KR20190106609A - Method for providing no-show management service using probability statistics based activity prediction model - Google Patents

Abstract

Provided is a method for providing a no-show management service using probability statistics-based no-show probability prediction, which comprises the steps of: collecting a reservation history log including data on a reservation request event and a reservation fulfillment data received from at least one client terminal; classifying whether the reservation is performed into reservation execution, no-show and reservation cancellation; calculating probability statistics on whether the client has fulfilled the reservation based on the ratio of reservation execution, no-show and reservation cancellation to the reservation request event; calculating the probability of no-show based on the calculated probability statistics by using a preset reservation prediction model algorithm, and storing the probability so that the probability is mapped with the at least one client terminal; and transmitting the probability of no-show of the at least one client terminal to an affiliated store terminal of an affiliated store when the at least one client terminal makes a reservation request for the affiliated store. Accordingly, the present invention can reduce possibility in which an affiliated store′s business is interrupted due to no-show on the reservation date.

Description

Provision of reservation default management service using probability statistics based on probability statistics of reservation default and reservation execution {METHOD FOR PROVIDING NO-SHOW MANAGEMENT SERVICE USING PROBABILITY STATISTICS BASED ACTIVITY PREDICTION MODEL}

The present invention relates to a method for providing a reservation management service using a probability statistics based reservation probability based on probability of reservation failure and reservation execution, and provides a method for notifying a merchant at the time of requesting a reservation by the reservation statistics and probability prediction.

A reservation is a preliminary promise and a means of making a preliminary step in promising what contract to make in the future. In particular, the service industry is a commercialization industry for intangible human services, inventory storage is impossible, it is extinct, and non-separation of production and consumption requires a strategy of storing services as a kind of inventory. The no-show that accompanies this refers to the act of making a reservation but not appearing at the reservation place without canceling the call, causing loss of sales and employment of the service provider, and the highest rate of restaurant default among restaurants. The reservation system is rarely operated.

At this time, the method of managing the reservation default consists of a method of determining whether or not to cancel through the location and distance. In this regard, the prior art Korean Patent Registration No. 10-1769760 (August 21, 2017 announcement), when the reservation request is received from the reservation is completed, the reservation place and reservation time is confirmed, the reservation person arrives at the reservation time Otherwise, the reservation location information and the estimated time of arrival are received from the navigation application of the subscriber's mobile device, and the reservation is canceled if the estimated time of arrival is after the waiting time from the reservation time, thereby preventing no show of the reservation. In this way, the restaurant operator maximizes the operating profit, and from the standpoint of the reservation is convenient configuration and reservation is possible to cancel.

However, even if the above-described configuration is used, there is no basis for the merchant owner to reject or approve the reservation itself, which leads to waste of manpower and resources by canceling the reservation once, and whether or not to execute the reservation. Is a restaurant that affects the next day's sales, even though the reservation must be canceled immediately, it is not canceled due to lack of attitude and awareness of the consumer, resulting in a decrease in sales of the restaurant, resulting in economic and social losses. There is a need for a system that can identify consumer tendencies and filter reservations.

In one embodiment of the present invention, the reservation manager of the customer statistics statistics, and predicts the possibility of booking using the behavior pattern and big data to instantly notify the merchant when the customer applies for a reservation manager by the merchant manager, If the reservation is likely to occur, risk management or handling can be performed separately.In the event of an unexpected event or event after the reservation is made, the reservation may increase or decrease. It is possible to provide a reservation department management service providing method using probability reservation based probability probability based reservation probability of reservation reservation and reservation execution, which can reduce work. However, the technical problem to be achieved by the present embodiment is not limited to the technical problem as described above, and other technical problems may exist.

As a technical means for achieving the above-described technical problem, an embodiment of the present invention, the step of collecting a reservation history log including a reservation request event received from the at least one customer terminal and whether the reservation is performed, whether the reservation is performed or not Classifying the reservation into reservation execution, no-show, and reservation cancellation, and calculating probability statistics of the customer's reservation execution based on the ratio of reservation execution, reservation failure and reservation cancellation for the reservation request event. Comprising a step of calculating the probability of the reservation book based on the calculated probability statistics using a predetermined reservation prediction model algorithm to store the mapping to at least one customer terminal, and at least one customer terminal to make a reservation request for the merchant If the case, the reservation of the at least one customer terminal also includes the step of delivering to the merchant terminal of the merchant; The.

According to any one of the problem solving means of the present invention described above, the reservation department of the customer also statistics the history, and predicts the possibility of the booking department using behavior patterns and big data to immediately notify the merchant when the customer applies for a reservation, the merchant The manager can manage risks or reservations that are likely to be subject to a reservation failure, and in the event of an unexpected event or event after the reservation is made, the possibility of reservation failure may be increased to finally reserve the franchise's business on the day of reservation. The abnormality caused by the default can be reduced.

