Food recommendation result generation method and device, equipment and storage medium

Abstract

The invention provides a food recommendation result generation method and device, equipment and a storage medium, and can be applied to the technical field of artificial intelligence and the technical field of financial science and technology. The method comprises the steps that an object signal image and a food signal image are acquired, the object signal image represents the object smell of a target object, and the food signal image represents the food smell; preprocessing the object signal image according to the waveform characteristics of the object signal image to obtain a target object signal image; performing object recognition according to the target object signal image to obtain a target object corresponding to the target object signal image; matching the historical food signal image with the food signal image to obtain a food recommendation result corresponding to the target object, the historical food signal image being related to the target object; and sending the food recommendation result to a client related to the target object.

Description

Technical Field

[0001] The present disclosure relates to the fields of artificial intelligence technology and financial technology, and in particular to a method, device, equipment, medium and program product for generating food recommendation results. Background Art

[0002] With the development of society, people have higher requirements for dining experience. For the convenience of life, most people choose to eat in the company. However, the company has a large number of employees, the dining time is relatively fixed, and the dishes provided are relatively fixed, which leads to problems such as poor dining experience for employees.

[0003] Specifically, the waiting time for some dishes that are popular among employees is long, the dishes supplied are relatively fixed, and they cannot meet the individual needs of employees. Summary of the invention

[0004] In view of the above problems, the present disclosure provides a method, device, equipment, medium and program product for generating food recommendation results.

[0005] According to a first aspect of the present disclosure, a method for generating food recommendation results is provided, comprising: acquiring an object signal image and a food signal image, wherein the object signal image represents the object odor of a target object, and the food signal image represents the food odor. Preprocessing the object signal image according to the waveform characteristics of the object signal image to obtain a target object signal image. Performing object recognition according to the target object signal image to obtain a target object corresponding to the object signal image. Matching a historical food signal image with the food signal image to obtain a food recommendation result corresponding to the target object, wherein the historical food signal image is related to the target object. Sending the food recommendation result to a client related to the target object.

[0006] According to an embodiment of the present disclosure, preprocessing the object signal image according to the waveform characteristics of the object signal image to obtain the target object signal image includes: determining the target characteristics from the waveform characteristics of the object signal image according to a preset waveform characteristic threshold. According to the target characteristics, performing noise reduction processing on the object signal image to obtain the target object signal image.

[0007] According to an embodiment of the present disclosure, the target feature includes a first target feature and a second target feature, the first target feature is greater than a waveform feature threshold, and the second target feature is less than the waveform feature threshold. According to the target feature, the object signal image is subjected to noise reduction processing to obtain the target object signal image, including: determining first voltage signal information corresponding to the first target feature. Determining second voltage signal information corresponding to the second target feature. According to the first voltage signal information and the second voltage signal information, the object signal image is subjected to noise reduction processing to obtain the target object signal image.

[0008] According to an embodiment of the present disclosure, performing object recognition based on a target object signal image to obtain a target object corresponding to the object signal image includes: extracting features from the target object signal image to obtain an object feature image. Performing object recognition based on the object feature image to obtain a target object corresponding to the object signal image.

[0009] According to an embodiment of the present disclosure, feature extraction is performed on a target object signal image to obtain an object feature image, including: performing global feature extraction on the target object signal image to obtain a first feature image. The first feature image is input into a local feature extraction sublayer to output a second feature image, and the object feature image includes the first feature image and the second feature image.

[0010] According to an embodiment of the present disclosure, the historical food signal image includes at least one historical food signal image block, the historical video signal image block corresponds to the historical food feature vector, the food signal image includes at least one food feature image block, the food feature image block corresponds to the food feature vector, and the historical food signal image is matched with the food signal image to obtain a food recommendation result corresponding to the target object, including: performing similarity calculation on the historical food signal image and the food signal image according to the historical food feature vector and the food feature vector, and obtaining a similarity result corresponding to the food signal image. According to the similarity result, a food recommendation result matching the target object is obtained.

[0011] According to an embodiment of the present disclosure, the food recommendation result includes at least one food signal image and recommended exchange value information corresponding to the food signal image, and the method further includes: obtaining historical exchange value information corresponding to the historical food signal image. Comparing the recommended exchange value information with the historical exchange value information to obtain an exchange value comparison result. According to the exchange value comparison result, determining a target food signal image from at least one food signal image.

[0012] According to an embodiment of the present disclosure, the object signal image is collected by an odor collection device, and the method further includes: determining target location information corresponding to the odor collection device according to device identification information of the odor collection device. Sending the target location information to the client, wherein the client is adapted to generate food delivery information according to the target location information, and the food delivery information indicates that the target food corresponding to the target food signal image is delivered to the target location.

