WO2019083464A1

WO2019083464A1 - System and methods for collecting and analyzing customer behavioral data

Info

Publication number: WO2019083464A1
Application number: PCT/TH2018/000046
Authority: WO
Inventors: Chanikarn WONGVIRIYAWONG; Kejkaew THANASUAN; Yosawat JIRACHOKCHAIWONG
Original assignee: King Mongkut's University Of Technology Thonburi
Priority date: 2017-10-25
Filing date: 2018-10-25
Publication date: 2019-05-02

Abstract

A system and methods for collecting and analyzing of consumer behaviors comprises a structure for data acquisition including sensors in communication with a diner satisfaction quantification subsystem and automatic menu and services subsystem. The structure for data acquisition includes a dining surface and overhead fixture. The sensors include at least a camera, a touchscreen, and a means for measuring weight, spatial distribution of measured weight over an area of the dining surface, and a time distribution of the measured weight. The diner satisfaction quantification subsystem analyzes video of customers dining, the measured weight, the spatial distribution and the time distribution to determine diner satisfaction level.

Description

SYSTEM AND METHODS FOR COLLECTING AND ANALYZING

CUSTOMER BEHAVIORAL DATA

TECHNICAL FIELD

The present disclosure relates generally to mechanical engineering and automation, and more specifically to systems and methods to collect behavioral data and use the data for analytical processing to quantify consumer behaviors.

BACKGROUND

Current approaches to studying consumer behavior and assessing consumer satisfaction and/or diner satisfaction in the food industry typically use questionnaires and/or focus groups, whereby subjects give scores reflecting their satisfaction with various kinds of food and/or beverages. These methods have two main limitations: 1) customers' consciously stated opinions might not reflect their actual opinions; and 2) the environment in which the questionnaires and focus groups are conducted is not representative of the actual environment of restaurants or shops where food and/or beverages are consumed. Experimental results are likely to be a mismatch with real consumer behavior and satisfaction. For example, focus group subjects might not be actual consumers and may have different opinions from the target customer group.

Other existing systems aim to optimize consumer satisfaction with the customer service being provided, e.g. by minimizing wait times and/or facilitating communication. However, no system was found to provide a quantified prediction of a food consumer's expected appreciation of food quality and/or sensory appeal, or diner satisfaction.

US Pat. App. No. 2008/0127864 discloses a table for patrons' use in a restaurant to send orders for food and beverages directly to food preparation staff, without using waiters or waitresses, thereby reducing possible errors by waiters or waitresses. But the table disclosed does not provide a quantified prediction of a food consumer's expected appreciation of food quality and/or sensory appeal. US Pat. App. No.2008/0288326 discloses a system that predicts consumer satisfaction contingent on accepting one or more offers from potential sellers, based on the receipt of predictive assessments from one or more predictors. This system was designed to help consumers determine which good or service will best suit each consumer's needs and the best deal for that product. But the system disclosed does not provide a quantified prediction of a food consumer's expected appreciation of food quality and/or sensory appeal based on sensor data acquired in a realistic restaurant environment.

US Reissue Pat. No.42759 discloses a computer integrated communication system for restaurants that enables customer request information and other communications to be sent from a table unit to staff units. The system addresses the need to provide accurate real time information, enable the delivery of advertisements and improve customer satisfaction by reducing poor service, delays, and service inefficiencies. But the system disclosed does not provide a quantified prediction of a food consumer's expected appreciation of food quality and/or sensory appeal based on sensor data acquired in a realistic restaurant environment.

Australian Patent App. No. 2003/264201 discloses a computerized system for the management of personnel response time in a restaurant. But the system disclosed does not provide a quantified prediction of a food consumer's expected appreciation of food quality and/or sensory appeal based on sensor data acquired in a realistic restaurant environment.

The system disclosed herein aims to add value to food and beverage products by utilizing big data analytics and machine learning to develop a model forecasting expected consumer appreciation of food quality and/or sensory appeal based on sensor data acquired in a realistic or representative restaurant environment. A successful prototype has been used with food products developed by the food industry. And the accuracy of the machine learning models in the system is thus improved.

