WO2021103631A1 - Queuing method and device, and system, client, and server - Google Patents

Abstract

A queuing method and device, and a system, a client, and a server, capable of providing an accurate, valuable and highly targeted queuing service for a bank customer. By prompting waiting time and handling time to the customer, the customer can reasonably plan time, number ticket resources are saved, and bank service efficiency and quality are improved. The queuing method comprises: a queuing machine obtains customer information, and identifies and extracts customer effective queuing data (S100); the queuing machine performs data cleaning according to the customer effective queuing data, and groups and ranks the customer effective queuing data (S102); the queuing machine performs data processing according to the grouped and ranked data, and calculates time required for ending each service handling (S104); and the queuing machine prompts handling time consumption and a predicted waiting duration before number taking according to the time required for ending the service handling, and notifies the customer after number taking (S106).

Description

Queuing method, system, client, device and server thereof Technical field

The invention relates to a queuing machine, a queuing processing system and a method thereof, in particular to a queuing method, a system, a client, a device and a server thereof.

Background technique

New technologies have injected new momentum into the development of the financial industry. In order to improve customer satisfaction, various intelligent solutions and service scenarios are in the ascendant. IT technology and artificial intelligence can save the distribution density of banking outlets, reduce the loss of non-core resources such as manpower, and liberate a large amount of repetitive work by banking practitioners. When the customer just starts to pick up the number for business, the system can automatically prompt the customer to arrange the number and how many customers are waiting before this number. However, customers cannot know in real time how long they need to wait and how long each business needs to be processed when they transact business at the branch. Usually, the bank roughly estimates these times based on the personal experience of the lobby manager. Many customers feel dissatisfied and not annoying while waiting, and even abandon the account after waiting for a period of time, causing subsequent customers to pass the account for no reason and have to renew the account. Obtaining a number reduces the service efficiency of bank outlets and also causes a waste of resources. Customers can only passively receive notifications from the bank, and cannot actively obtain the real-time status of the business they want to know, which leads to the emergence of a large number of abandoned and abandoned accounts, and the bank database fails to remove the abandoned and abandoned information in real time, which is serious It restricts the improvement of bank efficiency, does not reflect the convenience and accuracy of data and information interaction brought by the new generation of information technology and big data, and affects the overall service level of the banking industry.

Summary of the invention

In view of the above technical problems, the present invention discloses a queuing method, system, client, device and server thereof. The purpose of the present invention is to enable the bank to update the ranking information in real time through data processing, integrated face recognition and voice recognition technology, and the customer can actively set the time, frequency and content of receiving bank notifications through the client, so as to avoid excessive occurrences. Abandon the account number, and then achieve the effect of improving the efficiency and quality of bank services.

In order to achieve the above objectives, the present invention adopts the following technical solutions:

In the first aspect, an embodiment of the present application provides a queuing method, including:

The queuing machine obtains customer information, and identifies and extracts effective customer queuing data;

The queuing machine performs data cleaning according to the effective queuing data of the customer, and groups and sorts the effective queuing data of the customer;

The queuing machine performs data processing according to the grouped and sorted data, and calculates the time required for the completion of each business;

According to the time required for the completion of the business processing, the queuing machine prompts the processing time and estimated waiting time before picking up the number, and informs the customer after picking up the number.

Preferably, the queuing machine obtains customer information, and identifies and extracts effective queuing data of customers, and further includes:

The queuing machine asks customers whether they need to transact business and use the queuing machine's screen display, and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or third-party platforms, and/or print notices, and make the inquiry;

The queuing machine identifies the customer who was judged as yes in the previous step;

For customers who have successfully identified their identity information, the queuing machine obtains the specific types of services that the customer needs to handle through screen display and/or voice inquiry; for customers who fail to identify their identity information, the queuing machine provides customers with common causes of errors through screen display and/or voice analysis;

The queuing machine informs the customers who have failed to identify the identity information through the screen display of the queuing machine, and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or third-party platforms, and/or printing a notice Bank staff assisted and sent waiting notices to customers. The waiting notification includes basic customer information and estimated waiting time. The assistance of notifying bank staff includes assisting in displaying on the queuing machine screen, and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or third-party platforms, and/or printing notices, and assisting in obtaining numbers.

Preferably, the queuing machine obtains customer information through face recognition, and the face recognition method includes:

Step S131: The queuing machine processor receives the data of the queuing machine camera and determines whether there is a human face. If so, it retrieves the video of the customer's voice interaction with the queuing machine captured by the camera to identify whether the customer has vital signs; if it is, proceed to step S132, If not, end face recognition, determine that no one is waiting for customer identification information, and stop voice inquiry; the voice interaction video between the customer and the queuing machine includes the lip-synching video obtained by the queuing machine camera;

Step S132: The queuing machine processor instructs the speaker to voice guide the customer to pose, perform real-time face collection, and generate the first face collection data;

Step S133: The queuing machine requires the customer to perform face collection again in real time according to the interval and number of times set by the queuing machine;

Step S134: The queuing machine processor calculation unit compares and scores the facial information of the face information acquired for the first time according to the interval time and number of times set by the queuing machine: if it is determined to be the same after multiple comparisons and the scores For customers, face recognition is adopted; if multiple comparisons and scores determine that they are different customers, it is determined that the face recognition has failed, and step S135 is performed;

Step S135: The queuing machine classifies customers whose face recognition has failed. If one of the pictures and/or videos can identify the customer, but the recognition fails because the interval and number of times set by the queuing machine are not reached, proceed Step S136: If there is no picture and/or video that can identify the customer, the face recognition is ended, and the customer is notified by voice;

Step S136: End face recognition, and notify the customer through voice, and extract the queuing data of the valid customer after the recognition is completed, compare the customer’s habit of handling banking business at the same time period, select the customer’s previous business, and call the same The time required for the completion of business processing is displayed on the screen of the queuing machine, and the content of the ticket is printed to inform the customer of the processing time and estimated waiting time.

