlement request carrying the payment token and the pending fees is generated and issued to a target subprogram; in response to the settlement request, the target subprogram deducts the pending fees from the settlement user's funds account based on the payment token.

[0040] In actual applications, after identifying the category of each selected dish in the dish combination, the user may not notice the incorrect identification of the dish category, resulting in an error in the calculation of the pending fees, and then causing an incorrect deduction of funds for the settlement user. In view of this, in this embodiment, after the settlement processing is performed for the settlement fees of each selected dish in the identified dish combination, the settlement user can change the category of any selected dish in each selected dish and submit it. Specifically, in an optional implementation provided by this embodiment, after calculating the pending fees of the dish combination according to the dish category and performing the settlement processing of the pending fees based on the payment token of the settlement user, the following operations are also performed: Pushing a settlement message of the dish combination to the settlement user through a target subprogram; the settlement message carries the dish category of each selected dish in the dish combination; If an updated dish combination submitted by the settlement user through the target subprogram is detected, the total cost of the updated dish combination is calculated according to the dish type of each updated dish in the updated dish combination; The difference fee is calculated based on the total fee and the fee to be settled, and the difference fee is settled or refunded.

[0041] The updated dish combination refers to a dish combination after the dish category of any one or more selected dishes in the dish combination corresponding to the above settlement process is updated. For example, the dish combination corresponding to the above settlement process is "dish A" and "dish B", and the updated dish combination is "dish A" and "dish C".

[0042] Specifically, a settlement message is pushed to the settlement user through the target subroutine. The settlement message carries the types of dishes selected in the dish combination to enhance the user's perception. After viewing the settlement message, if it is detected that the settlement user has submitted an updated dish combination through the target subroutine, it represents that the settlement user has submitted a dish type correction. The total cost of the updated dish combination is calculated based on the types of dishes of each updated dish in the updated dish combination, and the difference between the total cost and the pending cost is calculated, i.e., the difference cost. The difference cost is used for the next dish consumption settlement of the settlement user or the difference cost is returned to the settlement user, thereby further enhancing the user experience.

[0043] In the specific implementation process, for dish identification, the role of the dish identification model is crucial, and a higher recognition accuracy rate is required. The following is a specific description of the two implementation methods for improving the recognition accuracy rate of the dish identification model provided in this embodiment.

[0044] (1) constructing training samples based on the dish categories of the updated dishes and the dish categories of the selected dishes, and performing supervised training on the dish recognition model based on the constructed training samples.

[0045] The dish categories of each updated dish and the dish categories of each selected dish are used as training samples, and the dish recognition model is supervised trained through the training samples, so as to improve the recognition accuracy of the dish recognition model.

[0046] (2) Adjusting parameters of the dish recognition model according to the dish categories of the updated dishes and the dish categories of the selected dishes.

[0047] It should be added that by comparing the dish categories of each updated dish with the dish categories of each selected dish, the recognition accuracy of the dish recognition model for each selected dish is determined, and the parameters of the dish recognition model are adjusted according to the recognition accuracy.

[0048] In the process of improving the recognition accuracy of the dish recognition model, any one of the above two implementation methods can be selected for execution.

[0049] The following takes the application of a dish settlement processing method based on identity recognition provided in this embodiment in a group dining scenario as an example to further illustrate the dish settlement processing method based on identity recognition provided in this embodiment, see Figure 3 , an identity recognition-based dish settlement processing method applied to group dining scenarios, specifically steps S302 to S326.

[0050] Step S302, obtaining the group meal dish image and the face image of the group meal dish combination to be identified collected by the dish machine.

[0051] Step S304, input the face image into the identity recognition model stored in the food processing machine for offline identity recognition, and use the user corresponding to the user identification output by the identity recognition model as the settlement user.

[0052] Step S306: If the user identifier output by the identity recognition model is empty, the remote identity recognition interface is called to perform identity recognition processing on the face image, and the user corresponding to the user identifier returned by the remote identity recognition interface is used as the settlement user.