In order to enhance and maintain the competitive advantage of their food and beverage products, companies develop new products and/or marketing to increase perceived product value. However, current methods of quantifying the true response of consumers to such value propositions are typically more accurate and robust after the product has been launched, allowing actual consumer behavior to be measured. This creates significant product development risks since the intended value may not meet the expectations or demand of consumers. Accurate market research reduces the cost and risk of bringing new food and/or beverage products to one or more new markets. Thus, a need continues to exist for systems and methods of accurately quantifying expected consumer appreciation of food quality and/or sensory appeal based on sensor data acquired in a realistic or representative restaurant environment prior to the actual product launch. SUMMARY OF THE INVENTION

A system and methods for collecting and analyzing customer behavioral data in order to study consumer behaviors and responses to products are disclosed herein. The system and methods disclosed herein determine consumers' assessment of the perceived value and sensory appeal of products by calculating a diner satisfaction level based on sensor data acquired in a realistic or representative environment, similar to a cafe or restaurant. The system and methods disclosed herein use various kinds of raw data such as videos, weights, weight distributions, touchscreen data, and the like. The raw data is analyzed to determine secondary information such as gestures, body language, postures, physiological responses of the body, facial expressions, rates of consumption, affective states, body movements, customer activities, and the like. The automated system for collecting and analyzing customer behavioral data comprises three subsystems as follows:

1) A diner satisfaction quantification subsystem that comprises at least one processor and memory capable of executing software to quantify consumer behaviors during consumption. Input data for the diner satisfaction quantification system includes sensor data such as videos, weights, weight distribution data, and the like. The diner satisfaction quantification system uses the input data to determine diner satisfaction indicators, including locations of products on the dining table, the time and amount of each bite or sip a diner consumes of a product, the time at the start and conclusion of the consumption period, and the like.

2) The automatic menu and services subsystem comprises at least one processor and memory capable of executing software to automate ordering and communication with the kitchen and restaurant staff. The automatic menu and services subsystem allows a customer to choose a menu item, such as a food or beverage product. It includes a touchscreen or the like for menu item selection. In addition, in some embodiments, customers can call waiters and waitresses for help and other services through the automatic menu and services subsystem.

In some embodiments, the touchscreen displays a calculated diner satisfaction level determined by the diner satisfaction quantification subsystem for one or more menu items. The diner satisfaction level may include a numerical value indicating one or more of the following quantities: a) an individual customer's diner satisfaction with a food product relative to other food products; b) an individual customer's diner satisfaction with a food product relative to that of the total customer population; c) overall diner satisfaction with a food product relative to other food products; d) the customer population's diner satisfaction with a food product relative to other food products that a particular customer has consumed; e) a customer segment's diner satisfaction with a food product relative to other food products that a particular customer has consumed; f) a customer segment's diner satisfaction with a food product relative that of to the total customer population; and g) a customer segment's diner satisfaction with a food product relative to other food products. In other embodiments, the touchscreen may display an icon or word, such as "recommended" with menu item listings having a diner satisfaction level above a certain threshold.

3) The data collection subsystem uses sensors to collect data in a realistic or representative dining environment. In the prototype implementation, the sensors are embedded in a structure for data acquisition comprising a 4-legged table and overhead fixture. In other embodiments, the dining surface part of the structure may be a table with at least one leg, a bar, a coffee table or other dining surface. In some embodiments, at least one touchscreen is embedded in the dining surface such that the touchscreen and dining surface lie in approximately the same plane. In some preferred embodiments, the touchscreen comprises a light emitting diode (LED) television (TV) in the middle of the table. In some embodiments, computer appliances are located inside of the structure. In some embodiments, the computer appliances include sensors and a camera. In some embodiments, the overhead fixture includes a pillar combination designed to hang above the table and appear similar to a lantern, light fixture, chandelier or the like, in which the camera is embedded. In preferred embodiments, the sensors include sensors for measuring the weight and weight distribution of the food and an Internet Protocol (IP) camera for recording video while customers eat.

In some embodiments, one or more of the sensors may store data it collects and/or processes (e.g., in electronic memory). Additionally or alternatively, sensors may transmit collected data. Optionally, to transmit data to the diner satisfaction quantification subsystem, sensors may use various forms of wired communication and/or wireless communication, such as Wi-Fi signals, Bluetooth, cellphone signals, near-field communication (NFC) radio signals, or the like. In some embodiments, the data collected by the sensors is communicated to the diner satisfaction quantification system via a network, such as the Internet, an intranet, or the like.

The automated system and methods for collecting and analyzing customer behavioral data disclosed herein collects data using at least a camera, such as an IP camera, video camera, or the like; touchscreen, such as LED TV, or the like; and pressure sensor, such as a load cell, or the like. All data then gets sent to the diner satisfaction quantification subsystem, which may be implemented on a cloud server. Data may be sent via servers, internet, or other suitable communication means. Data is evaluated in real-time or near real-time by the diner satisfaction quantification subsystem to evaluate consumers' behaviors while dining.