[0013] The second aspect of the present disclosure provides a device for generating food recommendation results, including: a first acquisition module, used to acquire an object signal image and a food signal image, the object signal image represents the object odor of the target object, and the food signal image represents the food odor. A preprocessing module, used to preprocess the object signal image according to the waveform characteristics of the object signal image to obtain the target object signal image. An object recognition module, used to perform object recognition based on the target object signal image to obtain the target object corresponding to the object signal image. A matching module, used to match the historical food signal image with the food signal image to obtain the food recommendation result corresponding to the target object, the historical food signal image is related to the target object. A first sending module, used to send the food recommendation result to a client related to the target object.

[0014] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above method.

[0015] The fourth aspect of the present disclosure also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the above method.

[0016] The fifth aspect of the present disclosure also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0017] According to the food recommendation result generation method, device, equipment, medium and program product provided by the present disclosure, by acquiring the object signal image and the food signal image, and pre-processing the object signal image according to the waveform characteristics of the object signal image, the obtained target object signal image can more accurately represent the smell of the target object, and then the object recognition is performed according to the target object signal image, so that the target object corresponding to the object signal image can be accurately determined, thereby improving the accuracy of the target object recognition. By matching the historical food signal image related to the target object with the food signal image, the food recommendation result corresponding to the target object can be made to more accurately meet the target object's demand for food, thereby improving the accuracy of personalized recommendations. The client can arrange future food supply based on the received food recommendation results, at least partially solving the problem of poor dining experience for employees. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0019] Figure 1A diagram schematically shows an application scenario of the method for generating food recommendation results according to an embodiment of the present disclosure;

[0020] Figure 2 A flowchart of a method for generating food recommendation results according to an embodiment of the present disclosure is schematically shown;

[0021] Figure 3 A schematic diagram schematically shows a method of extracting features from a target object signal image to obtain an object feature image according to an embodiment of the present disclosure;

[0022] Figure 4 A schematic diagram of a dining tray device according to an embodiment of the present disclosure is schematically shown;

[0023] Figure 5 The working diagram of the embedded electronic nose device according to the embodiment of the present disclosure is schematically shown;

[0024] Figure 6 A structural block diagram of a device for generating food recommendation results according to an embodiment of the present disclosure is schematically shown; and

[0025] Figure 7 A block diagram of an electronic device suitable for implementing a method for generating food recommendation results according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0026] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0027] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0028] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0029] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0030] In the technical solution of the present invention, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0031] During peak employee dining times, the restaurant cannot accurately arrange dishes according to employees' personal preferences, resulting in a poor employee experience.

[0032] In view of this, an embodiment of the present disclosure provides a method for generating food recommendation results, including: acquiring an object signal image and a food signal image, wherein the object signal image represents the object odor of a target object, and the food signal image represents the food odor. Preprocessing the object signal image according to the waveform characteristics of the object signal image to obtain a target object signal image. Performing object recognition according to the target object signal image to obtain a target object corresponding to the object signal image. Matching a historical food signal image with the food signal image to obtain a food recommendation result corresponding to the target object, wherein the historical food signal image is related to the target object. Sending the food recommendation result to a client related to the target object.

[0033] Figure 1 The application scenario diagram for generating food recommendation results according to an embodiment of the present disclosure is schematically shown.

[0034] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0035] The user may use at least one of the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0036] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, etc. For example, the first terminal device 101 can be a device with an odor collection device, and the second terminal device 102 can be a client related to the target object.

[0037] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0038] It should be noted that the food recommendation result generation method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the food recommendation result generation device provided in the embodiment of the present disclosure can generally be set in the server 105. The food recommendation result generation method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the food recommendation result generation device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0039] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0040] Figure 2 The flowchart of the method for generating food recommendation results according to an embodiment of the present disclosure is schematically shown.

[0041] like Figure 2As shown, the method for generating food recommendation results in this embodiment includes operations S210 to S250.

[0042] In operation S210, an object signal image and a food signal image are acquired.

[0043] In operation S220, the object signal image is preprocessed according to the waveform characteristics of the object signal image to obtain a target object signal image.

[0044] In operation S230, object recognition is performed according to the target object signal image to obtain a target object corresponding to the object signal image.

[0045] In operation S240, the historical food signal image is matched with the food signal image to obtain a food recommendation result corresponding to the target object.

[0046] In operation S250, the food recommendation result is sent to a client associated with the target object.

[0047] According to an embodiment of the present disclosure, a food signal image represents food odor. The food odor information is converted into an electrical signal, and the food signal image can be an electrical signal image of the food odor. For example, a voltage signal image, a current signal image, an analog signal image, etc. The food signal image can include multiple food odors.