1 is a view for explaining a system for providing a reservation management service using a reservation statistics based probability probability based on probability reservation and reservation execution according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a reservation diagram management service providing server included in the system of FIG. 1.
3 is a diagram illustrating an embodiment of a reservation management service using a reservation statistics based probability probability based on probability reservation and reservation execution according to an embodiment of the present invention.
4 is a diagram illustrating a process in which data is transmitted and received between components included in a reservation chart management service providing system using probability reservation based probability reservation based on probability reservation and reservation execution of FIG. 1 according to an embodiment of the present invention. Drawing.
FIG. 5 is a flowchart illustrating a method of providing a reservation management service using a reservation statistics based probability probability based on probability reservation and reservation execution according to an embodiment of the present invention.

DETAILED DESCRIPTION Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art may easily implement the present invention. As those skilled in the art would realize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and like reference numerals designate like parts throughout the specification.

Throughout the specification, when a part is "connected" to another part, this includes not only "directly connected" but also "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, which means that it may further include other components, except to exclude other components, unless specifically stated otherwise, one or more other features It is to be understood that the present disclosure does not exclude the possibility of the presence or the addition of numbers, steps, operations, components, parts, or combinations thereof.

As used throughout the specification, the terms "about", "substantially", and the like, are used at, or in close proximity to, numerical values when manufacturing and material tolerances inherent in the meanings indicated are intended to aid the understanding of the invention. Accurate or absolute figures are used to assist in the prevention of unfair use by unscrupulous infringers. As used throughout the specification of the present invention, the term "step of" or "step of" does not mean "step for".

In the present specification, the term 'unit' includes a unit realized by hardware, a unit realized by software, and a unit realized by both. In addition, one unit may be realized using two or more pieces of hardware, or two or more units may be realized by one piece of hardware.

Some of the operations or functions described as being performed by the terminal, the apparatus, or the device may be performed instead in the server connected to the terminal, the apparatus, or the device. Similarly, some of the operations or functions described as being performed by the server may be performed by the terminal, apparatus or device connected to the server.

In the present specification, some of the operations or functions described as mapping or matching with a terminal mean that a unique number of a terminal or identification information of an individual, which is identification data of the terminal, is mapped or matched. Can be interpreted as

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

1 is a view for explaining a system for providing a reservation management service using a reservation statistics based probability probability based on probability reservation and reservation execution according to an embodiment of the present invention. Referring to FIG. 1, a reservation chart management service providing system 1 using a probability statistics based reservation chart probability prediction of a reservation chart and a reservation execution includes at least one customer terminal 100 and a reservation chart management service providing server 300. It may include at least one affiliated store terminal 400. However, since the reserved book management service providing system 1 using the reserved book diagram and the probability statistics based reservation book likelihood prediction of the reservation execution of FIG. 1 is only one embodiment of the present invention, the present invention is limited through FIG. 1. It is not to be interpreted.

In this case, each component of FIG. 1 is generally connected through a network 200. For example, as shown in FIG. 1, at least one customer terminal 100 may be connected to the reservation management service providing server 300 through the network 200. In addition, the reservation management service providing server 300 may be connected to at least one customer terminal 100 and at least one affiliated store terminal 400 through the network 200. In addition, the at least one affiliated store terminal 400 may be connected to the reservation service management server 300 through the network 200.

Here, the network refers to a connection structure capable of exchanging information between respective nodes such as a plurality of terminals and servers. Examples of such a network include RF, 3rd Generation Partnership Project (3GPP) network, and long term (LTE). Evolution network, 5th Generation Partnership Project (5GPP) network, World Interoperability for Microwave Access (WIMAX) network, Internet, Local Area Network (LAN), Wireless Local Area Network (WLAN), Wide Area Network (WAN) , PAN (Personal Area Network), Bluetooth (Bluetooth) network, NFC network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network and the like, but is not limited thereto.

In the following description, the term “at least one” is defined as a singular and plural term, and each component may exist in the singular or plural, even though the term “at least one” does not exist, and may mean the singular or plural. It will be self explanatory. In addition, the singular or plural elements may be changed according to embodiments.

The at least one client terminal 100 may proceed with a reservation using a webpage, an app page, a program, or an application related to a reservation management service using a reservation statistics probability prediction based on probability probability of reservation reservation and reservation execution, or call origination ( It may be a terminal of a customer who makes a reservation through a telephone). And, if at least one client terminal 100, if the same reservation within the predetermined period of time in the same affiliated store, the reservation unit management service providing server 300 to answer whether to cancel the existing reservation while the reservation is in progress It may be a terminal for transmitting.

Here, the at least one customer terminal 100 may be implemented as a computer that can access a server or terminal in a remote place through a network. Here, the computer may include, for example, a navigation, a laptop equipped with a web browser, a desktop, a laptop, and the like. In this case, the at least one customer terminal 100 may be implemented as a terminal that can be connected to a server or terminal in a remote place through a network. The at least one customer terminal 100 is, for example, a wireless communication device that ensures portability and mobility, and includes, for example, navigation, a personal communication system (PCS), a global system for mobile communications (GSM), a personal digital cellular (PDC), Personal Handyphone System (PHS), Personal Digital Assistant (PDA), International Mobile Telecommunication (IMT) -2000, Code Division Multiple Access (CDMA) -2000, W-Code Division Multiple Access (W-CDMA), Wireless Broadband Internet A handheld-based wireless communication device such as a terminal, a smartphone, a smart pad, a tablet PC, etc. may be included.

