CN114120516B - Method for optimizing business hall number calling sequence - Google Patents
Method for optimizing business hall number calling sequence Download PDFInfo
- Publication number
- CN114120516B CN114120516B CN202111422828.2A CN202111422828A CN114120516B CN 114120516 B CN114120516 B CN 114120516B CN 202111422828 A CN202111422828 A CN 202111422828A CN 114120516 B CN114120516 B CN 114120516B
- Authority
- CN
- China
- Prior art keywords
- client
- queuing
- waiting time
- time
- customer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 230000002787 reinforcement Effects 0.000 claims abstract description 23
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C11/00—Arrangements, systems or apparatus for checking, e.g. the occurrence of a condition, not provided for elsewhere
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C11/00—Arrangements, systems or apparatus for checking, e.g. the occurrence of a condition, not provided for elsewhere
- G07C2011/04—Arrangements, systems or apparatus for checking, e.g. the occurrence of a condition, not provided for elsewhere related to queuing systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a business hall number calling sequence optimizing method, which comprises the following steps: step 1: when a customer uses a queuing machine to conduct queuing, a queuing system records queuing information of the customer; step 2: preprocessing the ranking information to obtain the longest waiting time and the to-be-handled service processing time of the client; step 3: inputting the queuing information, the longest waiting time and the to-be-handled business processing time of the client into a deep reinforcement learning network to obtain the dynamic score of the client, determining a pre-queuing queue according to the dynamic score, judging whether the waiting time of the client in the pre-queuing sequence exceeds the longest waiting time, if so, increasing the score of the client and improving the order of the client in the pre-queuing queue, thereby obtaining the final queuing queue. The invention can dynamically adjust the queuing sequence according to the data such as the identity of the client, the number taking time, the type of the business to be handled and the like, avoid overlong waiting time of the client and improve the satisfaction degree of the client.
Description
Technical Field
The invention relates to the technical field of information processing, in particular to a business hall number calling sequence optimization method.
Background
The bank queuing system is also called a bank queuing machine and a number calling display system, and is a system applied to banks.
With the rapid development of electronic information products and intelligent products, and the increasing demands of human life on service environments and service efficiency, especially in the service industry, the concept of queuing systems has been developed. The popular service industry of banks naturally enters the first camp of the queuing system, and the banking queuing system is now a substitute term of the queuing system, so that people can easily find that each bank is provided with a queuing system for ticket taking machine, voice number calling and display.
Before the queuing system is produced, waiting personnel always stand for queuing when queuing, one-squeeze two-three-urgent four-beat queuing is performed for five fear of queue insertion, and even the conflict between language and limbs is brought. After the queuing system is born, the problems are completely avoided, and waiting personnel can sit in the rest hall for safe queuing after taking out the number ticket, so that the queuing system not only improves the service efficiency, but also improves the service environment; more importantly, the method brings good environment and relaxed mood for waiting staff, and even can reasonably arrange own waiting time and the like.
However, even with queuing systems, there are still problems when handling business for queuing. For example, at present, the number calling mechanisms of business halls such as banks, operators and the like adopt sequential number calling, namely, the sequential number calling is carried out according to the number taking sequence of clients, so that the fairness of the clients waiting can be greatly ensured, but the problem of overlong waiting time may exist for special clients such as VIP, old people and the like. Therefore, a number calling mechanism based on the identity of the client is widely used, and the mechanism directly prioritizes clients with special identities such as VIP, old people, soldiers and the like, so that when the clients with special identities are particularly more, the waiting time of the ordinary clients is too long, the dissatisfaction of the ordinary clients is easily caused, and the satisfaction degree of the clients is reduced.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a business hall calling sequence optimization method.
The aim of the invention is realized by the following technical scheme:
a business hall number calling sequence optimizing method comprises the following steps: the method comprises the following steps:
Step 1: when a customer uses a queuing machine to conduct queuing, a queuing system records queuing information of the customer; step 2: preprocessing the ranking information to obtain the longest waiting time and the to-be-handled service processing time of the client;
Step 3: inputting the queuing information, the longest waiting time and the to-be-handled business processing time of the client into a deep reinforcement learning network to obtain the dynamic score of the client, determining a pre-queuing queue according to the dynamic score, judging whether the waiting time of the client in the pre-queuing sequence exceeds the longest waiting time, if so, increasing the score of the client and improving the order of the client in the pre-queuing queue, thereby obtaining a final queuing queue;
When the deep reinforcement learning network is trained, the task completion probability of the current queuing queue is calculated according to the to-be-handled service processing time of the clients in the current queuing queue, namely, how many clients can complete service handling within the longest waiting time of the clients, and the task completion probability is used as a reward function to update the deep reinforcement learning network.