[0048] According to an embodiment of the present disclosure, the object signal image represents the object odor of the target object. The object signal image is converted into an electrical signal, and the object signal image can also be an electrical signal image. Like the food signal image, the object signal image can be a voltage signal image, a current signal image, an analog signal image, etc. of the object odor.

[0049] According to an embodiment of the present disclosure, the historical food signal image is related to the target object, wherein the historical food signal image may include a variety of food odors.

[0050] According to an embodiment of the present disclosure, the waveform feature of the object signal image may be the change of the electrical signal within a period of time presented by the electrical signal image of the object odor. For example, from 0 to 0.02 seconds, the electrical signal value of the object odor decreases successively, and from 0.02 seconds to 0.65 seconds, it increases successively.

[0051] According to an embodiment of the present disclosure, the object recognition method may be a neural network algorithm, a support vector machine algorithm, etc. For example, by using a neural network algorithm, object recognition is performed based on a target object signal image to obtain a target object corresponding to the object signal image.

[0052] According to an embodiment of the present disclosure, the historical food may be the food ordered by the target object in the restaurant in the past period of time, and the historical food signal image may be the odor signal image corresponding to the historical food. For example, the historical food signal image may be a voltage signal image, a current signal image, an analog signal image, etc. of the odor of the historical food.

[0053] According to an embodiment of the present disclosure, the historical food signal image is matched with the food signal image, and the matching information may be image information, food value information, etc. Matching image information may be to compare the historical food odor information with the food odor information to determine whether the historical food odor information and the food odor information are consistent. Matching food value information, firstly perform food identification based on the historical food signal image and the food signal image to obtain the target historical food and the target food, and then match the food value information of the target historical food with the target food value information to obtain the food recommendation result corresponding to the target object. The food value information may be nutritional value information, etc.

[0054] According to an embodiment of the present disclosure, the client associated with the target object may be a restaurant system, a food delivery vehicle system, etc., through which the target object orders food.

[0055] For example, the object may be an employee, and the client may be a restaurant system of a company. The restaurant system has a device for collecting the smell of the object and the smell of food, and obtains the object signal image and the food signal image by performing signal processing on the smell information. It is noted that the information related to the embodiments of the present disclosure is collected with the authorization of the employee or with full authorization of all parties.

[0056] The object odor and food odor are collected in the past period of time, and the processed historical food signal image is associated with the object odor corresponding to the historical food signal image and stored. The above information can be stored in a database.

[0057] When an employee comes to the restaurant for a meal, the employee's odor is collected to obtain an object signal image. According to the waveform characteristics of the object signal image, the object signal image is preprocessed to obtain a target object signal image. The employee is identified based on the target object signal image. The historical food signal images related to the employee are extracted from the database, and then the historical food signal images are matched with the food signal images to obtain the food recommendation results corresponding to the target object. The food recommendation results are sent to the restaurant system where the employee dines.

[0058] The food recommendation results corresponding to each employee are analyzed to obtain the food analysis results. The restaurant system can arrange food for future time periods based on the food analysis results.

[0059] According to the embodiments of the present disclosure, by acquiring an object signal image and a food signal image, and preprocessing the object signal image according to the waveform characteristics of the object signal image, the obtained target object signal image can more accurately characterize the smell of the target object, and then performing object recognition based on the target object signal image can accurately determine the target object corresponding to the object signal image, thereby improving the accuracy of target object recognition. By matching the historical food signal image related to the target object with the food signal image, the obtained food recommendation result corresponding to the target object can more accurately meet the target object's demand for food, thereby improving the accuracy of personalized recommendations. The client can arrange future food supply based on the received food recommendation results, thereby at least partially solving the problem of poor dining experience for employees.

[0060] According to an embodiment of the present disclosure, preprocessing the object signal image according to the waveform characteristics of the object signal image to obtain the target object signal image includes: determining the target characteristics from the waveform characteristics of the object signal image according to a preset waveform characteristic threshold. According to the target characteristics, performing noise reduction processing on the object signal image to obtain the target object signal image.

[0061] According to an embodiment of the present disclosure, the preset waveform feature threshold may be a preset electric signal threshold of the object odor. For example, a waveform feature greater than the preset waveform feature threshold is determined as a target feature. Alternatively, a waveform feature less than the preset waveform feature threshold is determined as a target feature.

[0062] According to an embodiment of the present disclosure, a target feature is determined from the waveform feature of an object signal image through a preset waveform feature threshold, and then the object signal image is denoised based on the target feature to reduce the noise of the object signal image, thereby making the information contained in the target object signal image more accurate.