The reservation management service providing server 300 may be a server providing a reservation management service web page, an app page, a program, or an application using the probability statistics based reservation probability probability prediction of the reservation revocation and the reservation execution. In addition, the reservation management service providing server 300 calculates a reservation request of the at least one client terminal 100 and a result of the cancellation, reservation cancellation or reservation completion, which are the resultant values, to each customer. It may be a server that stores statistics by mapping and storing. In addition, the reservation management service providing server 300 may be a server for constructing big data in a manner of classifying behavior patterns according to a reservation request of at least one customer terminal 100 and a result value thereof. In addition, the reservation management service providing server 300 determines whether the reservation is received by transmitting a result of calculating the probability of cancellation of the customer terminal 100 to the affiliated store terminal 400 when a new reservation request arrives. To provide evidence. In addition, the reservation management service providing server 300 may be a server that performs a cancellation process, asking the customer terminal 100 to cancel the duplicate reservation when there is a duplicate reservation in the near future. In addition, the reservation management service providing server 300 may be a server that informs the affiliated store terminal 400 that a multi-reservation exists when a customer tries to make a reservation to several affiliated stores.

Here, the reservation unit management service providing server 300 may be implemented as a computer that can be connected to a server or a terminal in a remote place through a network. Here, the computer may include, for example, a navigation, a laptop equipped with a web browser, a desktop, a laptop, and the like.

The at least one affiliated store terminal 400 may be a terminal of an affiliated store using a webpage, an app page, a program, or an application related to a reserved book management service using probabilities statistics-based reserved book probability prediction of book bookings and reservation execution. In this case, the at least one affiliated store terminal 400 may be a terminal that receives information on the possibility of canceling the reservation of the customer from the reservation management service providing server 300, and transmits as a feedback whether to receive a reservation reception based on this. It may be a terminal. In addition, the at least one affiliated store terminal 400 may receive information on the multi-reservation of the customer from the reservation unit management service providing server 300.

Here, the at least one affiliated store terminal 400 may be implemented as a computer that can access a server or terminal in a remote place through a network. Here, the computer may include, for example, a notebook equipped with a point of sale (POS), a web browser (WEB Browser), a desktop, a laptop, and the like. In this case, the at least one affiliated store terminal 400 may be implemented as a terminal that can access a server or terminal in a remote place through a network. The at least one affiliated terminal 400 is, for example, a wireless communication device that ensures portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), Personal Handyphone System (PHS), Personal Digital Assistant (PDA), International Mobile Telecommunication (IMT) -2000, Code Division Multiple Access (CDMA) -2000, W-Code Division Multiple Access (W-CDMA), Wireless Broadband Internet A handheld-based wireless communication device such as a terminal, a smartphone, a smart pad, a tablet PC, etc. may be included.

FIG. 2 is a block diagram illustrating a reservation chart management service providing server included in the system of FIG. 1, and FIG. 3 illustrates probability prediction based probability reservation of a reservation chart and a reservation execution according to an embodiment of the present invention. FIG. 4 is a diagram illustrating an embodiment in which a reservation management system used is implemented.

Referring to FIG. 2, the reservation management service providing server 300 may include a collection unit 310, a classification unit 320, a calculation unit 330, a storage unit 340, a delivery unit 350, and an approval confirmation unit. 360, a duplicate notification unit 370 may be included.

Reservation unit diagram management service providing server 300 according to an embodiment of the present invention or another server (not shown) operating in conjunction with at least one customer terminal 100, and at least one affiliated terminal 400 reservation unit diagram And at least one customer terminal 100 and at least one merchant terminal 400 when transmitting a reservation management service application, a program, an app page, a web page, etc. using probability statistics based reservation probability probability prediction of reservation execution. The reservation unit may also install or open a reservation unit management service application, a program, an app page, a web page, etc., using the probability statistics based reservation unit probability prediction of the reservation unit and the reservation execution. In addition, the service program may be driven in at least one customer terminal 100 and at least one affiliated store terminal 400 using a script executed in a web browser. Here, the web browser is a program that enables the use of the World Wide Web (WWW) service, and refers to a program that receives and displays hypertext described in HTML (hyper text mark-up language), for example, Netscape. , Explorer, chrome and the like. In addition, an application means an application on a terminal, and includes, for example, an app running on a mobile terminal (smartphone).

Referring to FIG. 2, the collection unit 310 may collect a reservation history log including a reservation request event and reservation execution data received from at least one customer terminal 100. In this case, the reservation history log may be collected from a customer or a merchant.

At this time, the collection unit 310 may build big data using the collected log and the user's behavior pattern, the process is as follows. First, the data may be classified into structured data, semi-structured data, and unstructured data according to a user's behavior pattern and degree of formalization. The formal data is data having a standard with a defined type and format. The formal data is data of a type that is input in a fixed format (value, date, etc.) or selected as an item. The second is metadata of various data. Next, semi-structured data is a data class that allows you to define what is contained in the text, depending on the nature of the data, although most fields are not fixed in text form. Unstructured data are items that are irregular in shape and difficult to define, and generally include text and images. Such unstructured data can also be learned and sorted and patterned with keywords, tags, or meta data, and then, when a new classification of unstructured data is required, the data can be processed into a record format and provided with associated data.