Preferably, the method of comparing and scoring includes:

Compare and score the data obtained by multiple real-time face collection with the first face collection data, and if the score is equal to the set threshold, the comparison is successful, and face recognition is passed;

If the score is less than the set threshold, then enter the step S135;

If the score is greater than the set threshold, proceed to step S135;

Preferably, the data cleaning method includes:

Delete the unreasonable time-consuming customer queuing data;

According to the setting, filter the data with too short processing time;

Group the cleaned data according to the type of business, according to age and gender, to obtain further sample data;

Arrange the obtained two sets of data in ascending order.

6. Preferably, the data processing method includes:

Calculate the interquartile range of the same level of data for different business types, choose to retain the data from the first quartile to the third quartile, and perform the summation;

Calculate the mean value from the first quartile to the third quartile. If the amount of data in each group is less than four, and the data cannot be divided into quarters, then the mean value is directly calculated without seeking the quartile.

Combine the mean value of each group of interquartile range, and perform the mean operation on the first quartile to the third quartile of each data group under the same business category to obtain the mean value of the business category, which is the average transaction of the business Duration and the average processing time for each level.

7. Preferably, the queuing machine, according to the time required for the completion of the business processing, prompts the processing time and estimated waiting time before picking up the number, and after notifying the customer after picking up the number, it also includes:

Cache and/or save dictionaries with business as keywords;

Print the estimated time required for business processing and estimated waiting time on the number ticket and send a message to notify the customer;

When the customer is waiting for the business process, when the number of people waiting for the same type of business reaches the set value, the customer is notified of the number of people waiting for the same type of business to assist the customer in referring to the arrival time; the business includes banking.

Preferably, the prompt before taking the number includes display on the queuing machine screen, and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or a third-party platform, and/or printing a notice, prompting; The notification after the number is obtained includes display on the screen of the queuing machine, and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or a third-party platform, and/or printing a notice and notification.

In the second aspect, an embodiment of the present application provides a voice interaction method for a queuing machine, which includes the following steps:

When the camera of the queuing machine recognizes a customer, it proactively greets the customer, and recommends relevant services that can be handled according to past handling habits;

The queuing machine microphone collects voice information, and obtains the business information that the customer wants to handle through offline and/or online voice recognition. At the same time, the queuing machine camera captures the customer's lip-motion video and provides it to the face recognition unit for vital signs identification; if If you have vital signs, proceed to the next step; if you don’t have vital signs, you will be notified through the queuing machine and/or client device that the client cannot be processed;

The queuing machine judges whether the bank can accept the business at present, if not, inform the customer through the queuing machine and/or client device that it cannot handle the business; if so, proceed to the next step;

The voice notification of the queuing machine can be processed and/or sent to the client device, and at the same time the bank server will broadcast the information returned by the bank branch server to the customer;

The queuing machine extracts effective customer queuing data, performs data cleaning, data processing, and calculates the time required for the completion of each business;

The queuing machine informs the customer of the time required for the completion of each business through the queuing machine screen display and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or the third-party platform, and according to the client's settings , Real-time update of the time required for the completion of each business transaction for customers to inquire through the customer client.

In the third aspect, an embodiment of the present application provides a queuing machine system, including:

The processor is used to obtain customer information, identify and extract effective customer queuing data; data cleaning and data processing; realize the interaction of information and data between the client and the server, so that the customer can query and set the information of the queuing machine;

The processor includes: an acquisition module, a calculation module, and a setting module;

The acquisition module is used to acquire customer information, and to identify and extract effective customer queuing data. The customer information includes identity information and services to be handled;

The calculation module is used to perform data cleaning according to the effective queuing data of the customer, and to group and sort the effective queuing data of the customer; and also to perform data processing according to the grouped and sorted data, and calculate each The time required for the completion of the business;

The setting module is used to enable the customer to set the service content and method of the queuing machine through the customer client; the service content and method include: the scene that requires voice interaction, the volume of the voice, the speed of the voice, and the sending to the customer The time and/or number of notifications, the notification includes the time required for the completion of the business processing, the number of people waiting for the same type of business; it is also used to set the interval and the number of times for the queuing machine to recognize facial information; set multiple people The scoring weight and/or scoring method of face information recognition and comparison;

Transceiver module: According to the time required for the completion of the business processing, the processing time and the expected waiting time are sent out before the number is obtained and/or the notification is issued after the number is obtained; it is also used in the display device, the client, and/ Or information and data interaction between queuing machines; said prompting before picking up a number, including display on the screen of the queuing machine, and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or a third-party platform , And/or print a notice to send out a reminder; said sending out a notice after picking up the number, including displaying on the screen of the queuing machine, and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or a third-party platform, And/or print a notice to issue a notice;

The display module is used to display the content of the data and information interaction between the queuing machine and the customer in real time.

Preferably, the queuing machine system further includes:

The storage module is used to store calculation data and information; it is also used to store a memory dictionary stored with business as a key;

The security authentication module is used to verify the real identity of the customer or the operator of the queuing machine server;

The security authentication module includes a face recognition unit, a voice recognition unit, and an account management unit;

The face recognition unit is used to verify customer information through face recognition and extract the customer's business processing information; and is also used to identify the customer's lip-synching video;

The voice recognition unit is used to recognize the information expressed by the customer through voice and/or mouth shape information;

The account management unit is used to identify the real identity of the customer or the bank worker who needs to operate the queuing machine server by means of account and password login.

In a fourth aspect, an embodiment of the present application provides a client, and the client includes:

The setting module is used to set the service content and mode of the queuing machine; the service content and mode include: the scene that requires voice interaction, the volume of the voice, the speed of the voice, the time and/or frequency of sending notifications to customers , And/or type, the notification includes the time required for the completion of the service, the number of people waiting for the same type of service, and the information and/or type broadcasted by the speaker of the queuing machine;

The transceiver module is used for the interaction of information and data between the display device and/or the queuing machine; the interaction of the information and data includes: receiving prompts for processing time and estimated waiting time before picking up the number; receiving the end of business processing Time required; receiving the real-time update sent by the queuing machine the time required for the completion of each business;

The query module is used to query the time required for the completion of each service for the update sent by the queuing machine in real time; it is also used to query the time required for the completion of the service for the real-time update of the queuing machine.