[0053] Step S308: Associating the group meal dish image with the settlement user.

[0054] Step S310: input the group meal dish image and the historical behavior data of the settlement user into the dish recognition model to perform dish category recognition, and obtain the dish category of each selected dish in the group meal dish combination.

[0055] Among them, the execution process of dish category recognition specifically includes: splitting the group meal dish images to obtain the feature images of each selected dish in the group meal dish combination; based on the feature images and historical behavior data, calculating the similarity between each selected dish and each candidate dish in the dish library, and determining the dish category of each selected dish according to the similarity calculation results.

[0056] Specifically, in the process of calculating the similarity between each selected dish and each candidate dish in the dish library, the similarity between each selected dish and each candidate dish in the dish library is calculated, and the dish category of each selected dish in the selected dishes is determined based on the similarity calculation results.

[0057] It should be noted that the output of the dish recognition model includes the dish category of each selected dish and the similar dish category of each selected dish; the similar dish category is the dish category of each candidate dish in the dish library whose similarity with each selected dish meets the preset conditions, and the similar dish list is composed of the candidate dishes of the similar dish category.

[0058] Specifically, the similar dish category of each selected dish is the dish category of the candidate dishes in the dish library whose similarity with the selected dish meets the preset conditions, and the similar dish list of each selected dish is composed of candidate dishes of the similar dish category.

[0059] Step S312, obtaining a list of similar dishes to each selected dish and displaying it through a dish machine.

[0060] Step S314: If a replacement instruction is detected to replace any selected dish in the group meal dish combination with any similar dish in the similar dish list, any selected dish is updated to any similar dish.

[0061] Step S316, calculate the pending fees of the group meal dish combination according to the dish types, generate a settlement request carrying the payment token and the pending fees, and send it to the target subroutine.

[0062] The dish categories include any dish categories of similar dishes and the dish categories of selected dishes that have not been updated.

[0063] Afterwards, in response to the settlement request, the target subprogram deducts the pending fees from the settlement user's fund account based on the payment token.

[0064] Step S318: Push the settlement message of the group meal dish combination to the settlement user through the target subprogram.

[0065] The settlement message carries the types of dishes selected in the group meal combination.

[0066] Step S320: If an updated group meal dish combination submitted by the settlement user through the target subprogram is detected, the total cost of the updated group meal dish combination is calculated according to the dish type of each updated dish in the updated group meal dish combination.

[0067] Step S322, calculate the difference in cost based on the total cost and the pending cost, and perform settlement or refund processing on the difference in cost.

[0068] Step S324, constructing training samples based on the dish category of each updated dish and the dish category of each selected dish, and performing supervised training on the dish recognition model based on the constructed training samples.

[0069] In addition, step S324 may also be replaced by: adjusting the parameters of the dish recognition model according to the dish category of each updated dish and the dish category of each selected dish.

[0070] In summary, the dish settlement processing method based on identity recognition provided in this embodiment first obtains the dish image and user identity image of the dish combination to be identified collected by the dish machine, inputs the user identity image into the identity recognition model stored in the dish machine for offline identity recognition, and uses the user corresponding to the user identifier output by the identity recognition model as the settlement user. If the user identifier output by the identity recognition model is empty, call the remote identity recognition interface to perform identity recognition processing on the user identity image, use the user corresponding to the user identifier returned by the remote identity recognition interface as the settlement user, and associate the dish image with the settlement user. Through identity recognition technology and big data behavior preference analysis, the accuracy of dish recognition is enhanced. In the context of the normalization of public health events, with the help of dish intelligent recognition technology, human contact is reduced; Secondly, the dish image and the historical behavior data of the settlement user are input into the dish recognition model to identify the dish category, obtain the dish category of each selected dish in the dish combination, obtain a list of similar dishes for each selected dish and display it through the dish machine. If a replacement instruction based on any similar dish in the similar dish list to replace any selected dish in the dish combination is detected, any selected dish is updated to any similar dish. In addition, according to the dish keywords input through the dish machine, candidate dishes corresponding to the dish keywords can be retrieved in the dish library and displayed through the dish machine. If a replacement instruction based on the candidate dish to replace any selected dish in the dish combination is detected, any selected dish is updated to the candidate dish. The rights and interests of users are protected by correcting the misidentification of dish categories, and the user experience is improved. Finally, the pending fees of the dish combination are calculated according to the types of dishes, and the pending fees are settled based on the payment token of the settlement user. The settlement message of the dish combination is pushed to the settlement user through the target subroutine. If an updated dish combination is detected submitted by the settlement user through the target subroutine, the total cost of the updated dish combination is calculated according to the types of dishes of each updated dish in the updated dish combination, the difference is calculated based on the total cost and the pending fees, and the difference is settled or returned to ensure the safety of users' funds. Compared with using smart plates to complete dish identification, this can reduce costs.