The collected data is classified through a preprocessing process. Then, when a new input value is input, the classified identifier is extracted when the reference data having a predetermined similarity is extracted from the established big data based on the already classified identifier. Based on this, a query for automatically searching for reference data having a preset similarity may be derived, and the reference data having a preset similarity may be searched and extracted using the derived query. On the other hand, the data after preprocessing can be analyzed including data mining. At this time, the data mining classifies the data based on similarity without class information or class information that predicts a new class of data by learning a training data set in which a class is known by searching for an intrinsic relationship between preprocessed data. Clustering can be performed. Of course, in addition to this, there may be various mining methods, and may be mined differently according to the type of big data collected and stored or the type of query to be requested later. The big data constructed in this way may be subjected to a verification process by artificial neural network deep learning or machine learning.

In this case, the artificial neural network may use a CNN (Convolutional neural network) structure, CNN is a network structure using a convolutional layer is suitable for image processing, to classify the image based on the features in the image by inputting the image data Because it can. In addition, text mining is a technique aimed at extracting and processing useful information based on natural language processing techniques from non / half-form text data. Text mining techniques can extract meaningful information from large chunks of text, identify linkages with other information, find categories of text, or do more than just search for information. In addition, cluster analysis can be used to finally find groups of similar characteristics while joining sieves with similar characteristics.

The classification unit 320 may classify whether or not a reservation is performed into a reservation execution, a reservation view (No-show), and a reservation cancellation.

The calculation unit 330 may calculate probability statistics on whether or not to reserve a customer based on a ratio of reservation execution, reservation failure, and cancellation of a reservation request event. This may be performed by each affiliated store, by business type, or the like, or may collectively calculate whether a customer fulfills all reservations. In this case, the prediction of the reservation default may include an analysis based on the number of reservations or the expected sales, in addition to the parameters such as the weather and the history of the previous reservation default / day cancellation / visit. When a customer makes a reservation for a company's dinner or on behalf of a group (i.e., when making reservations for more than 10 people), the booking department is also more likely, while a small number of individuals make a reservation. If the reservation probability is significantly lower, data analysis will show that if the new reservation for this customer is made up of a small number of people, then the lower reservation probability will also be displayed. In case of over 10,000 won, the default rate is low (may be a high-end restaurant or a large number of people), and reservations with menus of 300,000 won or less may reflect this tendency when the reservation default rate is high.

The storage unit 340 may calculate and store the probability of the reservation unit based on the calculated probability statistics using a preset reservation prediction model algorithm to be mapped to the at least one customer terminal 100. The preset prediction model algorithm may be a statistical model algorithm including any one or a combination of decision trees, neural networks, logistic regression, multiple regression, and binary variance analysis. However, it is obvious that any statistical model that is not limited to the above algorithm and predicts the future by log data may be used.

In this case, the predetermined reservation prediction model algorithm uses a context-awareness parameter, and the context-awareness parameter includes a user context, illuminance, humidity, and temperature including a profile and a location of the customer. A physical context, and a time context including time, day, week, and month.

For example, assume that customer A tends to make a reservation failure on a rainy day without canceling the reservation. In such a case, A's reservation may be increased by identifying the possibility of precipitation, humidity, etc. at the date, time and region where A made a reservation. Or customer B tends to fall into personal training the next day if he's drinking the next day. In such a case, the booking unit may increase the possibility of the day after the B customer's drink.

The influence factors on the possibility of reservations will be summarized below.

First, there may be variables related to the theory of planned behavior (subject to behavior of reservation default, subjective norms about reservation default, perceived behavior control over reservation default). Planned behavior consists of the concept of an individual's attitude, subjective norms, and perceived behavioral control. Attitudes refer to the degree of general feeling that a favorable or unfavorable assessment of a behavior or object is. It is a conceptualization of a kind of social pressure perceived by an actor in response to important surrounding characters. Perceived behavioral control also refers to one's own perception of how easily an individual can perform an action.

The validity of this theory of planning behavior has been verified in various fields, and is mentioned as an important influence factor in explaining consumer behavior, especially in the social sciences. The theory of planning behavior is attracting attention because it enables a more accurate understanding of the relative importance of the factors affecting consumer behavior and the process of determining their behavioral intention, and is useful for predicting consumer behavior in various fields.

Second, reservations have also been triggered. In other words, the relationship between the experience of the reservation book and the possibility of the book book also shows that the customer who made the book book is related to the book book since the book book has a history of behavior. In particular, the experience of making reservation reservations is the most influential factor for reservation failure, and consumers who have experienced reservation failure are considered to have a high possibility of reservation failure.

Third is the recognition of the negative effect of reservation default. Consumers' perceptions of the negative effects of certain risks will increase their motivation to participate in the decision-making process and heighten social interest. However, risks are based on personal observations, experiences, and perceptions, so the perception of negative effects on a particular event can affect the perception of the consumer, and the consequences of the behavior may vary depending on how the perception is perceived by the consumer. In particular, risk severity is related to how severe the consequences of the occurrence of the risk are and is closely related to consumer fears or fears. The more perceived a negative effect that a particular risk is closely related to you, and that it is likely to pose a serious danger to you, the more likely you are to be afraid, and consumers are likely to take certain actions that the message recommends to eliminate the fear. This is high. In summary, perception of negative effects such as severity awareness can be assumed to be a variable affecting behavioral intention and likelihood of behavior.

As a result, the lack of recognition of reservation failure in the service industry causes reservation failure, and there is a lack of general understanding and recognition of reservations even though damage caused by reservation failure to other consumers or operators. It can be seen as a failure to act immediately and to book a reservation. As a result, it is very likely that the acceptance of consumers' perception of reservation fraud, which is anti-social and unplanned behavior, will be a big problem and cause reservation failure. Recognition of the negative effect of reservation default as a major factor affecting the possibility of reservation default is included as a variable.

Finally, the socio-demographic variable, which is based on the study of the relationship between socio-demographic variable and reservation default, males had a higher proportion of reservation defaults than women, and the lower the age group, the higher the probability of reservation default, Uses a relatively low ratio. However, in addition to the above-described variable, the variable may be added, deleted or edited according to the characteristics of the industry, and is not limited to the above-described variable.

In order to verify the reliability of each variable, internal consistency can be reviewed, and the level of social demographic characteristics, variables related to planning behavior theory, experience of reservation failure, recognition of negative effects of reservation failure, and possibility of reservation failure For this purpose, statistics, averages, and standard deviations can be statistically processed. In addition, multiple regression analysis can be performed to determine the influence of variables on reservation default, and binary variance analysis can be performed to focus on the moderating effects of recognition of negative effects of reservation default on the possibility of reservation default. have. However, as described above, the method for considering the possibility of the reservation unit may be any method that can verify the variable and increase the predictability in addition to the above-described method.

In addition to the qualitative methods described above, quantitative methods can also be used. Quantitative methods can be largely divided into time series models and causal models. Among them, exponential smoothing models and ARIMA models can be used. Among them, exponential smoothing model is a simple method to be applied when networking resources or computing resources are insufficient or insufficient for prediction. In this case, the exponential smoothing model may use a simple exponential smoothing model, a Holt exponential smoothing model, and a Winters exponential smoothing model. However, even if an accurate model is used, the method of estimating accuracy can be used in that the predicted value estimated by the quantitative prediction method acts as an important variable for later decision making.

There are six main criteria for assessing accuracy: sum of squared error (SSE), mean square error (MSE), root mean square error (RSE), root means quared percentage error (RMPE), mean absolute percentage error (MAPE), Theil-U coefficient), any one or a combination of these criteria can be used.

When the at least one customer terminal 100 makes a reservation request for the affiliated store, the transfer unit 350 may transmit the possibility of the reservation unit of the at least one customer terminal 100 to the affiliated store terminal 400 of the affiliated store. At this time, when at least one client terminal 100 makes a reservation request for an affiliated store, when the reservation unit of at least one client terminal 100 transmits a possibility to the affiliated store terminal 400 of the affiliated store, the at least one client terminal ( When the call is sent to the affiliated store terminal 400 in 100, the execution execution, the reserved portion of the reservation and the cancellation rate, and the likelihood of the reserved portion may be transmitted to the affiliated store terminal 400.

For example, while the connection tone signal is output before the call connection is made from the at least one customer terminal 100 to the affiliated store terminal 400, the affiliated store terminal 400 may output behavior prediction information. At this time, if the possibility of cancellation is high, the manager of the affiliated store may decide whether to answer the call before the call, and thus may not spend time on a job that is not likely to succeed.

When at least one client terminal 100 makes a reservation request for an affiliated store, the delivery unit 350 transmits a possibility of the reservation unit of the at least one client terminal 100 to the affiliated store terminal 400 of the affiliated store. The reservation request for reservation of the affiliated store terminal 400 from one customer terminal 100, the reservation execution, the reservation failure and the reservation cancellation rate, and the behavior prediction information regarding the possibility of the reservation failure are output on the screen of the merchant terminal 400. Can transmit

For example, when the affiliated store terminal 400 is a terminal having a display, a ringing tone sounds and the display of the affiliated store terminal 400 displays "X customer, reservation completion rate 30%, cancellation rate 40%, reservation default rate 30%, High likelihood of cancellation).

When the delivery unit 350 makes a reservation request for the affiliated store in the at least one client terminal 100, when the reservation unit of the at least one client terminal 100 transmits a possibility to the affiliated store terminal 400 of the affiliate store, at least one If the reservation request for the affiliated store has already existed in the future at the information inquiry result of the customer terminal 100, the at least one client terminal 100 may inform that the reservation request for the affiliated store already exists.

For example, if customer A makes a reservation at member B's shop at 7:00 pm on April 30, 2018, but requests a reservation on April 28, 2018 at 7:00 pm, most of the time, the reservation is changed. Of course, this does not preclude the rebooking of two appointments within two days. Accordingly, the delivery unit 350 asks the A customer whether the reservation is canceled on April 30, 2018 and replaced with the reservation on April 28, 2018, or the reservation exists on April 30, 2018. It can guide you that there is.