In a fifth aspect, an embodiment of the present application provides a queuing device, including the queuing machine system described above, and the queuing machine system can implement the method described in the embodiment of the present application.

In a sixth aspect, an embodiment of the present application provides a server, including a processor and a machine-readable storage medium. The machine-readable storage medium stores machine-executable instructions that can be executed by the processor. When executed, the processor-executable instructions cause the processor to implement the method described in the embodiment of the present application.

As can be seen from the above, in the solution provided by the embodiments of the present application, compared with the prior art, the present invention has the following beneficial effects: a queuing method provided by the present invention can handle different businesses according to the customer, and the customer’s historical business handling situation , Perform comprehensive statistical analysis on the handling of other customers of the same business, through the process of data cleaning, data processing, and the introduction of the analysis method of the quartile method, to solve the problem of real-time data and information interaction between the customer and the queuing machine. The queuing machine using this queuing method, system, client, device and its server can prompt the customer to wait for the estimated time for processing the business, update the estimated time in real time, and the time required for processing the business; it can also be based on the client's settings, Provide customers with queuing information analysis that meets their own requirements and characteristics. The technical solution applied by the present invention has the technical characteristics of a large number of big data technologies, high speed, variety, high authenticity, and fast real-time update, and can provide bank customers with accurate and valuable queuing services that are more targeted; reducing the waiting time of bank customers; It is helpful for bank customers to arrange their itineraries early. At the same time, the bank’s office efficiency is improved by reducing the number of customers abandoning the number due to the waiting time beyond the tolerable range after taking the number, reducing the work intensity of the bank’s lobby manager; avoiding unnecessary waste of bank number ticket resources; helping to improve the bank Service level; improve customer satisfaction.

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

Description of the drawings

Fig. 1 is a flowchart of a queuing method according to an embodiment of the present invention;

2 is a flowchart of a data cleaning method according to an embodiment of the present invention;

Fig. 3 is a flowchart of a data processing method according to an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of a client according to an embodiment of the present invention;

Figure 5 is a schematic diagram of a queuing machine system according to an embodiment of the present invention;

Fig. 6 is an operation diagram of a queuing machine system according to an embodiment of the present invention.

Detailed ways

In order to be able to understand the above objectives, features and advantages of the present invention more clearly, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments can be combined with each other. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of the present invention. The terminology used in the specification of the present invention herein is only for the purpose of describing specific embodiments, and is not intended to limit the present invention.

Please refer to FIG. 1. FIG. 1 is a flowchart of a queuing method according to an embodiment of the present invention. The method includes:

Step S100: The queuing machine obtains customer information, and identifies and extracts effective queuing data of the customer;

Specifically, the customer’s valid queuing data includes normal processing time and completion time; the customer information includes identity information and services to be processed; the queuing machine obtains customer information through face recognition. ; The step S100 also includes:

Step S211: The queuing machine asks whether the customer needs to transact business and makes the inquiry through the display screen and/or voice;

Step S212: The queuing machine recognizes the identity information of the customer judged to be yes in step 211; specifically, compares all customer information in the system through the customer's face recognition, the comparison is successful, and the associated ID card, IC card, and customer level are inquired ; The customer that the queuing machine determines as yes to step 211 may be a VIP customer.

Step S213: The queuing machine obtains the specific types of services that the customer needs to handle through the screen display and/or voice inquiry for the customer who has successfully identified the identity information; the queuing machine provides the customer with the screen display and/or voice to the customer who fails to identify the identity information Analysis of common causes of errors;

Step S214: The queuing machine displays on the screen of the queuing machine, and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or a third-party platform, and/or prints notifications to the customer whose identity information has failed to be identified by the queuing machine Notice to the bank staff to assist and send a waiting notice to the customer; the waiting notice includes basic customer information and estimated waiting time; the informing bank staff to assist includes assisting in the display on the queuing machine screen, and/or voice broadcast, and /Or mobile communications, and/or the Internet, and/or third-party platforms, and/or print notices to assist in obtaining numbers.

The queuing machine obtains customer information through face recognition, and the face recognition method includes:

Step S131: The queuing machine processor receives the data of the queuing machine camera and determines whether there is a human face. If so, it retrieves the video of the customer's voice interaction with the queuing machine captured by the camera to identify whether the customer has vital signs; if it is, proceed to step S132, If not, end face recognition, determine that no one is waiting for customer identification information, and stop voice inquiry; the voice interaction video between the customer and the queuing machine includes the video of the customer's lip-motion captured by the queuing machine camera; the identification of whether the customer is Having vital signs is achieved by recognizing the appearance of facial features in unfixed positions, such as oral features in a video of a customer’s mouth movement. Specifically, the video of the voice interaction between the customer and the queuing machine is a video that the queuing machine camera acquires the customer's lip-motion video and provides the video to the face recognition unit;

Step S132: The queuing machine processor instructs the speaker to voice guide the customer to pose, perform real-time face collection, and generate the first face collection data;

Step S133: The queuing machine requires the customer to perform face collection again in real time according to the interval and number of times set by the queuing machine;

Step S134: The queuing machine processor calculation unit compares and scores the facial information of the face information acquired for the first time according to the interval time and number of times set by the queuing machine: if it is determined to be the same after multiple comparisons and the scores For customers, face recognition is adopted; if multiple comparisons and scores determine that they are different customers, it is determined that the face recognition has failed, and step S135 is performed;

Step S135: The queuing machine classifies customers whose face recognition has failed. If one of the pictures and/or videos can identify the customer, but the recognition fails because the interval and number of times set by the queuing machine are not reached, proceed Step S136: If there is no picture and/or video that can identify the customer, the face recognition is ended, and the customer is notified by voice;

Step S136: End face recognition, and notify the customer through voice, and extract the queuing data of the valid customer after the recognition is completed, compare the customer’s habit of handling banking business at the same time period, select the customer’s previous business, and call the same The time required for the completion of business processing is displayed on the screen of the queuing machine, and the content of the ticket is printed to inform the customer of the processing time and estimated waiting time.