[0063] According to an embodiment of the present disclosure, according to the target feature, performing noise reduction processing on the object signal image to obtain the target object signal image includes: determining first voltage signal information corresponding to the first target feature. Determining second voltage signal information corresponding to the second target feature. According to the first voltage signal information and the second voltage signal information, performing noise reduction processing on the object signal image to obtain the target object signal image.

[0064] According to an embodiment of the present disclosure, the target feature includes a first target feature and a second target feature, the first target feature is greater than a waveform feature threshold, and the second target feature is less than the waveform feature threshold.

[0065] For example, the first voltage signal information may be the voltage signal information with the largest value in the object signal image. The second voltage signal information may be the voltage signal information with the smallest value in the object signal image. As shown in formula (1):

[0066] x i =(V i max -V i min ) / V i min (1)

[0067] X i Represents the noise reduction voltage signal, V i max Indicates the maximum voltage signal, V i min Indicates the minimum voltage signal.

[0068] This method can further eliminate the existing superposition noise and the multiplication noise caused by channel imperfections while performing baseline suppression, thereby reducing the noise in the image.

[0069] According to an embodiment of the present disclosure, the object signal image is subjected to noise reduction processing through the first voltage signal information and the second voltage signal information to obtain a target object signal image, thereby reducing noise in the image, facilitating object recognition, and improving recognition accuracy.

[0070] According to an embodiment of the present disclosure, performing object recognition based on a target object signal image to obtain a target object corresponding to the object signal image includes: extracting features from the target object signal image to obtain an object feature image. Performing object recognition based on the object feature image to obtain a target object corresponding to the object signal image.

[0071] According to the embodiments of the present disclosure, the same model can be used to perform feature extraction on the target object signal image, and then perform object recognition. Different models can also be used to perform feature extraction and object recognition respectively. The model can be a deep convolutional neural network model, a support vector machine model, etc.

[0072] According to the embodiments of the present disclosure, by performing feature extraction on the target object signal image after noise reduction, the obtained object feature image is more accurate and the recognition rate is improved.

[0073] According to an embodiment of the present disclosure, feature extraction is performed on a target object signal image to obtain an object feature image, including: performing global feature extraction on the target object signal image to obtain a first feature image. The first feature image is input into a local feature extraction sublayer to output a second feature image, and the object feature image includes the first feature image and the second feature image.

[0074] According to an embodiment of the present disclosure, the trained Faster R-CNN model is used to extract features from a target object signal image to obtain an object feature image.

[0075] Figure 3 The schematic diagram schematically shows a method of extracting features from a target object signal image to obtain an object feature image according to an embodiment of the present disclosure.

[0076] like Figure 3 As shown in the figure, the target object signal image is input into the feature extraction layer to obtain the object feature image. The structure of the feature extraction layer includes a convolution sublayer 302 and a local feature extraction sublayer 304. Specifically, the target object signal image 301 is input into the convolution sublayer 302 for global feature extraction to obtain a first feature image 303. The first feature image 303 is input into the local feature extraction sublayer 304, and a second feature image 305 is output. The local feature extraction sublayer 304 can be the RPN layer (Region Proposal Network) in the trained FasterR-CNN model.

[0077] The obtained first feature image 303 and second feature image 305 are input into the trained ROI pooling sublayer 306 for classification recognition and regression. The ROI pooling sublayer 306, fully connected sublayer 1 (307), and fully connected sublayer 2 (310) are used for classification recognition, and finally a classification score 311 for the target object signal image 301 is obtained. The ROI pooling sublayer 306, fully connected sublayer 1 (307), and fully connected sublayer 3 (308) are used for regression, and finally a regression result 309 for the target object signal image 301 is obtained.

[0078] According to an embodiment of the present disclosure, a fully connected local feature extraction sublayer 304 (RPN) is established, and a high-quality second feature image can be trained in an end-to-end manner. Then, the first feature image and the second feature image trained by Faster R-CNN are input into the classification recognition layer, and a continuous convolution operation is performed on the object feature image to realize end-to-end training of the Faster R-CNN model.

[0079] According to the embodiment of the present disclosure, a first feature image is obtained by performing global feature extraction on the target object signal image, and the first feature image is input into a local feature extraction sublayer to output a second feature image, thereby improving the quality of the feature image.

[0080] According to an embodiment of the present disclosure, matching the historical food signal image with the food signal image to obtain a food recommendation result corresponding to the target object includes: performing similarity calculation on the historical food signal image and the food signal image according to the historical food feature vector and the food feature vector to obtain a similarity result corresponding to the food signal image. Based on the similarity result, a food recommendation result matching the target object is obtained.