The approval confirmation unit 360, when the delivery unit 350 makes a reservation request for the affiliated store in the at least one client terminal 100, the reservation unit of the at least one client terminal 100 may determine a possibility that the reservation unit of the affiliate store ( After delivery to 400, the affiliated store terminal 400 may check whether approval of the reservation request of the at least one client terminal 100 is made. In addition, when the approval for the reservation request is received, the approval confirmation unit 360 may complete the reservation completion process for the at least one customer terminal 100.

When the duplicate notification unit 370 makes a reservation request for the affiliated store at the at least one client terminal 100 in the delivery unit 350, the reservation unit of the at least one client terminal 100 may also determine the possibility of the affiliated store terminal of the affiliate store ( 400 and, when a plurality of reservation request events for a plurality of affiliated terminal 400 from the one customer terminal 100 occurs on the same date, time and type, information about the plurality of reservation attempts to the merchant terminal 400 can be passed.

However, it may include a similar time range, such as "time including the same time" rather than "same time". For example, if you make a reservation at A merchant at 19:00 on January 1 and make a reservation at B at 19:30 on January 1, you can exclude the fact that you don't think of a duplicate reservation because it is not the same time. If you make a reservation at 19:00 for multiple merchants, the reservation is clearly overlapping, but even if you make a reservation at a different time, it is actually a duplicate reservation for you to eat within 30 to 1 hour and go to another merchant. In +/- 30 minutes to 1 hour 30 minutes may be considered as a duplicate reservation. Of course, you can have someone else's reservation for you, so you'll need to make sure that the same person is right before you process a duplicate booking, but even if you're not clearly on the same time, It is considered a duplicate.

For example, suppose that customer A made a reservation for eight at restaurant B at 7:00 pm on April 15, 2018. At this time, if the customer A tries to make a reservation at the same date and time as the restaurant C, the duplicate notification unit 370 may transmit information of "A customer, restaurant B restaurant already reserved" to the affiliated store terminal 400.

On the other hand, the reservation management service providing server 300, the customer of the at least one customer terminal 100 to build big data from the reservation history log of the at least one customer terminal 100, and generates a reservation request event, The probability of belonging to the classification of user behavior patterns included in the constructed big data is calculated to infer the highest probability behavior pattern, and the preset reservation prediction model algorithm can predict the probability of reservation by using the behavior pattern. have.

At this time, the user's behavior data for inferring the reservation failure can be collected, inferred and stored, and the behavior pattern database is built using the behavior data that can be collected according to the user's situation. First, context data such as location, weather, temperature data, information on a visited restaurant, visit history, and post-visit evaluation may be collected from the customer terminal 100. In addition, after the normalized process of the collected data, it can be inferred according to the user purpose by matching the behavior pattern with the user behavior model that is classified and organized using the naive Bayes calculation formula.

At this time, in order to analyze the user behavior data, the restaurant visit history data is subjected to a pre-processing to be suitable for analysis. Pre-processing data of restaurant visit data may be region, category, date, temperature and weather data, and the four seasons are classified by date and temperature, and the weather is sunny, rainy and snowy according to snowfall, cloudiness and precipitation. The weekday data can be divided into weekdays and holidays.

At this time, the location information can be collected from the customer terminal, but the weather and temperature data can be obtained from not only the customer terminal but also from other information providers (eg, weather service, weather, etc.) that provide weather information.

A classification system is needed to analyze and infer behavior patterns. The data collected and preprocessed may be composed of pattern data with the addition of restaurant visit classification. When data is newly added and stored, the user's restaurant visit pattern may be inferred by calculating the probability that the newly collected data may belong to the classification by the Naive Bayes classification technique. Date, temperature, and precipitation can be stored as mobile context data, and restaurants and scores can be stored as user-recorded information. As the naive Bayes classification criteria, the highest probability classification is added to the behavior pattern data according to the classification data criteria. If the pattern data is not included in the existing behavior classification process in the calculation process, it is newly stored in the behavior pattern DB. The new behavior pattern data is used as the inferred pattern as it is stored, so the more data, the higher the reliability of the result.

In summary, quantitative statistics are provided by analyzing the past history of the customer, while predicting the possibility of the customer's cancellation according to the behavioral pattern and the situational awareness attitude, constructing the big data, conducting continuous learning, and occurring after the reservation By adjusting the number of cancellation possibility based on the customer's unexpected event, the merchant can finally determine which customer is most likely to cancel on the day and decide whether to be overbooked, thereby increasing the sales rate of service goods. have.

Hereinafter, an operation process according to the configuration of the reservation management service providing server of FIG. 2 described above will be described in detail with reference to FIG. 3. However, the embodiment is only any one of various embodiments of the present invention, but is not limited thereto.

Referring to FIG. 3, (a) the reservation management service providing server 300 performs statistical modeling together with big data construction and behavior pattern classification, such as collecting a history requested by a customer and classifying patterns. In addition, (b) the reservation management service providing server 300 analyzes each customer, and (c) when performing the reservation request, the merchant terminal 400 quantitatively quantifying the existing situation together with the behavior prediction result. To send.