Wherein, the method of comparing and scoring in step S134 includes:

Compare and score the data obtained by multiple real-time face collection with the first face collection data, and if the score is equal to the set threshold, the comparison is successful, and face recognition is passed;

If the score is less than the set threshold, go to step S135;

If the score is greater than the set threshold, step S135 is entered.

The setting threshold is set by the setting module, and the specific setting basis is: according to testing different people, collecting and recording whether the result of each face recognition is correct, and recording the corresponding scoring score and the number of recordings. Classify and count all face recognition records. Divide all scoring scores and recording times into one category, correctly identified scoring scores and recording times into one category, incorrectly identified scoring scores and recording times into one category; then put the three types of values in the same category. In the coordinate system: the ordinate is the number of records corresponding to the scoring value, and the abscissa is the scoring value. Different categories are connected by lines of different colors, and the intersection of the three lines can be seen intuitively; choose the one with a larger score The value of the intersection attachment is used as a threshold, and a certain number of recordings needs to be taken into account to eliminate the statistical distortion of the score and/or the number of recordings is too small; so that setting the threshold can be used to identify the correct number of recordings and scores. Optimization, the recognition accuracy is within the ideal range. The ideal range may be to set the threshold to 50-80.

For example: Set the threshold to 50; it means that when the collected picture recognizes that the facial feature value of the facial data is equal to the facial feature value of a certain picture in the system registration, the ratio reaches 50%;

Compare and score the data obtained by multiple real-time face collection with the first face collection data, and if the score is equal to 50, the comparison is successful, and face recognition is passed;

If the score is less than 50, go to step S135;

If the score is greater than 50, go to step S135.

The setting threshold may also only consider two classifications; in this case, the setting threshold is set by the setting module, and the specific setting basis is: according to the testing of different personnel, collecting and recording each time Check whether the result of recognition is correct, and record the corresponding scoring value and the number of records. Perform classification statistics on all records, the correctly identified one is one type, and the wrong one is one type, and the two types of data are placed in the same coordinate system: the abscissa is the scoring value, and the ordinate is the number of records corresponding to the scoring value; Connect the scoring value of each type of abscissa and the coordinate points corresponding to the number of records of the corresponding ordinate to form two connections in a coordinate system that have one or more intersections with each other. Line, record the distribution of the two types of data; find the intersection of the two types of data, and select the score of the intersection with the larger score as the threshold. At the same time, you need to take into account the factor of a certain number of records, and exclude the intersection with too few records. Point value. Through this method, the set threshold can be optimized for the correct number and score of the recognition, and the accuracy of the recognition is greatly improved, and it is within the ideal range.

For example: the threshold is set to 80; it means that when the collected picture recognizes that the facial feature value of the facial data is equal to the facial feature value of a certain picture in the system registration, the ratio reaches 80%.

Compare and score the data obtained by multiple real-time face collection with the first face collection data, and if the score is equal to 80, the comparison is successful;

If the score is less than 80, the entering step reaches the exit threshold number of times, it is determined that no one is waiting for the customer identification information and the voice inquiry is stopped;

If the score is greater than 80, the entering step reaches the threshold number of departures, it is determined that no one is waiting for the customer identification information and the voice inquiry is stopped.

Through the introduction of face recognition technology, a senseless authentication of customers is realized and the bank's affinity for customers is enhanced. Increase the customer experience of bank branches. It saves the amount of data interaction between the queuing machine and the external network. Improve the efficiency of the bank's work.

Step S102: The queuing machine performs data cleaning according to the effective queuing data of the customer, and groups and sorts the effective queuing data of the customer;

Please refer to FIG. 2. FIG. 2 is a data cleaning method described in step S102 in an embodiment of the present invention, including:

Step S421: Delete the unreasonable time-consuming customer queuing data; for example, the situation where the customer does not process the corresponding service after obtaining the number is called abandoning the account. If the time of the bank staff waiting for the abandoned client is included in the bank The time for handling the business will generate overtime. The time for bank staff to wait for abandoned customers is relatively fixed. Through the setting module, bank staff can set different timeout values in the database according to different types of business; remove the timeout data from the sample data to get the first Sample data for rounds. The sample data obtained in this way is more accurate, which can make the result of data cleaning more scientific;

Step S422: According to the settings, filter the data with too short processing time; for example, when the customer has not abandoned the account number, but due to forgetting to bring the ID or other temporary emergencies, the situation of abandoning the business on the spot often occurs. From the analysis of historical data, the data with too short processing time is basically of no reference value, because the bank has a large daily turnover, and the data with too short processing time is also excluded from the sample. Bank staff can also set the time value for the business with too short processing time. For example, according to previous statistics on data volume, the data whose processing time is less than 1 minute is invalid data. This time is also achieved through configuration items, and the threshold can be determined by the customer;

Step S423: The cleaned data is grouped according to the type of business, according to age and gender, to obtain further sample data; specifically, each group of data is separated into two sets of data, and the waiting time and business processing time of the sample data are separated ；

Step S424: Arrange the obtained two sets of data in an ascending order. For example, the data is classified by business content, and different businesses are divided into different categories. Then the data of the same category is grouped according to the customer level as the grouping standard, and the data of each group is sorted from small to large according to the processing time. So far, the data that meets the quality requirements and is arranged according to relevant requirements are organized.

Step S104: The queuing machine performs data processing according to the grouped and sorted data, and calculates the time required for the completion of each service; the data after the grouping and sorting is the queuing machine according to the grouping and sorting Further sample data;

Please refer to FIG. 3. FIG. 3 is a data processing method described in step S104 in an embodiment of the present invention, including:

Step S531: Calculate the interquartile range of data of the same level of different business types, select to retain the data at the first quartile to the third quartile, and perform the summation;

Step S532: Calculate the average value from the first quartile to the third quartile. If the amount of data in each group is less than four, and the data cannot be divided into quarters, then the average value is directly calculated without seeking the quartile;

Step S533: Combine the mean values of each group of interquartile range, and perform the mean operation on the first quartile to the third quartile of each data group under the same business category to obtain the mean value of the business category, that is, to obtain the business The average processing time of each level and the average processing time of each level.

The interquartile range, also known as the interquartile range, is a method in descriptive statistics to determine the difference between the third quartile and the first quartile. Like variance and standard deviation, it means statistics The dispersion of variables in the data. The four-point difference is more of a robust statistic. Therefore, adopting the interquartile range method as the method of data processing in the present invention makes the data statistics more reasonable, and further improves the operating efficiency of the queuing machine calculation module.

For example: there are data 1, 3, 5, 7, 8, 6, 4, 2. Sort from smallest to largest to get: 1,2,3,4,5,6,7,8. According to the quartile method, they are divided into four groups: 1, 2; 3, 4; 5, 6; 7, 8. Leave the middle two groups, namely groups 3 and 4 and groups 5 and 6, for the average.

Step S106: According to the time required for the completion of the service processing, the queuing machine prompts the processing time and estimated waiting time before picking up the number, and notifies the customer after the number picking; the prompt before the number picking includes displaying on the queuing machine screen, And/or voice broadcast, and/or mobile communication, and/or the Internet, and/or third-party platforms, and/or print notices, prompts; said notice after the number is picked up includes being displayed on the screen of the queuing machine, and/or Voice broadcast, and/or mobile communication, and/or the Internet, and/or third-party platforms, and/or printed notices, notifications.

After the step S106, it further includes:

Step S641: Cache and/or save the dictionary with business as the key word; for example, the average processing time of each business category and the average processing time of each level are obtained, and the business name and each level name are used as the main keywords. The corresponding average duration value is stored in the cache dictionary and local file as a dictionary value so that it can be quickly read and used when restarting on the same day, for the customer's reference to decide whether to handle this business.

Step S642: Print the estimated service processing time and estimated waiting time on the ticket and send a message to notify the customer; the notification includes: display on the queuing machine screen, and/or voice broadcast, and/or mobile communication, And/or the Internet, and/or third-party platform notifications; for example, notifications by SMS or WeChat, or notifications by the display screen of the queue machine or the interface of the display device associated with the queue machine;

Step S643: When the customer is waiting for the business process, when the number of people waiting for the same type of business reaches the set value, the customer is notified of the number of people waiting for the same type of business to assist the customer in referring to the arrival time; the business includes banking; for example, After obtaining the number, the customer can decide by himself whether to wait on the spot. If the customer decides not to wait on site, he can judge how long to leave and then return based on the number and time of waiting for the same type of business notified to the customer by the queuing machine, providing a reference for the customer to reasonably plan the customer's time. The queuing machine notifies the customer of the number and time of waiting for the same type of business can be notified in the form of an early warning value; the customer can set the remaining waiting time or the early warning value of the number of people through the client. When the number and time waiting for the same type of service of the queuing machine reaches the warning value, a notification is sent to the customer to provide the customer with a reminder service of the approaching number.

In an embodiment of the present application, a voice interaction method for a queuing machine is also provided, which includes the following steps:

When the camera of the queuing machine recognizes a customer, it proactively greets the customer, and recommends relevant services that can be handled according to past handling habits;

The queuing machine microphone collects voice information, and obtains the business information that the customer wants to handle through offline and/or online voice recognition. At the same time, the queuing machine camera captures the customer's lip-motion video and provides it to the face recognition unit for vital signs identification; if there is life If there is no vital sign, proceed to the next step; if there is no vital sign, notify the customer through the queuing machine and/or client device that it cannot be processed;

The queuing machine judges whether the bank can accept the business at present, if not, inform the customer through the queuing machine and/or client device that it cannot handle the business; if so, proceed to the next step;

The voice notification of the queuing machine can be processed and/or sent to the client device, and at the same time the bank server broadcasts the information returned by the bank branch server to the customer.

The queuing machine extracts effective customer queuing data, performs data cleaning, data processing, and calculates the time required for the completion of each business;

The queuing machine displays on the queuing machine screen, and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or a third-party platform, and/or prints a notice to notify customers of the completion of each service required According to the settings of the client client, the time required for the completion of each business is updated in real time for the client to inquire through the client client.

Customers can choose to use the queuing machine to receive notifications through voice, and/or flat display, and/or mobile communication through one or more of the methods through the customer client settings, or set other people to receive notifications on their behalf or at the same time. Notice. Through the technical solutions of voice recognition and interaction, customer voice inquiry and voice number taking are realized, so that customers can communicate and communicate with the queuing machine through voice, so that the queuing machine can directly respond to the business handled by the customer, avoiding a large number of queuing machine display screens. After displaying the business type, the delay caused by the customer selection process and the conformity and text input process is avoided, and repeated queries caused by customers forgetting the content displayed on the previous page due to the page turning of the display screen are avoided, thereby greatly improving the office efficiency of the bank. In the embodiment, voice recognition can also be connected with face recognition. The process of nodding, shaking or blinking in the prior art can be omitted in the bank ranking process, and the vital signs can be identified through the analysis and recording of the lip-motion video. , So that pictures, graphics, and videos without vital signs such as photos are excluded from the process of face recognition, which improves the customer's service experience in the banking industry. Enhance customers' goodwill towards outlets, increase outlet traffic and return rate of new customers.

Please refer to FIG. 4, which is a schematic structural diagram of a client 76 according to an embodiment of the present invention. The client is used for queuing, and the structure includes:

The setting module 74 is used to set the service content and mode of the queuing machine; the service content and mode include: the scene that requires voice interaction, the volume of the voice, the speed of the voice, the time for sending a notification to the customer, and/or Frequency, and/or type; the notification includes the time required for the completion of the business, the number of people waiting for the same type of business; the information and/or type broadcasted by the speaker of the queue machine;

The transceiver module 70 is used to exchange information and data between the display device and/or the queuing machine; the information and data interaction includes: receiving prompts for processing time and expected waiting time before picking up the number; receiving service processing ends Time required; receiving the real-time update sent by the queuing machine to the time required for the completion of each business;

The query module 72 is used to query the time required for the completion of each service processing update issued by the queuing machine in real time; it is also used to query the time required for the completion of the service processing updated by the queuing machine in real time.

Through the setting module 74 of the client 76, the client can set the approaching reminder according to his actual needs. By setting the number and time of waiting for the number ticket, setting the specific way of notification, setting the notified personnel, and improving the service pertinence of the queuing machine; the content set by the setting module 74 can be queried through the query module 72; the client 76 is conducive to customer acquisition Accurate business waiting and processing time; it is conducive to customers to arrange time and decide whether to take the number for business now according to their own circumstances. It is helpful for customers to reasonably plan their own time according to the prompts; it is beneficial to reduce the number of customers who abandon the number because the waiting time exceeds the tolerable range after obtaining the number, and to avoid wasting the number of ticket resources.

Please refer to FIG. 5. FIG. 5 is a schematic diagram of a queuing machine system 26 according to an embodiment provided by this application. The queuing machine system includes:

The processor 18 is used to obtain customer information, identify and extract effective customer queuing data; data cleaning and data processing; realize the interaction of information and data between the client and the server, so that the customer can query and set the information of the queuing machine;

The processor includes: an acquisition module 12, a calculation module 28, and a setting module 22;

The acquiring module 12 is used to acquire customer information, and to identify and extract effective customer queuing data. The customer information includes identity information and services to be handled;

The calculation module 28 is used to perform data cleaning according to the effective queuing data of the customer, and to group and sort the effective queuing data of the customer; and also to perform data processing according to the grouped and sorted data, and calculate each The time required for the completion of each business;

The setting module 22 is used to enable the customer to set the service content and mode of the queuing machine through the client client; the service content and mode include: scenes that require voice interaction, the volume of the voice, the speed of the voice, and the customer The time and/or frequency of sending notifications, the notifications including the time required for the completion of the business processing, and the number of people waiting for the same type of business; also used to set the interval and frequency of facial information recognition by the queuing machine; set multiple times The scoring weight and/or scoring method of face information recognition and comparison;

Transceiving module 32: According to the time required for the completion of the business processing, the processing time and the expected waiting time are sent out before the number is obtained and/or the notification is issued after the number is obtained; it is also used for display equipment, client, and /Or information and data interaction between queuing machines; said prompting before picking up the number, including display on the queuing machine screen, and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or a third party The platform, and/or print the notice to send out the prompt; the said sending out the notice after picking up the number, including the display on the screen of the queuing machine, and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or a third-party platform , And/or print a notice to issue a notice;

The display module 20 is used to display the content of the data and information interaction between the queuing machine and the customer in real time;

The storage module 30 is used to store calculation data and information; it is also used to store a memory dictionary stored with business as a key;

The security authentication module 34 is used to verify the real identity of the client or the operator of the queuing machine server;

The security authentication module includes a face recognition unit 14, a voice recognition unit 16, and an account management unit 24;

The face recognition unit 14 is used for verifying customer information through face recognition and extracting the customer's business processing information; it is also used for identifying the customer's lip-synching video;

The voice recognition unit 16 is used to recognize the information expressed by the customer through voice and/or mouth shape information;

The account management unit 24 is used to identify the real identity of the customer or the bank worker who needs to operate the queuing machine server by means of account and password login.

Please refer to FIG. 6, which is an operation diagram of the queuing machine system according to an embodiment provided by the present application. The customer 10 comes to the queuing machine, and the queuing machine system acquisition module 12 senses that someone is approaching and greets him actively; The facial information, voice, and lip-motion video are sent to the queuing machine system acquisition module 12, and the queuing machine system acquisition module 12 transmits the facial information, voice, and lip-motion video to the facial recognition unit 14 of the queuing machine system for recognition; The verbal action video includes lip shape information; the face recognition unit 14 of the queuing machine system recognizes the facial information and the lip shape action video; the voice and/or lip shape information is transmitted to the voice recognition unit 16 of the queuing machine system for recognition; The voice recognition unit 16 of the queuing machine system performs recognition. After the voice recognition unit 16 of the queuing machine system recognizes it, it sends it back to the face recognition unit 14 of the queuing machine system; the face recognition unit 14 of the queuing machine system recognizes according to the voice recognition unit 16 of the queuing machine system. The information determines whether the customer has vital signs; so far, the queuing machine system face recognition unit 14 sends the information of successful face recognition to the queuing machine system processor 18; the queuing machine system processor 18 selects the notification method to notify the customer according to the customer's setting 10. If the customer 10 does not set the default, the queuing machine speaker will broadcast the notification; the customer 10 sends a voice number application to the voice recognition unit 16 of the queuing machine system. The number application can also be sent through the method set by the customer. If the information is sent in the form of voice, it is directly sent to the queue machine system processor 18 without passing through the queue machine system voice recognition unit 16; the queue machine system voice recognition unit 16 receives the voice number application from the customer 10 for recognition, and then sends it To the queuing machine system processor 18; the queuing machine system processor 18 performs data processing, the data processing includes data cleaning and data processing, the queuing machine system processor 18 instructs the queuing machine to provide the customer with the number for business processing, and perform subsequent queuing The real-time update of the number status is available to the customer 10 for inquiries, or a notification of the real-time status of the numbering is sent according to the time and frequency set by the customer 10.

The queuing machine system is based on the collection of business processing quantity, statistics, analysis and processing time recommendation methods, and reminds customers of the waiting time and processing time for business processing through multiple channels. The queuing machine system can more accurately remind customers of business waiting and processing time, so that customers can arrange time according to their own circumstances and decide whether to take the number for business now, which improves the efficiency of bank services and reduces the cost of bank services.