Further, the ranking information comprises the identity of the client, the number taking time and the business to be handled.
Further, the step 2 specifically includes:
Step 201: acquiring the processing time of each service according to the history information;
Step 202: and obtaining the longest waiting time and the waiting business processing time of the client according to the ranking information and the history record information of the client.
Further, having different priorities for different of said customer identities; the higher the priority, the larger the initial value of the score setting, and the shorter the longest waiting time.
The step 3 is specifically as follows:
step 301: normalizing and discretizing the identity of the client, the longest waiting time, the number taking time, the current time and the to-be-handled service processing time, and then inputting the normalized and discretized time into a trained deep reinforcement learning network to generate dynamic scores of the client;
Step 302: determining a current pre-queuing queue according to the dynamic scoring;
step 303: calculating the waiting time of the client according to the current pre-queuing queue, and judging whether the waiting time of the client exceeds the longest waiting time of the client;
step 304: if not, not performing any treatment; if the number exceeds the number, the customer score is increased by mdelta, the customer score which is numbered before the customer is increased by delta, so that a final queuing queue is output, and a penalty is applied to the deep reinforcement learning network.
Further, the deep reinforcement learning network is provided with five input ends, and the client identity, the longest waiting time, the number taking time, the current time and the to-be-handled service processing time are respectively input; the deep reinforcement learning network has n outputs representing n different scores, the size of n being used to characterize the user's discrimination granularity.
The invention has the beneficial effects that: the invention provides a business hall number calling sequence optimization method, which can dynamically adjust the queuing sequence according to the data of the identity of a customer, the number taking time, the type of business to be handled and the like, avoid overlong waiting time of the customer and improve the satisfaction degree of the customer.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to the structures shown in these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of the method of the present invention.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In this embodiment, as shown in fig. 1, a business hall number calling sequence optimizing method: the method comprises the following steps:
Step 1: when a customer uses a queuing machine to conduct queuing, a queuing system records queuing information of the customer; step 2: preprocessing the ranking information to obtain the longest waiting time and the to-be-handled service processing time of the client;
Step 3: inputting the queuing information, the longest waiting time and the to-be-handled business processing time of the client into a deep reinforcement learning network to obtain the dynamic score of the client, determining a pre-queuing queue according to the dynamic score, judging whether the waiting time of the client in the pre-queuing sequence exceeds the longest waiting time, if so, increasing the score of the client and improving the order of the client in the pre-queuing queue, thereby obtaining a final queuing queue;
When the deep reinforcement learning network is trained, the task completion probability of the current queuing queue is calculated according to the to-be-handled service processing time of the clients in the current queuing queue, namely, how many clients can complete service handling within the longest waiting time of the clients, and the task completion probability is used as a reward function to update the deep reinforcement learning network.
Further, the ranking information comprises the identity of the client, the number taking time and the business to be handled.
Further, the step 2 specifically includes:
Step 201: acquiring the processing time of each service according to the history information;
Step 202: and obtaining the longest waiting time and the waiting business processing time of the client according to the ranking information and the history record information of the client.
Further, having different priorities for different of said customer identities; the higher the priority, the larger the initial value of the score setting, and the shorter the longest waiting time.
The step 3 is specifically as follows:
step 301: normalizing and discretizing the identity of the client, the longest waiting time, the number taking time, the current time and the to-be-handled service processing time, and then inputting the normalized and discretized time into a trained deep reinforcement learning network to generate dynamic scores of the client;
Step 302: determining a current pre-queuing queue according to the dynamic scoring;
step 303: calculating the waiting time of the client according to the current pre-queuing queue, and judging whether the waiting time of the client exceeds the longest waiting time of the client;
step 304: if not, not performing any treatment; if the number exceeds the number, the customer score is increased by mdelta, the customer score which is numbered before the customer is increased by delta, so that a final queuing queue is output, and a penalty is applied to the deep reinforcement learning network. Wherein m is a constant.