In this case, (d) the affiliated store terminal 400 receives the approval or not and transmits the reservation unit to the management service providing server 300 so that the customer terminal 100 can check it. In this case, the type of data to be transmitted may be voice, text, and the like, and the type of communication to be connected may be data communication or packet communication. And, (e) when a reservation request is made in the client terminal 100, the reservation management service providing server 300, so as to know in advance that there is a duplicate reservation, so that duplicate reservation does not occur, (f) Even if the customer terminal 100 attempts to make a multi-reservation, the affiliated store manager 400 can be recognized by transmitting to the merchant terminal 400.

Based on the probability statistics based on the reservation default and the reservation execution of FIG. 2 and FIG. 3, the description of the method for providing the reservation management service using the prediction of the probability of the reservation default is based on the probability statistics of the reservation default and the reservation execution through FIG. 1. Since the reservation unit may also be easily inferred from the same or described contents with respect to the method for providing a reservation management service using the reservation unit likelihood prediction, the following description will be omitted.

4 is a diagram illustrating a process in which data is transmitted and received between components included in a reservation chart management service providing system using probability reservation based probability reservation based on probability reservation and reservation execution of FIG. 1 according to an embodiment of the present invention. Drawing. Hereinafter, an example of a process in which data is transmitted and received between each component will be described with reference to FIG. 4, but the present disclosure is not limited to the above-described embodiments, and is illustrated in FIG. 4 according to the various embodiments described above. It is apparent to those skilled in the art that the process of transmitting and receiving data may be changed.

Referring to FIG. 4, the reservation management service providing server 300 receives a reservation history from at least one customer terminal 100 (S4100), and after performing data collection and preprocessing (S4200), determines a behavior pattern. In operation S4300, statistical processing is performed on the history log (S4400).

On the other hand, the reservation management service providing server 300, when an event such as a call origination or Internet reservation from the customer terminal 100 occurs (S4500), if there is a duplicate reservation to the merchant terminal 400, and informs it (S4600), by extracting the customer's pattern and statistics (S4700), with the possibility of cancellation (S4800), by sending to the merchant terminal 400 (S4810), the merchant terminal 400 to determine whether to approve (S4820). ).

The reservation management service providing server 300 transmits the information on the reservation rejection or completion to the customer terminal 100 according to the approval received from the merchant terminal 400 (S4840, S4850), and whether the same reservation exists. To identify (S4900), the customer terminal 100 to inquire or notify whether or not to cancel (S4910), when receiving a response (S4920), to notify the merchant terminal 400 (S4930).

The order between the above-described steps S4100 to S4930 is merely an example, and the present invention is not limited thereto. That is, the order between the above-described steps (S4100 to S4930) may be changed mutually, and some of the steps may be executed or deleted at the same time.

Based on the probability statistics based reservation probability and reservation performance of FIG. 4 as described above, the description of the method of providing a reservation failure management service using the probability prediction of the reservation failure is based on the probability statistics of the reservation failure and the reservation execution through FIGS. 1 to 3. Since the reservation unit may also be easily inferred from the same or described contents with respect to the method for providing a reservation management service using the reservation unit likelihood prediction, the following description will be omitted.

FIG. 5 is a flowchart illustrating a method of providing a reservation management service using a reservation statistics based probability probability based on probability reservation and reservation execution according to an embodiment of the present invention. Referring to FIG. 5, the reservation management service providing server collects a reservation history log including a reservation request event and reservation execution data received from at least one customer terminal (S5100).

In addition, the reservation management service providing server classifies whether the reservation is performed by reservation execution, reservation failure (No-show), and reservation cancellation (S5200), and the ratio of reservation execution, reservation failure and reservation cancellation for the reservation request event. Based on the probability statistics for the customer's reservation or not is calculated (S5300).

In addition, the reservation management service providing server calculates a probability of the reservation degree using a preset prediction model algorithm based on the calculated probability statistics, and stores the mapping to be mapped to at least one customer terminal (S5400). When the terminal makes a reservation request for the affiliated store, the reservation unit of the at least one client terminal also transmits a possibility to the affiliated store terminal of the affiliated store (S5500).

Based on the probability statistics based reservation probability and reservation execution of FIG. 5, the description of the method of providing a reservation failure management service using the reservation probability probability prediction is based on the probability statistics of the reservation failure and the reservation execution through FIGS. 1 to 4. Since the reservation unit may also be easily inferred from the same or described contents with respect to the method for providing a reservation management service using the reservation unit likelihood prediction, the following description will be omitted.

According to an embodiment described with reference to FIG. 5, a method of providing a reservation chart management service using a probability statistics-based reservation chart probability prediction of a reservation chart and a reservation execution is executable by a computer such as an application or a program module executed by a computer. It may also be implemented in the form of a recording medium containing instructions. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, computer readable media may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

According to the above-described embodiment of the present invention, the method of providing a reservation chart management service using the probability book based probability prediction based on the probability of reservation and the reservation execution includes an application basically installed on the terminal (this is a platform or an operating system basically installed on the terminal). May be included in an application (ie, a program) directly installed on the master terminal by an application providing server such as an application store server, an application, or a web server associated with the corresponding service. May be executed by In this sense, the method of providing a reservation management service using reservation probability based on probability statistics based reservation probability according to the above-described embodiment of the present invention described above is basically an application installed on a terminal or directly installed by a user (that is, Program) and recorded on a computer-readable recording medium such as a terminal.