In an embodiment of the present application, a queuing device is provided, including the queuing machine system, and the queuing machine system can implement the method described in the embodiment of the application.

In an embodiment of the present application, a server is provided, which includes a processor and a machine-readable storage medium. The machine-readable storage medium stores machine-executable instructions that can be executed by the processor and is called by the processor and When executed, the processor-executable instructions cause the processor to implement the method described in the embodiment of the present application.

If the integrated components/modules/units of the system/computer device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned implementation methods, and can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the foregoing method implementation manners. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file, or some intermediate forms. The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory) ), Random Access Memory (RAM, Random Access Memory), electrical carrier signal, telecommunications signal, and software distribution media, etc. It should be noted that the content contained in the computer-readable medium can be appropriately added or deleted according to the requirements of the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to the legislation and patent practice, the computer-readable medium Does not include electrical carrier signals and telecommunication signals.

In the several specific implementation manners provided by the present invention, it should be understood that the disclosed system and method may be implemented in other ways. For example, the system implementation described above is only illustrative. For example, the division of the components is only a logical function division, and there may be other division modes in actual implementation.

In addition, the functional modules/components in the various embodiments of the present invention may be integrated into the same processing module/component, or each module/component may exist alone physically, or two or more modules/components may be integrated in the same processing module/component. Module/part. The above-mentioned integrated modules/components can be implemented either in the form of hardware, or in the form of hardware plus software functional modules/components.

For those skilled in the art, it is obvious that the embodiments of the present invention are not limited to the details of the above exemplary embodiments, and the embodiments of the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the embodiments of the present invention. example. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the embodiments of the present invention is defined by the appended claims rather than the foregoing description, and therefore it is intended to fall within All changes within the meaning and scope of equivalent elements of the claims are included in the embodiments of the present invention. Any reference signs in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "including" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units, modules or devices stated in the claims of a system, device or terminal can also be implemented by the same unit, module or device through software or hardware. Words such as first and second are used to denote names, but do not denote any specific order.

The above-mentioned embodiments only express several implementation modes of the present invention, and their description is relatively specific and detailed, but they should not be understood as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention should be subject to the appended claims.

Claims (14)