The system and methods disclosed herein collect and analyze at least three types of raw data, including video, weight distributions (over a surface area, and over time) and weights of food, utensils, dishes, and the like. In some embodiments, the system also collects touchscreen data. The system predicts consumer behavior analyzing at least these types of measurement data together. In some embodiments, the video data undergoes automatic feature extraction before being used in the analytical model of the diner satisfaction quantification subsystem. In some embodiments, such automatic feature extraction identifies one or more of the position of hands, utensils (such as spoons, forks, knives, chopsticks, or the like), condiments, glasses, plates, and the like. The diner satisfaction quantification subsystem creates an analytical model for predicting consumer behaviors and diner satisfaction level by using a machine learning algorithm.

The diner satisfaction level indicates a diner's assessment and satisfaction with the quality and sensory appeal (e.g. taste, smell, appearance, mouthfeel or the like) of food after consumption in the form of a single number. In particular, the diner satisfaction level may include a numerical value indicating one or more of the following quantities: a) an individual customer's diner satisfaction with a food product relative to other food products, b) an individual customer's diner satisfaction with a food product relative to that of the total customer population, c) overall diner satisfaction with a food product relative to other food products; d) the customer population's diner satisfaction with this product relative to other food products that the particular customer has consumed; e) a customer segment's diner satisfaction with a food product; f) a customer segment's diner satisfaction with a food product relative to the total customer population; and g) a customer segment's diner satisfaction with a food product relative to other food products .

Temporal and spatial weight distribution data is used for analyzing consumption activities, which include the frequency and amount of food in each bite or sip; the time at the beginning and end of the consumption period; whether the diner shares food; whether and which condiments a consumer uses; whether a consumer adds other ingredients to the food products, e.g. ice; whether a consumer lifts the dish; whether a consumer uses a straw to mix or move product contents; how much a consumer leans on the table; or the like. Data indicating the weight of food is used to calculate the speed of eating, the amount of food consumed and left on the table by the diner, and total consumed calories.

In addition, system and methods for collecting and analyzing customer behavioral data disclosed herein use a cognitive model to predict future sales. In addition to sensor data, input data to the cognitive model includes food product recipes and flavor profiles. The system disclosed herein creates and updates a model that improves prediction of product sales in existing distribution channels such as wholesale, retail, or the like, by including insights obtained from the diner satisfaction quantification subsystem, as well as historical sales of products in existing distribution channels. Thus a model for predicting future sales of food products using machine learning and big data analysis based on sensor data acquired in a realistic or representative environment prior to actual product launch is provided.

Customers can use a touchscreen menu system to access the automatic menu and services subsystem disclosed herein. In some embodiments of this menu system, a customer can select a language, food, beverage and/or taste profile, such as level of spiciness or sweetness, the amount of monosodium glutamate or sugar, or the like. A customer can answer surveys or provide written feedback on food products or a level of satisfaction. The menu also supports multiple users at the same time and can display customized food suggestions.

BRIEF DESCRIPTION OF THE DRAWINGS

Figure 1 shows a schematic representation of connections between elements of the hardware system included in the structure for data acquisition according to some embodiments.

Figure 2 shows a structure for data acquisition according to some embodiments.

Figure 3 shows a top view of the structure for data acquisition shown in Figure 2.

Figure 4 shows a side view of the structure for data acquisition shown in Figure 2.

Figure 5 is a flow chart showing the function of a diner satisfaction quantification subsystem based on measurements of consumer behaviors according to some embodiments.

Figure 6 shows an automatic menu and services subsystem according to some embodiments. DISCLOSURE OF THE INVENTION

As used herein the term "food" is used to describe anything that may be consumed orally utilizing the digestive system of the human body. Thus, as used herein, food includes items that a user may eat (e.g., an apple, a curry and rice dish, a brownie, a steak, or a yogurt, etc.), items that a user can drink (e.g., juice, soda, whiskey, etc.), and/or other types of orally consumed substances (e.g., certain types of medicine, chewing gum, etc.). In addition, consuming a combination of food items, such as a certain meal, may also be considered an experience in which a user consumes food. Furthermore, a reference to "food", "food product", or "menu item" in this disclosure may also be considered a reference to food or a combination of foods. For example, a meal comprising a certain first course, a certain main course, and a certain beverage may be considered a food product or menu item, e.g., for which a quantified prediction of a food consumer's expected appreciation of food quality and/or sensory appeal may be computed.

As used to described the term "diner satisfaction" is used to describe a diner's engagement with a food and assessment of food quality and/or sensory appeal. The sensory appeal of a food product includes diner's assessment of the food's taste, smell, appearance, mouthfeel or the like. For example, a consumer, restaurant patron, diner, or other person may sample or consume one or more foods and appreciate the flavor but dislike the texture or appearance of the food. Diner satisfaction may be subconscious.

A system and methods for collecting and analyzing customer behavioral data are disclosed herein. According to the embodiment shown in Figure 1, an IP camera (1), having a field of view of approximately 112.6 degrees wide, is connected to a computer (4) through a Power over Ethernet (POE) line (2) and POE injector (3). The IP camera records a video while customers are eating. Then the data is sent to a cloud server to be evaluated by the diner satisfaction quantification subsystem disclosed herein.

The system and methods for collecting and analyzing customer behavioral data disclosed herein include communication channels between a consumer and the automatic menu and services subsystem; and consumer and the diner satisfaction quantification subsystem, whereby data from consumers is sent to the diner satisfaction quantification subsystem for analytics, and to the automatic menu and services subsystem for execution in the kitchen and/or by restaurant staff. In some embodiments, such as the prototype, the communication channel between the consumer and the automatic menu and services subsystem includes a touchscreen (5) coupled to a 32-inch LED TV (6) for evaluating the location where a consumer touches the touchscreen, and sending data to a local server through a High Definition Multimedia Interface (HDMI) connected to the computer (12) via an Uninterruptible Power Supply (UPS) (11) and Ethernet line. Optionally, to transmit data to the diner satisfaction quantification subsystem, sensors may use various forms of wired communication and/or wireless communication, such as Wi-Fi signals, Bluetooth, cellphone signals, near-field communication (NFC) radio signals, or the like. In some embodiments, the data collected by the sensors is communicated to the diner satisfaction quantification subsystem via a network, such as the Internet, an intranet, or the like.

In some embodiments, load cells (7) are attached under opposite sides of dining surface of the structure for data acquisition. In some embodiments, data such as temporal and spatial distributions of weight is transmitted through a wired cable, and is then magnified by an amplifier (9), and sent to a microcontroller (10). The processed data from the microcontroller (10) is then forwarded to a local computer, or server, so that the data can later be sent to a cloud server associated with the diner satisfaction quantification subsystem and used to quantify customer behaviors.

Figure 2 shows a structure for data acquisition according to some embodiments. The structure for data acquisition comprises a dining surface and overhead fixture. In some embodiments, as shown in Figure 2, the structure includes a table (14) suitable for seating two diners. In some embodiments, the table (14) has a touchscreen (6) with a surface area of approximately 44.10 x 74.80 cm² centered in the top surface of the table (14). In some embodiments, the touchscreen (6) may be a 32-inch LED TV (6). In the embodiment shown in Figure 2, the space (15) under the table surface has a height of approximately 17 cm and may be used for holding the UPS (11) and/or computer. In some embodiments, as shown in Figure 2, the overhead fixture in the structure for data acquisition includes a side table and pillar combination having an overhead portion designed to appear similar to a lantern, light fixture, chandelier or the like, for housing a control box and IP camera (1) above the table (14) or dining surface.

Figure 3 shows a top view of the structure for data acquisition shown in Figure 2. In some embodiments, as shown in Figure 3, the dining surface of the structure (14) is approximately 100 cm wide and 100 cm long. In some embodiments, as shown in Figure 3, load cells having a surface area of approximately 25 x 25 cm² are placed on opposite sides of the touchscreen (6) substantially coincident with diner place settings. Chairs and the side table and pillar combination of the overhead fixture (16) for the IP camera are provided beside the table, in some embodiments. Figure 4 shows a side view of the structure for data acquisition shown in Figure 2. In some embodiments, the height of the overhead fixture housing the camera (1) is a height that allows the camera (1) to record all of the dining surface. For example, in some embodiments, as shown in Figure 4, the height of the overhead fixture for camera (1) is between approximately 1.5 and 2 meters.