The foregoing description of the present invention is intended for illustration, and it will be understood by those skilled in the art that the present invention may be easily modified in other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is shown by the following claims rather than the above description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included in the scope of the present invention. do.

Claims (10)

In the reservation book management service providing server running in the reservation book management service providing server,
Collecting a reservation history log including a reservation request event received from at least one client terminal and reservation execution data;
Classifying whether the reservation is performed as a reservation execution, a reservation failure (No-show), and a reservation cancellation;
Calculating probability statistics on whether or not the reservation is performed by the customer based on a ratio of reservation execution, reservation failure, and cancellation of the reservation request event;
Calculating the probability of the reservation unit based on the calculated probability statistics by using a preset reservation prediction model algorithm and storing the reservation possibility map with the at least one customer terminal; And
If the at least one client terminal makes a reservation request for an affiliated store, transmitting a possibility of the reservation unit of the at least one client terminal to the affiliated store terminal of the affiliated store;
Book reservation management service providing method using a probability statistics based reservation probability likelihood prediction of reservation default and reservation execution comprising a.
The method of claim 1,
If the at least one client terminal makes a reservation request for an affiliated store, transferring the possibility of the reservation unit of the at least one client terminal to the affiliated store terminal of the affiliated store,
When the at least one client terminal makes a call to the affiliated store terminal, transmitting the reservation execution, reservation failure and cancellation rate, and behavior prediction information on the possibility of the reservation failure to the affiliated store terminal;
Including,
While the connection sound signal is output before the call connection is made from the at least one client terminal to the affiliated terminal, the affiliated terminal outputs the behavior prediction information. Reservation service management service providing method using a.
The method of claim 1,
If the at least one client terminal makes a reservation request for an affiliated store, transferring the possibility of the reservation unit of the at least one client terminal to the affiliated store terminal of the affiliated store,
Transmitting, at the at least one customer terminal, a reservation request for reserving the affiliated store terminal, the reservation execution, a reservation failure rate and a reservation cancellation rate, and behavior prediction information on the possibility of the reservation failure degree output on a screen of the affiliated store terminal; ;
How to provide, using the reservation statistics probability reservation based reservation probability probability reservation reservation management service providing method.
The method of claim 3, wherein
If the at least one client terminal makes a reservation request for an affiliated store, after transferring the possibility of the reservation unit of the at least one client terminal to the affiliated store terminal of the affiliated store,
Confirming whether the affiliated store terminal approves the reservation request of the at least one client terminal;
When the approval for the reservation request is received, completing the reservation completion process for the at least one client terminal;
How to further comprising, reservation statistics based on probability statistics based on reservation probability and reservation reservation reservation management service providing method.
The method of claim 1,
If the at least one client terminal makes a reservation request for an affiliated store, after transferring the possibility of the reservation unit of the at least one client terminal to the affiliated store terminal of the affiliated store,
When a plurality of reservation request events for a plurality of merchant terminals from one customer terminal occur at the same date, time, and type, transferring information on a plurality of reservation attempts to the affiliated store terminal;
How to further comprising, reservation statistics based on probability statistics based on reservation probability and reservation reservation reservation management service providing method.
The method of claim 1,
The preset reservation prediction model algorithm is a statistical model algorithm including any one or a combination of decision trees, neural networks, logistic regression, multiple regression analysis, and binary variance analysis. A method of providing reservation management service using probability statistics based reservation probability probability prediction.
The method of claim 1,
The preset reservation prediction model algorithm uses a context-awareness parameter, and the context-awareness parameter includes a user context, illuminance, humidity, and temperature including the profile and location of the customer. Reserve chart using probabilistic statistics based reservation probability diagram of reservation banking and reservation fulfillment, which includes a physical context to include and a time context that includes time, day, week, and month. How to Provide Managed Services.
The method of claim 1,
Reservation department management service providing server,
Building big data from the reservation history log of the at least one client terminal;
The customer of the at least one customer terminal generating the reservation request event calculates the probability of belonging to the classification of the user behavior pattern included in the constructed big data, and infers the highest probability behavior pattern.
The predetermined reservation prediction model algorithm is to predict the reservation likelihood using the behavior pattern, reservation unit based on probability statistics based on reservation probability and reservation reservation reservation management service providing method using probability prediction.
The method of claim 1,
If the at least one client terminal makes a reservation request for an affiliated store, transferring the possibility of the reservation unit of the at least one client terminal to the affiliated store terminal of the affiliated store,
Informing that the reservation request for the affiliate store already exists in the at least one client terminal when the reservation request for the affiliate store already exists in the future as a result of the information inquiry of the at least one client terminal;
How to provide, using the reservation statistics probability reservation based reservation probability probability reservation reservation management service providing method.
An application stored on a medium for carrying out the method of claim 1.

Images