[0071] An embodiment of a dish settlement processing device based on identity recognition provided in this specification is as follows: In the above-mentioned embodiment, a method for processing dish settlement based on identity recognition is provided, and correspondingly, a device for processing dish settlement based on identity recognition is also provided, which will be described below in conjunction with the accompanying drawings.

[0072] Reference Figure 4 , which shows a schematic diagram of a dish settlement processing device based on identity recognition provided in this embodiment.

[0073] Since the device embodiment corresponds to the method embodiment, the description is relatively simple, and the relevant parts can refer to the corresponding description of the method embodiment provided above. The device embodiment described below is only illustrative.

[0074] This embodiment provides a dish settlement processing device based on identity recognition, including: An image acquisition module 402 is configured to acquire a dish image of a dish combination to be identified and a user identity image collected by a dish machine; A settlement user identification module 404 is configured to identify the settlement user corresponding to the user identity image and associate the dish image with the settlement user; A dish category recognition module 406 is configured to input the dish image and the historical behavior data of the settlement user into a dish recognition model to perform dish category recognition, and obtain the dish category of each selected dish in the dish combination; The settlement processing module 408 is configured to calculate the pending fees of the dish combination according to the dish type, and perform settlement processing of the pending fees based on the payment token of the settlement user.

[0075] An embodiment of a dish settlement processing device based on identity recognition provided in this specification is as follows: Corresponding to the above-described method for processing dish settlement based on identity recognition, based on the same technical concept, one or more embodiments of this specification further provide a dish settlement processing device based on identity recognition, and the dish settlement processing device based on identity recognition is used to execute the above-described method for processing dish settlement based on identity recognition. Figure 5 A schematic diagram of the structure of a dish settlement processing device based on identity recognition provided in one or more embodiments of this specification.

[0076] This embodiment provides a dish settlement processing device based on identity recognition, including: like Figure 5As shown, the dish settlement processing device based on identity recognition may have relatively large differences due to different configurations or performances, and may include one or more processors 501 and memory 502, and the memory 502 may store one or more storage applications or data. Among them, the memory 502 may be a short-term storage or a persistent storage. The application stored in the memory 502 may include one or more modules (not shown in the figure), and each module may include a series of computer executable instructions in the dish settlement processing device based on identity recognition. Further, the processor 501 may be configured to communicate with the memory 502, and execute a series of computer executable instructions in the memory 502 on the dish settlement processing device based on identity recognition. The dish settlement processing device based on identity recognition may also include one or more power supplies 503, one or more wired or wireless network interfaces 504, one or more input / output interfaces 505, one or more keyboards 506, etc.

[0077] In a specific embodiment, the dish settlement processing device based on identity recognition includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer executable instructions in the dish settlement processing device based on identity recognition, and the one or more programs are configured to be executed by one or more processors, including the following computer executable instructions: Acquire a dish image of a dish combination to be identified and a user identity image collected by a dish machine; Identify the settlement user corresponding to the user identity image, and associate the dish image with the settlement user; Inputting the dish image and the historical behavior data of the settlement user into a dish recognition model to perform dish category recognition, and obtaining the dish category of each selected dish in the dish combination; The pending fees of the dish combination are calculated according to the dish types, and the pending fees are settled based on the payment token of the settlement user.