Figure 5 is a flow chart showing selected functions of the diner satisfaction quantification subsystem comprising at least one processor and memory capable of executing software commands according to some embodiments. In some embodiments, instructions for implementing the diner satisfaction quantification subsystem may be stored on a computer-readable medium, which may optionally be a non-transitory computer-readable medium. In response to execution by a system or subsystem including a processor and memory, the instructions cause the performance of operations that are part of the diner satisfaction quantification subsystem. The diner satisfaction quantification subsystem automatically extracts features from the collected data, including video data, spatial and temporal distributions of weight, weight, multi-touch touchscreen data, and the like (18). The extracted features include spatial and temporal changes in the location of hands, utensils, plates, condiments, and the like. Extracted features are then entered into a machine learning algorithm for predicting diner satisfaction based on diner behavioral data (19). The result of the machine learning algorithm (20) is the diner satisfaction level for the food product of interest. Multi-touch data from the touchscreen are used for quantifying consumer behavior during decision making and associated diner engagement, by determining the frequency and speed with which the consumer chooses, for example, certain menu items and/or associated menu options. For example, a return diner may quickly choose a subset of the same food as chosen during a previous visit (exhibiting a higher frequency and speed of choosing a menu item) but more slowly make a different choice regarding sweetness level and/or optional ingredients. Weight and its spatial and temporal distribution are used to estimate the speed of consumption, amount of food consumed at a given time, total nutrients consumed, total calories consumed, and the like. Additionally, the diner satisfaction quantification subsystem utilizes mathematical models that mimic cognition and buyer decision making in order to forecast how well a particular food product will sell through various distribution channels in the future. Such models require inputs such as food product flavor profiles, recipes, historical revenue (if any), marketing plans, and the like. Thus a model for predicting future sales of food products using machine learning and big data algorithms based on sensor data acquired in a realistic or representative environment is provided.

Figure 6 shows an automatic menu and services subsystem according to some embodiments. As shown in Figure 6, in some embodiments, customers use a touchscreen menu to access the automatic menu and services subsystem disclosed herein. Using this touchscreen menu, a customer can select a language, food, beverage and/or taste profile, such as level of spiciness or sweetness, the amount of monosodium glutamate or sugar, or the like. Customers can give their opinion about food or assess their satisfaction with a food product. In addition, a customer can call waiters and waitresses for help or to request the bill through this system. The automatic menu and services system can show order status and/or cancel an order while food is cooking. In some embodiments, more than one user is supported at the same time, for example by displaying results to customers on the both sides of the touchscreen. The system and methods disclosed herein may be used in restaurants and throughout the food industry to measure customer satisfaction instead of using conventional questionnaires and interviews. At the same time, the system and methods disclosed also help to collect sales data and predict food sales. In addition, in some embodiments this system methods may be used to customize the look and taste of food for specific people. While the methods disclosed herein may be described and shown with reference to particular steps performed in a particular order, it is understood that these steps may be combined, sub-divided, and/or reordered to form an equivalent method without departing from the teachings of the embodiments. Accordingly, unless specifically indicated herein, the order and grouping of the steps is not a limitation of the embodiments. Furthermore, methods and mechanisms of the embodiments will sometimes be described in singular form for clarity. However, some embodiments may include multiple iterations of a method or multiple instantiations of a mechanism unless noted otherwise. For example, when a computer or processor is disclosed in one embodiment, the scope of the embodiment is intended to also cover the use of multiple computers or processors. Certain features of the embodiments, which may have been, for clarity, described in the context of separate embodiments, may also be provided in various combinations in a single embodiment. Conversely, various features of the embodiments, which may have been, for brevity, described in the context of a single embodiment, may also be provided separately or in any suitable sub-combination.

Some embodiments described herein may be practiced with various computer system configurations, such as cloud computing, a client-server model, grid computing, peer-to-peer, hand-held devices, multiprocessor systems, microprocessor-based systems, programmable consumer electronics, minicomputers, and/or mainframe computers. Additionally or alternatively, some of the embodiments may be practiced in a distributed computing environment where tasks are performed by remote processing devices that are linked through a communication network. In a distributed computing environment, program components may be located in both local and remote computing and/or storage devices. Additionally or alternatively, some of the embodiments may be practiced in the form of a service, such as infrastructure as a service (IaaS), platform as a service (PaaS), software as a service (SaaS), and/or network as a service (NaaS).

Embodiments described in conjunction with specific examples are presented by way of example, and not limitation. Moreover, it is evident that many alternatives, modifications, and variations will be apparent to those skilled in the art. It is to be understood that other embodiments may be utilized and structural changes may be made without departing from the scope of the appended claims and their equivalents.