[0081] According to an embodiment of the present disclosure, the historical food signal image includes at least one historical food signal image block, the historical video signal image block corresponds to the historical food feature vector, and the food signal image includes at least one food feature image block, the food feature image block corresponds to the food feature vector.

[0082] According to an embodiment of the present disclosure, the historical food signal image can be the food information collected by employees in a restaurant in one month. That is, the restaurant can store the dishes arranged weekly in the database and associate the employees with the food of each meal of the employees.

[0083] One month later, employees enter the restaurant and sit down at the dining table. The employee odor information is collected for 5 seconds to obtain the object signal image. The object signal image is sent to the server.

[0084] The server preprocesses the object signal image according to the waveform characteristics of the object signal image to obtain the target object signal image. Object recognition is performed based on the target object signal image to obtain the target object corresponding to the object signal image. Today's food is combined to obtain multiple groups of recommended foods, namely food signal images. The food signal image is matched with the historical food signal image for similarity calculation. The similarity calculation formula is shown in formula (2):

[0085]

[0086] d1 and d2 are the historical food signal images and food signal images, a i is the i-th historical food feature vector corresponding to the i-th historical food feature image block, b i is the i-th food feature vector corresponding to the i-th food feature image block. Sim(d1, d2) is the similarity between d1 and d2.

[0087] According to an embodiment of the present disclosure, by calculating the similarity between the historical food signal image and the food signal image based on the historical food feature vector and the food feature vector, the accuracy of personalized recommendation can be improved.

[0088] According to an embodiment of the present disclosure, the food recommendation result includes at least one food signal image and recommended exchange value information corresponding to the food signal image, and the method further includes: obtaining historical exchange value information corresponding to the historical food signal image. Comparing the recommended exchange value information with the historical exchange value information to obtain an exchange value comparison result. According to the exchange value comparison result, determining a target food signal image from at least one food signal image.

[0089] According to an embodiment of the present disclosure, at least one food signal image in the food recommendation result is sorted from high to low according to the similarity, and the first 10 food signal images in the list are taken. The historical exchange value information is compared with the first 10 recommended exchange value information in the similarity sequence from top to bottom one by one, and the food signal image with an error of 50% can be determined as the target food signal image.

[0090] According to an embodiment of the present disclosure, by comparing the recommended exchange value information with the historical exchange value information, suitable food may be recommended to the target object.

[0091] According to an embodiment of the present disclosure, the method further includes: determining target location information corresponding to the odor collection device according to device identification information of the odor collection device, and sending the target location information to the client, wherein the client is adapted to generate food delivery information according to the target location information, and the food delivery information indicates that the target food corresponding to the target food signal image is delivered to the target location.

[0092] According to an embodiment of the present disclosure, the object signal image is collected by an odor collection device.

[0093] According to an embodiment of the present disclosure, the device identification information of each odor collection device is stored in a database, and the device identification information is stored in association with the location information of the odor collection device.

[0094] According to the embodiment of the present disclosure, at a preset location, the target object presses the button of the odor collection device, and the odor collection device sends the location information to the server. The server compares the device identification information of the odor collection with the information in the database to obtain the target location information corresponding to the odor collection device.

[0095] According to an embodiment of the present disclosure, by determining the target location information corresponding to the odor collection device based on the device identification information of the odor collection device, the target food can be delivered to the target location, thereby reducing queues and congestion during peak dining hours.

[0096] According to an embodiment of the present disclosure, the odor collection device may be an embedded electronic nose device.

[0097] Figure 4 The figure schematically shows a dining tray device according to an embodiment of the present disclosure.

[0098] like Figure 4 As shown, by installing an embedded electronic nose device 402 in a dinner plate 401, after pressing the switch button of the dinner plate, food odor information can be collected, and each collection time can be 5 seconds, thereby generating a food signal image.

[0099] According to an embodiment of the present disclosure, by installing an embedded electronic nose device in the dining table, after the subject presses the switch button of the dinner plate, the subject's odor information can be collected, and each collection time can be 5 seconds, thereby generating a subject signal image.

[0100] Figure 5 The working diagram of the embedded electronic nose device according to the embodiment of the present disclosure is schematically shown.