Further, the deep reinforcement learning network is provided with five input ends, and the client identity, the longest waiting time, the number taking time, the current time and the to-be-handled service processing time are respectively input; the deep reinforcement learning network has n outputs representing n different scores, the size of n being used to characterize the user's discrimination granularity.
In this embodiment, the optimization objective of the deep reinforcement learning model is to maximize the success rate of calling numbers over a period of time. The method can optimize the number calling sequence of the business hall by modifying the number calling algorithm based on the existing number calling equipment, and improves the customer satisfaction degree by using lower cost.
The invention provides a business hall number calling sequence optimization method, which can dynamically adjust the queuing sequence according to the data of the identity of a customer, the number taking time, the type of business to be handled and the like, avoid overlong waiting time of the customer and improve the satisfaction degree of the customer.
It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of action described, as some steps may be performed in other order or simultaneously according to the present application. Further, it should be understood by those skilled in the art that the embodiments described in the specification are all preferred embodiments, and the acts and elements referred to are not necessarily required for the present application.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in the embodiments may be accomplished by computer programs stored in a computer-readable storage medium, which when executed, may include the steps of the embodiments of the methods described above. Wherein the storage medium may be a magnetic disk, an optical disk, a ROM, a RAM, etc.
The foregoing disclosure is illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.
Claims (4)
1. The business hall number calling sequence optimizing method is characterized by comprising the following steps of:
step 1: when a customer uses a queuing machine to conduct queuing, a queuing system records queuing information of the customer;
step 2: preprocessing the ranking information to obtain the longest waiting time and the to-be-handled service processing time of the client, wherein the preprocessing specifically comprises the following steps:
Step 201: acquiring the processing time of each service according to the history information;
Step 202: obtaining the longest waiting time and the waiting business processing time of the client according to the ranking information and the history record information of the client;
Step 3: inputting the queuing information, the longest waiting time and the to-be-handled service processing time of the client into a deep reinforcement learning network to obtain the dynamic score of the client, determining a pre-queuing queue according to the dynamic score, judging whether the waiting time of the client in the pre-queuing sequence exceeds the longest waiting time, if so, increasing the score of the client and improving the order of the client in the pre-queuing queue, thereby obtaining a final queuing queue, specifically comprising the following steps:
step 301: normalizing and discretizing the identity of the client, the longest waiting time, the number taking time, the current time and the to-be-handled service processing time, and then inputting the normalized and discretized time into a trained deep reinforcement learning network to generate dynamic scores of the client;
Step 302: determining a current pre-queuing queue according to the dynamic scoring;
step 303: calculating the waiting time of the client according to the current pre-queuing queue, and judging whether the waiting time of the client exceeds the longest waiting time of the client;
Step 304: if not, not performing any treatment; if the number exceeds the number, increasing the customer score by mdelta, increasing the customer score of the number which is taken before the customer by delta, thereby outputting a final queuing queue, and applying punishment to the deep reinforcement learning network;
When the deep reinforcement learning network is trained, the task completion probability of the current queuing queue is calculated according to the to-be-handled service processing time of the clients in the current queuing queue, namely, how many clients can complete service handling within the longest waiting time of the clients, and the task completion probability is used as a reward function to update the deep reinforcement learning network.
2. The method for optimizing the order of hall calls according to claim 1, wherein the ranking information comprises customer identity, number taking time and business to be handled.
3. A business hall call sequence optimizing method as claimed in claim 1, wherein said customer identities have different priorities; the higher the priority, the larger the initial value of the score setting, and the shorter the longest waiting time.