A queuing method, characterized in that the method includes: The queuing machine obtains customer information, and identifies and extracts effective customer queuing data; The queuing machine performs data cleaning according to the effective queuing data of the customer, and groups and sorts the effective queuing data of the customer; The queuing machine performs data processing according to the grouped and sorted data, and calculates the time required for the completion of each business; According to the time required for the completion of the business processing, the queuing machine prompts the processing time and estimated waiting time before picking up the number, and informs the customer after picking up the number. The queuing method according to claim 1, wherein the queuing machine obtains customer information, and identifies and extracts effective queuing data of the customer, further comprising: The queuing machine asks customers whether they need to transact business and use the queuing machine's screen display, and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or third-party platforms, and/or print notices, and make the inquiry; The queuing machine identifies the customer who was judged as yes in the previous step; For customers who have successfully identified their identity information, the queuing machine obtains the specific types of services that the customer needs to handle through screen display and/or voice inquiry; for customers who fail to identify their identity information, the queuing machine provides customers with common causes of errors through screen display and/or voice analysis; The queuing machine informs the customers who have failed to identify the identity information through the screen display of the queuing machine, and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or third-party platforms, and/or printing a notice Bank staff assisted and sent waiting notices to customers. The queuing method according to claim 2, wherein the queuing machine obtains customer information through face recognition, and the face recognition method comprises: Step S131: The queuing machine processor receives the data of the queuing machine camera and determines whether there is a human face. If so, it retrieves the video of the customer's voice interaction with the queuing machine captured by the camera to identify whether the customer has vital signs; if it is, proceed to step S132, If not, end face recognition, determine that no one is waiting for customer identification information, and stop voice inquiry; the voice interaction video between the customer and the queuing machine includes the lip-synching video obtained by the queuing machine camera; Step S132: The queuing machine processor instructs the speaker to voice guide the customer to pose, perform real-time face collection, and generate the first face collection data; Step S133: The queuing machine requires the customer to perform face collection again in real time according to the interval and number of times set by the queuing machine; Step S134: The queuing machine processor calculation unit compares and scores the facial information of the face information acquired for the first time according to the interval time and number of times set by the queuing machine: if it is determined to be the same after multiple comparisons and the scores For customers, face recognition is adopted; if multiple comparisons and scores determine that they are different customers, it is determined that the face recognition has failed, and step S135 is performed; Step S135: The queuing machine classifies customers whose face recognition has failed. If one of the pictures and/or videos can identify the customer, but the recognition fails because the interval and number of times set by the queuing machine are not reached, proceed Step S136: If there is no picture and/or video that can identify the customer, the face recognition is ended, and the customer is notified by voice; Step S136: End face recognition, and notify the customer through voice, and extract the queuing data of the valid customer after the recognition is completed, compare the customer’s habit of handling banking business at the same time period, select the customer’s previous business, and call the same The time required for the completion of business processing is displayed on the screen of the queuing machine, and the content of the ticket is printed to inform the customer of the processing time and estimated waiting time. The queuing method according to claim 3, wherein the method of comparing and scoring includes: Compare and score the data obtained by multiple real-time face collection with the first face collection data, and if the score is equal to the set threshold, the comparison is successful, and face recognition is passed; If the score is less than the set threshold, then enter the step S135; If the score is greater than the set threshold, then step S135 is entered. The queuing method according to claim 1, wherein the data cleaning method comprises: Delete the unreasonable time-consuming customer queuing data; According to the setting, filter the data with too short processing time; Group the cleaned data according to the type of business, according to age and gender, to obtain further sample data; Arrange the obtained two sets of data in ascending order. The queuing method according to claim 1, wherein the data processing method comprises: Calculate the interquartile range of the same level of data for different business types, choose to retain the data from the first quartile to the third quartile, and perform the summation; Calculate the average value from the first quartile to the third quartile. If the amount of data in each group is less than four, and the data cannot be divided into quarters, then the average value is directly calculated without seeking the quartile; Combine the mean value of each group of interquartile range, and perform the mean operation on the first quartile to the third quartile of each data group under the same business category to obtain the mean value of the business category, which is the average transaction of the business Duration and the average processing time for each level. The queuing method according to claim 1, wherein the queuing machine prompts the processing time and estimated waiting time before taking the number according to the time required for the completion of the business processing, and after notifying the customer after the number is taken, Also includes: Cache and/or save dictionaries with business as keywords; Print the estimated time required for business processing and estimated waiting time on the number ticket and send a message to notify the customer; When the customer is waiting for the business process, when the number of people waiting for the same type of business reaches the set value, the customer is notified of the number of people waiting for the same type of business to assist the customer in referring to the arrival time; the business includes banking. The queuing method according to claim 1, characterized in that, the prompt before taking the number includes displaying on the screen of the queuing machine, and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or a third party Platform, and/or print notice, prompt; said notification after the number is taken includes display on the screen of the queue machine, and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or a third-party platform, and / Or print a notice, notice. A voice interaction method for a queuing machine is characterized in that the voice interaction method for a queuing machine includes the following steps: When the camera of the queuing machine recognizes a customer, it proactively greets the customer, and recommends relevant services that can be handled according to past handling habits; The queuing machine microphone collects voice information, and obtains the business information that the customer wants to handle through offline and/or online voice recognition. At the same time, the queuing machine camera captures the customer's lip-motion video and provides it to the face recognition unit for vital signs identification; if If you have vital signs, proceed to the next step; if you don’t have vital signs, you will be notified through the queuing machine and/or client device that the client cannot be processed; The queuing machine judges whether the bank can accept the business at present, if not, inform the customer through the queuing machine and/or client device that it cannot handle the business; if so, proceed to the next step; The voice notification of the queuing machine can be processed and/or sent to the client device, and at the same time the bank server will broadcast the information returned by the bank branch server to the customer; The queuing machine extracts effective customer queuing data, performs data cleaning, data processing, and calculates the time required for the completion of each business; The queuing machine informs the customer of the time required for the completion of each business through the queuing machine screen display and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or the third-party platform, and according to the client's settings , Real-time update of the time required for the completion of each business transaction for customers to inquire through the customer client. A queuing machine system is characterized in that it comprises: The processor is used to obtain customer information, identify and extract effective customer queuing data; data cleaning and data processing; realize the interaction of information and data between the client and the server, so that the customer can query and set the information of the queuing machine; The processor includes: an acquisition module, a calculation module, and a setting module; The acquisition module is used to acquire customer information, and to identify and extract effective customer queuing data. The customer information includes identity information and services to be handled; The calculation module is used to perform data cleaning according to the effective queuing data of the customer, and to group and sort the effective queuing data of the customer; and also to perform data processing according to the grouped and sorted data, and calculate each The time required for the completion of the business; The setting module is used to enable the customer to set the service content and method of the queuing machine through the customer client; the service content and method include: scenes requiring voice interaction, voice volume, voice speed, and sending to the customer The time and/or number of notifications, the notification includes the time required for the completion of the business processing, the number of people waiting for the same type of business; it is also used to set the interval and the number of times for the queuing machine to recognize facial information; set multiple people The scoring weight and/or scoring method of face information recognition and comparison; Transceiver module: According to the time required for the completion of the business processing, the processing time and the expected waiting time are sent out before the number is obtained and/or the notification is issued after the number is obtained; it is also used in the display device, the client, and/ Or information and data interaction between queuing machines; said prompting before picking up a number, including display on the screen of the queuing machine, and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or a third-party platform , And/or print a notice to send out a reminder; said sending out a notice after picking up the number, including displaying on the screen of the queuing machine, and/or voice broadcast, and/or mobile communication, and/or the Internet, and/or a third-party platform, And/or print a notice to issue a notice; The display module is used to display the content of the data and information interaction between the queuing machine and the customer in real time. The queuing machine system according to claim 10, wherein the queuing machine system further comprises: The storage module is used to store calculation data and information; it is also used to store a memory dictionary stored with business as a key; The security authentication module is used to verify the real identity of the customer or the operator of the queuing machine server; The security authentication module includes a face recognition unit, a voice recognition unit, and an account management unit; The face recognition unit is used to verify customer information through face recognition and extract the customer's business processing information; and is also used to identify the customer's lip-synching video; The voice recognition unit is used to recognize the information expressed by the customer through voice and/or mouth shape information; The account management unit is used to identify the real identity of the customer or the bank worker who needs to operate the queuing machine server by means of account and password login. A client, characterized in that the client includes: The setting module is used to set the service content and mode of the queuing machine; the service content and mode include: the scene that requires voice interaction, the volume of the voice, the speed of the voice, the time and/or frequency of sending notifications to customers , And/or type, the notification includes the time required for the completion of the service, the number of people waiting for the same type of service, and the information and/or type broadcasted by the speaker of the queuing machine; The transceiver module is used for the interaction of information and data between the display device and/or the queuing machine; the interaction of the information and data includes: receiving prompts for processing time and estimated waiting time before picking up the number; receiving the end of business processing Time required; receiving the real-time update sent by the queuing machine the time required for the completion of each business; The query module is used to query the time required for the completion of each service for the update sent by the queuing machine in real time; it is also used to query the time required for the completion of the service for the real-time update of the queuing machine. A queuing device, characterized by comprising the queuing machine system according to any one of claims 10 or 11. A server, characterized by comprising: a processor and a machine-readable storage medium, the machine-readable storage medium stores machine-executable instructions that can be executed by the processor, and when called and executed by the processor, the The processor-executable instructions cause the processor to implement the method of any one of claims 1-9.

Images