[0101] like Figure 5 As shown, the embedded electronic nose device 510 includes an air pump 501, a closed air chamber 502, a gas sensor array, and an operational amplifier circuit 503. The air pump 501 provides gas to the closed air chamber through an air inlet arranged on the closed air chamber 502; a sensor array is arranged in the closed air chamber 502 for collecting gas fingerprint information of the gas in the closed air chamber. The sensor array consists of 5 gas sensors. By contacting the gas, the gas type and information related to the concentration are converted into a voltage signal, the fingerprint information of the gas is obtained, and the original data signal is provided for subsequent data processing and pattern recognition. The sensor array is encapsulated in the closed air chamber 502 and connected to the interface circuit, and the sensor array transmits the voltage signal to the interface circuit. The interface circuit realizes serial communication in an I / O interface simulation manner. The electronic nose device includes 5 device ends, and multiple device ends can collect sample data in parallel when collecting sample data, and the sensor array of each device end contains different sensors.

[0102] The embedded electronic nose system uses the STM32F103RCT6 microcontroller as the main control chip. Its memory includes 256K Flash (non-volatile memory) and 64K SRAM (volatile memory). The communication interface includes 3 SP1 (service provider interface), 2 I2C, 5 USART / UART (serial communication protocol), and 1 USB / CAN / SDIO (bus). Since the STM32F103RCT6 microcontroller does not contain a MAC controller (Media Access Control), a network chip or network module that implements the TCP / IP (Transmission Control Protocol / Internet Protocol) protocol stack is selected to connect the device to the network. The main control module is only responsible for operating application layer data. For wired Ethernet, the W5500 network chip is selected, an embedded Ethernet controller that integrates the hardware TCP / IP protocol stack, 10 / 100M Ethernet data link layer and physical layer. The network connection can be expanded in the single-chip system using a single chip. W5500 has 8 independent ports for simultaneous communication, a high-speed serial peripheral interface and an internal 32K-byte transceiver buffer. The wireless LAN uses the ESP8266EX network chip, which is highly integrated with antenna switches, RF, power amplifiers, low noise amplifiers, filters and power management modules, requiring only a few peripheral circuits. It has a built-in Tensilica L106 32-bit microcontroller with ultra-low power consumption and 16-bit RSIC (Reduced Instruction Set Computer), with a clock speed of up to 160MHZ (megahertz), and implements the WIFI protocol stack and TCP / IP protocol. It supports STA / AP / STA+AP working modes, where STA is station mode, that is, wifi works in wireless terminal mode; AP is access point mode, that is, wifi works in hotspot mode.

[0103] like Figure 5 As shown, after the server successfully establishes a network connection with the embedded electronic nose device 510 , the obtained object signal image and food signal image can be collected and then sent to the server 520 .

[0104] According to an embodiment of the present disclosure, the database may store historical food signal images, and may also store daily food lists and information binding tables.

[0105] The daily food list is used to store the restaurant's daily food types and exchange value information. When the restaurant service staff enters the food code of the day, the server receives the food code of the day and searches the daily food list for the exchange value information corresponding to the food code of the day.

[0106] The information binding status table is used to bind the plate information to the object, and the object to the meal food. For example, the object can be an employee, and the food can be a dish. When the employee takes the plate, the employee information is bound to the plate information. When the employee picks up the meal, the employee, plate, and dish information are bound. The information binding status table is used to record the time when the dish changes when the employee picks up the meal. If the dish does not change for more than 10 minutes, it is considered that the employee has finished picking up the meal, and the binding status is released at this time. The client can automatically deduct the exchange value information corresponding to the dish served by the employee.

[0107] The present disclosure also provides a device for generating food recommendation results. Figure 6 The device is described in detail.

[0108] Figure 6 The structural block diagram of the food recommendation result generating device according to the embodiment of the present disclosure is schematically shown.

[0109] like Figure 6 As shown, the food recommendation result generating device 600 of this embodiment includes a first acquisition module 610, a preprocessing module 620, an object recognition module 630, a matching module 640 and a first sending module 650.

[0110] The first acquisition module 610 is used to acquire the object signal image and the food signal image. In one embodiment, the first acquisition module 610 can be used to perform the operation S210 described above, which will not be described in detail here.

[0111] The preprocessing module 620 is used to preprocess the object signal image according to the waveform characteristics of the object signal image to obtain the target object signal image. In one embodiment, the preprocessing module 620 can be used to perform the operation S220 described above, which will not be described in detail here.

[0112] The object recognition module 630 is used to perform object recognition according to the target object signal image to obtain the target object corresponding to the object signal image. In one embodiment, the object recognition module 630 can be used to perform the operation S230 described above, which will not be described in detail here.

[0113] The matching module 640 is used to match the historical food signal image with the food signal image to obtain a food recommendation result corresponding to the target object. In one embodiment, the matching module 640 can be used to perform the operation S240 described above, which will not be repeated here.

[0114] The first sending module 650 is used to send the food recommendation result to the client related to the target object. In one embodiment, the first sending module 650 can be used to perform the operation S250 described above, which will not be repeated here.