[0078] An embodiment of a storage medium provided in this specification is as follows: Corresponding to the above-described method for processing meal settlement based on identity recognition, based on the same technical concept, one or more embodiments of this specification also provide a storage medium.

[0079] The storage medium provided in this embodiment is used to store computer executable instructions, and the computer executable instructions implement the following process when executed by a processor: Acquire a dish image of a dish combination to be identified and a user identity image collected by a dish machine; Identify the settlement user corresponding to the user identity image, and associate the dish image with the settlement user; Inputting the dish image and the historical behavior data of the settlement user into a dish recognition model to perform dish category recognition, and obtaining the dish category of each selected dish in the dish combination; The pending fees of the dish combination are calculated according to the dish types, and the pending fees are settled based on the payment token of the settlement user.

[0080] It should be noted that the embodiment of the storage medium in this specification and the embodiment of the dish settlement processing method based on identity recognition in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned corresponding method, and the repeated parts will not be repeated.

[0081] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0082] In the 1930s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements to method flows). However, with the development of technology, many of today's method flow improvements can be regarded as direct improvements to hardware circuit structures. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using hardware entity modules. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask chip manufacturers to design and produce dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0083] The controller may be implemented in any suitable manner, for example, the controller may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, and the memory controller may also be implemented as part of the control logic of the memory. It is also known to those skilled in the art that, in addition to implementing the controller in a purely computer-readable program code manner, the controller may be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, such a controller may be considered as a hardware component, and the devices for implementing various functions included therein may also be considered as structures within the hardware component. Or even, the devices for implementing various functions may be considered as both software modules for implementing the method and structures within the hardware component.

[0084] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0085] For the convenience of description, the above devices are described in terms of functions and are divided into various units. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0086] It should be understood by those skilled in the art that one or more embodiments of the present specification may be provided as a method, system or computer program product. Therefore, one or more embodiments of the present specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0087] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0088] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0089] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0090] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0091] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0092] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined in this article, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0093] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0094] One or more embodiments of the present specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0095] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0096] The above description is only an embodiment of this document and is not intended to limit this document. For those skilled in the art, this document may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this document should be included in the scope of the claims of this document.

Claims

1. A method for processing dish settlement based on identity recognition, comprising: Acquire a dish image of a dish combination to be identified and a user identity image collected by a dish machine; Identify the settlement user corresponding to the user identity image, and associate the dish image with the settlement user; Identify the dish category based on the dish image and the historical behavior data of the settlement user to obtain the dish category of each selected dish in the dish combination; Determine corresponding candidate dishes according to the input dish keywords, and replace any selected dish in the dish combination according to the candidate dishes; The pending fees of the dish combination are calculated according to the types of dishes, and the settlement of the pending fees is performed based on the payment token of the settlement user.

2. According to the method for processing dish settlement based on identity recognition in claim 1, the dish type recognition comprises: Splitting the dish image to obtain a characteristic image of each selected dish in the dish combination; Based on the feature image and the historical behavior data, similarity calculation is performed between each selected dish and each candidate dish in the dish library, and the dish category of each selected dish is determined according to the similarity calculation result.

3. According to the method for processing dish settlement based on identity recognition in claim 2, the step of performing dish category recognition based on the dish image and the historical behavior data of the settlement user to obtain the dish category of each selected dish in the dish combination is performed based on a dish recognition model; the output of the dish recognition model includes the dish category of each selected dish and the dish category similar to each selected dish; in, The similar dish categories are the dish categories of each candidate dish in the dish library whose similarity with each selected dish meets a preset condition.

4. According to the method for processing dish settlement based on identity recognition in claim 1, the step of determining the corresponding candidate dish according to the input dish keyword and replacing any selected dish in the dish combination according to the candidate dish comprises: According to the dish keyword input through the dish machine, the candidate dishes corresponding to the dish keyword are retrieved from the dish library and displayed through the dish machine; If a replacement instruction to replace any selected dish in the dish combination based on the candidate dish is detected, any selected dish in the dish combination is updated to the candidate dish.

5. According to the method for processing dish settlement based on identity recognition in claim 1, after the step of calculating the pending fees of the dish combination according to the dish type and performing the settlement processing step of the pending fees based on the payment token of the settlement user is executed, the method further comprises: Pushing a settlement message of the dish combination to the settlement user through a target subprogram; The settlement message carries the category of each selected dish in the dish combination; If an updated dish combination submitted by the settlement user through the target subprogram is detected, the total cost of the updated dish combination is calculated according to the dish type of each updated dish in the updated dish combination; The difference fee is calculated based on the total fee and the fee to be settled, and the difference fee is settled or refunded.

6. The method for processing dish settlement based on identity recognition according to claim 5, further comprising: Constructing training samples based on the dish categories of each updated dish and the dish categories of each selected dish, and performing supervised training on the dish recognition model according to the constructed training samples; or, According to the dish categories of the updated dishes and the dish categories of the selected dishes, the parameters of the dish recognition model are adjusted.

7. According to the method for processing meal settlement based on identity recognition as claimed in claim 1, the settlement processing of the pending fees based on the payment token of the settlement user comprises: Generate a settlement request carrying the payment token and the pending fees and send it to the target subprogram; In response to the settlement request, the target subprogram deducts the pending fees from the settlement user's fund account based on the payment token.

8. The method for processing dish settlement based on identity recognition according to claim 1, wherein the step of identifying the settlement user corresponding to the user identity image comprises: Input the user identity image into the identity recognition model stored in the food processing machine for offline identity recognition, and use the user corresponding to the user identification output by the identity recognition model as the settlement user; If the user identifier output by the identity recognition model is empty, a remote identity recognition interface is called to perform identity recognition processing on the user identity image, and the user corresponding to the user identifier returned by the remote identity recognition interface is used as the settlement user.

9. A dish settlement processing device based on identity recognition, comprising: An image acquisition module is configured to acquire a dish image of a dish combination to be identified and a user identity image collected by a dish machine; a settlement user identification module, configured to identify the settlement user corresponding to the user identity image, and associate the dish image with the settlement user; a dish category recognition module, configured to perform dish category recognition based on the dish image and the historical behavior data of the settlement user, and obtain the dish category of each selected dish in the dish combination; Determine corresponding candidate dishes according to the input dish keywords, and replace any selected dish in the dish combination according to the candidate dishes; The settlement processing module is configured to calculate the pending fees of the dish combination according to the dish type, and perform settlement processing of the pending fees based on the payment token of the settlement user.

10. A dish settlement processing device based on identity recognition, comprising: processor; and a memory configured to store computer executable instructions that, when executed, cause the processor to: Acquire a dish image of a dish combination to be identified and a user identity image collected by a dish machine; Identify the settlement user corresponding to the user identity image, and associate the dish image with the settlement user; Identify the dish category based on the dish image and the historical behavior data of the settlement user to obtain the dish category of each selected dish in the dish combination; Determine corresponding candidate dishes according to the input dish keywords, and replace any selected dish in the dish combination according to the candidate dishes; The pending fees of the dish combination are calculated according to the types of dishes, and the settlement of the pending fees is performed based on the payment token of the settlement user.

11. A storage medium for storing computer executable instructions, wherein the computer executable instructions implement the following process when executed by a processor: Acquire a dish image of a dish combination to be identified and a user identity image collected by a dish machine; Identify the settlement user corresponding to the user identity image, and associate the dish image with the settlement user; Identify the dish category based on the dish image and the historical behavior data of the settlement user to obtain the dish category of each selected dish in the dish combination; Determine corresponding candidate dishes according to the input dish keywords, and replace any selected dish in the dish combination according to the candidate dishes; The pending fees of the dish combination are calculated according to the types of dishes, and the settlement of the pending fees is performed based on the payment token of the settlement user.

Images