Claims

1. A system for collecting and analyzing customer behavioral data comprising:

a structure for data acquisition including a dining surface and overhead fixture having sensors in communication with a diner satisfaction quantification subsystem, wherein the sensors include at least a camera, a touchscreen, and a means for measuring weight, a spatial distribution of measured weight over an area of the dining surface, and a time distribution of the measured weight; and

an automatic menu and services subsystem in communication with the sensors and the diner satisfaction quantification subsystem.

2. The system for collecting and analyzing customer behavioral data of claim 1 wherein the dining surface comprises a table having at least one leg.

3. The system for collecting and analyzing customer behavioral data of claim 1 wherein the touchscreen comprises an LED television.

4. The system for collecting and analyzing customer behavioral data of claim 1 wherein the means for measuring weight, spatial distribution of measured weight over an area of the dining surface, and time distribution of the measured weight comprises at least one load cell.

5. The system for collecting and analyzing customer behavioral data of claim 1 wherein the camera is in the overhead fixture and the touchscreen and means for measuring weight, spatial distribution of measured weight over an area of the dining surface, and time distribution of the measured weight are embedded in the dining surface.

6. The system for collecting and analyzing customer behavioral data of claim 1 wherein the automatic menu and services subsystem is accessed via the touchscreen, thereby allowing customers to choose menu items from a menu displayed on the touchscreen and to request one or more services.

7. The system for collecting and analyzing customer behavioral data of claim 6 wherein the touchscreen displays a diner satisfaction level associated with at least one menu item, wherein the diner satisfaction level is determined by the diner satisfaction quantification subsystem.

8. The system for collecting and analyzing customer behavioral data of claim 1 wherein the camera is a video camera for recording a video of customers dining.

9. The system for collecting and analyzing customer behavioral data of claim 8 wherein the diner satisfaction quantification subsystem analyzes the video of customers dining, the measured weight, the spatial distribution and the time distribution to determine a diner satisfaction level.

10. A method for collecting and analyzing customer behavioral data comprising:

recording a video of customers dining;

displaying an automatic menu and services subsystem on a touchscreen;

collecting customer interactions with the touchscreen as touchscreen data;

measuring weight via at least one sensor,

collecting spatial distributions of measured weight over an area of a dining surface and a time distribution of the measured weight from the at least one sensor;

transmitting, for analysis, the video, weight, spatial distributions, time distribution, and touchscreen data to a diner satisfaction quantification subsystem comprising a processor and a memory; and

determining a diner satisfaction level based on the video, weight, spatial distributions, time distribution, and touchscreen data.

11. A system for collecting and analyzing customer behavioral data comprising:

a dining surface having sensors, wherein the sensors include a touchscreen and means for measuring weight, spatial distribution of measured weight over an area of the dining surface, and a time distribution of the measured weight; and

an overhead fixture including a camera;

wherein the camera and sensors provide input data to a diner satisfaction quantification subsystem for determining a diner satisfaction level associated with at least one menu item wherein the diner satisfaction quantification subsystem comprises a processor and a memory.

12. The system for collecting and analyzing customer behavioral data of claim 11 wherein the dining surface comprises a table having at least one leg and the touchscreen comprises an LED television.

13. The system for collecting and analyzing customer behavioral data of claim 11 wherein the means for measuring weight, spatial distribution of measured weight, and the time distribution of the measured weight comprises at least one load cell.

14. The system for collecting and analyzing customer behavioral data of claim 11 wherein the camera is a video camera for recording a video of customers dining.

15. The system for collecting and analyzing customer behavioral data of claim 11 wherein the diner satisfaction level associated with the menu item comprises a number indicating a diner's assessment of quality and sensory appeal of the menu item.

16. The system for collecting and analyzing customer behavioral data of claim 11 wherein the diner satisfaction level associated with the menu item comprises a number indicating a diner's assessment of quality and sensory appeal of the menu item relative to other food products.

17. The system for collecting and analyzing customer behavioral data of claim 11 wherein the diner satisfaction level associated with the menu item comprises a number indicating a diner's assessment of quality and sensory appeal of the menu item relative to other diners' assessments of the menu item.

18. The system for collecting and analyzing customer behavioral data of claim 11 wherein the diner satisfaction level associated with the menu item comprises a number indicating overall diner satisfaction with the menu item relative to other food products.

19. The system for collecting and analyzing customer behavioral data of claim 11 further comprising an automatic menu and services subsystem accessed via the touchscreen, thereby allowing customers to choose menu items from a menu displayed on the touchscreen and to request one or more services.

20. The system for collecting and analyzing customer behavioral data of claim 19 wherein the touchscreen displays the diner satisfaction level associated with at least one menu item.