[0115] According to an embodiment of the present disclosure, the preprocessing module 620 includes a determination submodule and a noise reduction processing submodule. The determination submodule is used to determine the target feature from the waveform feature of the object signal image according to a preset waveform feature threshold. The noise reduction processing submodule is used to perform noise reduction processing on the object signal image according to the target feature to obtain a target object signal image.

[0116] According to an embodiment of the present disclosure, the target feature includes a first target feature and a second target feature, the first target feature is greater than a waveform feature threshold, and the second target feature is less than the waveform feature threshold. The noise reduction processing submodule includes a first determination unit, a second determination unit, and a noise reduction processing unit. The first determination unit is used to determine the first voltage signal information corresponding to the first target feature. The second determination unit is used to determine the second voltage signal information corresponding to the second target feature. The noise reduction processing subunit is used to perform noise reduction processing on the object signal image according to the first voltage signal information and the second voltage signal information to obtain a target object signal image.

[0117] According to an embodiment of the present disclosure, the object recognition module 830 includes a feature extraction submodule and an object recognition submodule. The feature extraction submodule is used to extract features from the target object signal image to obtain an object feature image. The object recognition submodule is used to perform object recognition based on the object feature image to obtain a target object corresponding to the object signal image.

[0118] According to an embodiment of the present disclosure, the feature extraction submodule includes a global feature extraction unit and an input unit. The global feature extraction unit is used to perform global feature extraction on the target object signal image to obtain a first feature image. The input unit is used to input the first feature image into the local feature extraction sublayer and output a second feature image, and the object feature image includes the first feature image and the second feature image.

[0119] According to an embodiment of the present disclosure, the historical food signal image includes at least one historical food signal image block, the historical video signal image block corresponds to the historical food feature vector, and the food signal image includes at least one food feature image block, and the food feature image block corresponds to the food feature vector. The matching module 640 includes a similarity calculation submodule and an acquisition submodule. The similarity calculation submodule is used to perform similarity calculation on the historical food signal image and the food signal image according to the historical food feature vector and the food feature vector, and obtain a similarity result corresponding to the food signal image. The acquisition submodule is used to obtain a food recommendation result that matches the target object according to the similarity result.

[0120] According to an embodiment of the present disclosure, the food recommendation result includes at least one food signal image and recommended exchange value information corresponding to the food signal image. The above-mentioned device also includes a second acquisition module, a comparison module and a first determination module. The second acquisition module is used to obtain the historical exchange value information corresponding to the historical food signal image. The comparison module is used to compare the recommended exchange value information with the historical exchange value information to obtain an exchange value comparison result. The first determination module is used to determine the target food signal image from at least one food signal image based on the exchange value comparison result.

[0121] According to an embodiment of the present disclosure, the object signal image is collected by the odor collection device. The above-mentioned device also includes a second determination module and a sending module. The second determination module is used to determine the target location information corresponding to the odor collection device according to the device identification information of the odor collection device. The sending module is used to send the target location information to the client, wherein the client is suitable for generating food delivery information according to the target location information, and the food delivery information indicates that the target food corresponding to the target food signal image is delivered to the target location.

[0122] It should be noted that the food recommendation result generating device part in the embodiment of the present disclosure corresponds to the food recommendation result generating method part in the embodiment of the present disclosure. The description of the food recommendation result generating device part specifically refers to the food recommendation result generating method part, which will not be repeated here.

[0123] According to an embodiment of the present disclosure, any multiple modules among the first acquisition module 610, the preprocessing module 620, the object recognition module 630, the matching module 640 and the first sending module 650 can be combined in one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first acquisition module 610, the preprocessing module 620, the object recognition module 630, the matching module 640 and the first sending module 650 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation modes of software, hardware and firmware or in a suitable combination of any of them. Alternatively, at least one of the first acquisition module 610, the preprocessing module 620, the object recognition module 630, the matching module 640 and the first sending module 650 may be at least partially implemented as a computer program module, which may perform corresponding functions when executed.

[0124] Figure 7 A block diagram of an electronic device suitable for implementing a method for generating food recommendation results according to an embodiment of the present disclosure is schematically shown.

[0125] like Figure 7 As shown, the electronic device 700 according to an embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include an onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0126] In RAM 703, various programs and data required for the operation of electronic device 700 are stored. Processor 701, ROM 702 and RAM 703 are connected to each other via bus 704. Processor 701 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 702 and / or RAM 703. It should be noted that the program can also be stored in one or more memories other than ROM 702 and RAM 703. Processor 701 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0127] According to an embodiment of the present disclosure, the electronic device 700 may further include an input / output (I / O) interface 705, which is also connected to the bus 704. The electronic device 700 may further include one or more of the following components connected to the input / output (I / O) interface 705: an input portion 706 including a keyboard, a mouse, etc.; an output portion 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 708 including a hard disk, etc.; and a communication portion 709 including a network interface card such as a LAN card, a modem, etc. The communication portion 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the input / output (I / O) interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage portion 708 as needed.

[0128] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0129] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 702 and / or RAM 703 described above and / or one or more memories other than ROM 702 and RAM 703.

[0130] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the food recommendation result generation method provided by the embodiment of the present disclosure.

[0131] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 701. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0132] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 709, and / or installed from the removable medium 711. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0133] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the processor 701, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0134] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0135] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0136] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0137] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for generating food recommendation results, comprising: Acquire an object signal image and a food signal image, wherein the object signal image represents an object odor of a target object, and the food signal image represents a food odor; Preprocessing the object signal image according to the waveform characteristics of the object signal image to obtain a target object signal image; Performing object recognition according to the target object signal image to obtain a target object corresponding to the object signal image; Matching a historical food signal image with the food signal image to obtain a food recommendation result corresponding to the target object, wherein the historical food signal image is related to the target object; The food recommendation result is sent to a client associated with the target object.

2. The method according to claim 1, wherein: Preprocessing the object signal image according to the waveform feature of the object signal image to obtain the target object signal image includes: Determining a target feature from the waveform features of the object signal image according to a preset waveform feature threshold; According to the target feature, the object signal image is subjected to noise reduction processing to obtain the target object signal image.

3. The method according to claim 2, wherein: The target feature includes a first target feature and a second target feature, the first target feature is greater than the waveform feature threshold, and the second target feature is less than the waveform feature threshold, and the object signal image is subjected to noise reduction processing according to the target feature to obtain the target object signal image, comprising: Determining first voltage signal information corresponding to the first target feature; Determining second voltage signal information corresponding to the second target feature; According to the first voltage signal information and the second voltage signal information, the object signal image is subjected to noise reduction processing to obtain the target object signal image.

4. The method according to claim 1, wherein: The performing object recognition according to the target object signal image to obtain the target object corresponding to the object signal image comprises: Extracting features from the target object signal image to obtain an object feature image; Object recognition is performed according to the object feature image to obtain a target object corresponding to the object signal image.

5. The method according to claim 4, extracting features from the target object signal image to obtain the object feature image comprises: Performing global feature extraction on the target object signal image to obtain a first feature image; The first feature image is input into a local feature extraction sublayer, and a second feature image is output, wherein the object feature image includes the first feature image and the second feature image.

6. The method according to claim 1, wherein: The historical food signal image includes at least one historical food signal image block, the historical video signal image block corresponds to a historical food feature vector, the food signal image includes at least one food feature image block, the food feature image block corresponds to a food feature vector, and matching the historical food signal image with the food signal image to obtain a food recommendation result corresponding to the target object includes: According to the historical food feature vector and the food feature vector, similarity calculation is performed on the historical food signal image and the food signal image to obtain a similarity result corresponding to the food signal image; According to the similarity result, the food recommendation result matching the target object is obtained.

7. The method according to claim 1, wherein the food recommendation result comprises at least one of the food signal images and recommendation exchange value information corresponding to the food signal image, and the method further comprises: Acquiring historical exchange value information corresponding to the historical food signal image; Comparing the recommended exchange value information with the historical exchange value information to obtain an exchange value comparison result; A target food signal image is determined from at least one of the food signal images according to the exchange value comparison result.

8. The method according to claim 7, wherein: The object signal image is collected by an odor collection device, and the method further includes: Determining target location information corresponding to the odor collection device according to the device identification information of the odor collection device; The target location information is sent to the client, wherein the client is adapted to generate food delivery information according to the target location information, the food delivery information indicating that a target food corresponding to the target food signal image is delivered to the target location.

9. A device for generating food recommendation results, comprising: A first acquisition module, configured to acquire an object signal image and a food signal image, wherein the object signal image represents an object odor of a target object, and the food signal image represents a food odor; A preprocessing module, used for preprocessing the object signal image according to the waveform characteristics of the object signal image to obtain a target object signal image; An object recognition module, used to perform object recognition according to the target object signal image to obtain a target object corresponding to the object signal image; a matching module, used for matching a historical food signal image with the food signal image to obtain a food recommendation result corresponding to the target object, wherein the historical food signal image is related to the target object; The first sending module is used to send the food recommendation result to a client related to the target object.

10. An electronic device comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are enabled to execute the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the method according to any one of claims 1 to 8.

Images