4. The method for optimizing the number calling sequence in a business hall according to claim 1, wherein the deep reinforcement learning network is provided with five input ends for respectively inputting a client identity, a longest waiting time, a number taking time, a current time and a to-be-handled business processing time; the deep reinforcement learning network has n outputs representing n different scores, the size of n being used to characterize the user's discrimination granularity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111422828.2A CN114120516B (en) | 2021-11-26 | 2021-11-26 | Method for optimizing business hall number calling sequence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111422828.2A CN114120516B (en) | 2021-11-26 | 2021-11-26 | Method for optimizing business hall number calling sequence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114120516A CN114120516A (en) | 2022-03-01 |
| CN114120516B true CN114120516B (en) | 2024-04-30 |
Family
ID=80370155
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111422828.2A Active CN114120516B (en) | 2021-11-26 | 2021-11-26 | Method for optimizing business hall number calling sequence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114120516B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114664014B (en) * | 2022-03-28 | 2024-10-18 | 中国银行股份有限公司 | Bank outlet user queuing method and device |
| CN115171264B (en) * | 2022-07-04 | 2024-05-07 | 中国银行股份有限公司 | Queuing management method and related device |
| CN115394002A (en) * | 2022-08-24 | 2022-11-25 | 中国银行股份有限公司 | Data processing method and device |
| CN115482620A (en) * | 2022-09-29 | 2022-12-16 | 上海浦东发展银行股份有限公司 | Multi-channel intelligent number calling method, device, equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103679529A (en) * | 2013-12-10 | 2014-03-26 | 谭希韬 | Method and system for calculating banking business handling time based on application for banking businesses |
| CN104732640A (en) * | 2015-03-09 | 2015-06-24 | 联动优势科技有限公司 | Queuing number calling method and number call server |
| CN110516874A (en) * | 2019-08-28 | 2019-11-29 | 中国银行股份有限公司 | Information processing method, apparatus and system |
| CN111489026A (en) * | 2020-04-08 | 2020-08-04 | 中国银行股份有限公司 | Queuing time estimation method, system and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101860819A (en) * | 2010-06-07 | 2010-10-13 | 广州从兴电子开发有限公司 | User information pushing method, presentation method, system, server and client |
-
2021
- 2021-11-26 CN CN202111422828.2A patent/CN114120516B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103679529A (en) * | 2013-12-10 | 2014-03-26 | 谭希韬 | Method and system for calculating banking business handling time based on application for banking businesses |
| CN104732640A (en) * | 2015-03-09 | 2015-06-24 | 联动优势科技有限公司 | Queuing number calling method and number call server |
| CN110516874A (en) * | 2019-08-28 | 2019-11-29 | 中国银行股份有限公司 | Information processing method, apparatus and system |
| CN111489026A (en) * | 2020-04-08 | 2020-08-04 | 中国银行股份有限公司 | Queuing time estimation method, system and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114120516A (en) | 2022-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114120516B (en) | Method for optimizing business hall number calling sequence | |
| US10991366B2 (en) | Method of processing dialogue query priority based on dialog act information dependent on number of empty slots of the query | |
| CN111489095B (en) | Risk user management method, apparatus, computer device and storage medium | |
| CN110175229B (en) | Method and system for on-line training based on natural language | |
| CN113360622B (en) | User dialogue information processing method and device and computer equipment | |
| CN105355200B (en) | System and method for directly training and modifying robot interactive content | |
| US12002454B2 (en) | Method and apparatus for intent recognition and intent prediction based upon user interaction and behavior | |
| CN111080087B (en) | Calling center scheduling method based on customer emotion analysis | |
| CN111858854A (en) | Question-answer matching method based on historical dialogue information and related device | |
| CN110674276B (en) | Robot self-learning method, robot terminal, device and readable storage medium | |
| CN115169906A (en) | Customer service distribution method and device, computer equipment and storage medium | |
| CN117909483A (en) | Personalized dialogue method, system, equipment and medium | |
| CN109074809A (en) | Information processing equipment, information processing method and program | |
| CN113987151A (en) | Intelligent customer service reply method and device | |
| CN117312982A (en) | Method for detecting true person in man-machine conversation process based on large model | |
| CN114969295A (en) | Dialog interaction data processing method, device and equipment based on artificial intelligence | |
| CN114218356B (en) | Semantic recognition method, device, equipment and storage medium based on artificial intelligence | |
| CN113010664B (en) | Data processing method and device and computer equipment | |
| CN114254088A (en) | Method for constructing automatic response model and automatic response method | |
| CN115641850A (en) | Method and device for recognizing ending of conversation turns, storage medium and computer equipment | |
| CN116521875B (en) | Prototype enhanced small sample dialogue emotion recognition method for introducing group emotion infection | |
| Fotedar et al. | Automatic Recognition of Social Roles Using Long Term Role Transitions in Small Group Interactions. | |
| CN114500754A (en) | Voice data processing method, device, storage medium and equipment | |
| CN116564294A (en) | Training method and device for noise identification model | |
| CN117972216A (en) | LLM-based intelligent question-answer reply method, system and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |