CN117576822B - Queuing and number calling guiding system based on Internet platform - Google Patents

Queuing and number calling guiding system based on Internet platform Download PDF

Info

Publication number
CN117576822B
CN117576822B CN202311545492.8A CN202311545492A CN117576822B CN 117576822 B CN117576822 B CN 117576822B CN 202311545492 A CN202311545492 A CN 202311545492A CN 117576822 B CN117576822 B CN 117576822B
Authority
CN
China
Prior art keywords
queued
target
user
weight
time
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
Application number
CN202311545492.8A
Other languages
Chinese (zh)
Other versions
CN117576822A (en
Inventor
伍启明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Huishi Technology Group Co ltd
Original Assignee
Shanghai Huishi Technology Group Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Huishi Technology Group Co ltd filed Critical Shanghai Huishi Technology Group Co ltd
Priority to CN202311545492.8A priority Critical patent/CN117576822B/en
Publication of CN117576822A publication Critical patent/CN117576822A/en
Application granted granted Critical
Publication of CN117576822B publication Critical patent/CN117576822B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/253—Fusion techniques of extracted features
    • 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

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the technical field of data processing, in particular to a queuing and number calling guiding system based on an Internet platform, which comprises a memory and a processor, wherein the processor executes a computer program stored in the memory to realize the following steps: acquiring reservation time information of all users to be queued, determining time weight, and screening all target users to be queued based on the time weight; determining service weight by analyzing time distribution characteristics of target users to be queued; determining contribution degree through time weight and service weight, and carrying out clustering treatment on all users to be queued based on the contribution degree to obtain each cluster; and queuing and number calling guiding is carried out on each user to be queued in each cluster. According to the invention, the self-adaptive weight in the clustering process is constructed according to the user data characteristics, so that the adverse effect that the clustering result does not contain the user data characteristics is eliminated, and the accuracy of the queuing number calling guiding result is improved.

Description

Queuing and number calling guiding system based on Internet platform
Technical Field
The invention relates to the technical field of data processing, in particular to a queuing and number calling guiding system based on an Internet platform.
Background
In order to avoid long-time waiting of a user in a queuing stage, the queuing can be reserved in advance through an internet platform, reservation time and service items are selected, and a queuing and number calling guiding system is constructed. When the user visits or services are taken turns, the platform informs the user to go to the appointed place in a mode of short message, application (APP) reminding and the like. When the number of users is large, the platform guides the users to queue and select time periods based on the results provided by the clustering algorithm, so that congestion and time waste caused by excessive people flowing or queuing are avoided. For clustering algorithms, e.g., ISODATA (ITERATIVE SELF-organization DATA ANALYSIS Technique, iterative self-Organizing data analysis techniques).
In the prior art, ISODATA is used for clustering according to reservation information provided by users, such as reservation time, service start time, service end time and the like, group division of users is performed according to a clustering result, users belonging to the same group are guided by the same service time, and confusion caused by a large number of users at a certain time point is avoided. In the process of clustering according to user information by using ISODATA, a clustering cluster center is constructed by using the same weight for users with inconsistent information, so that the clustering result is easy to lose the characteristic information of the users, and the queuing number calling guiding result is deviated, thereby influencing the user experience. Wherein the information of inconsistent users comprises reserved service duration, service type and the like.
Disclosure of Invention
In order to solve the technical problem that the clustering result of the existing queuing and number calling guiding system is easy to lose the characteristic information of the user and causes deviation of the queuing and number calling guiding result, the invention aims to provide the queuing and number calling guiding system based on an Internet platform, and the adopted technical scheme is as follows:
one embodiment of the invention provides a queuing and number calling guiding system based on an internet platform, which comprises a memory and a processor, wherein the processor executes a computer program stored in the memory to realize the following steps:
Acquiring reservation time information of all users to be queued in a preset time period, wherein the reservation time information comprises service start time and service end time;
Analyzing the abnormal service time characteristics of the users to be queued according to the service start time and the service end time of each user to be queued, and determining the time weight of each user to be queued; selecting all target users to be queued according to the time weight of each user to be queued;
Analyzing the time distribution characteristics of the target users to be queued according to the service start time and the service end time of each target user to be queued, and determining the service weight of each target user to be queued; determining the contribution degree of each target user to be queued according to the fusion characteristics of the service weight and the time weight of each target user to be queued;
clustering is carried out on all the users to be queued, and the contribution degree of each target user to be queued is used as the weight in the process of determining the cluster center, so that each cluster is obtained; and queuing and number calling guiding is carried out on each user to be queued in each cluster.
Further, analyzing the abnormal service time characteristics of the users to be queued according to the service start time and the service end time of each user to be queued, and determining the time weight of each user to be queued comprises the following steps:
constructing a coordinate system by taking the service start time as a horizontal axis and the service end time as a vertical axis; mapping each user to be queued onto a coordinate system based on the service start time and the service end time of each user to be queued, and obtaining each sample point on the coordinate system; the angular bisector of the first quadrant determined on the coordinate system is a target straight line;
for any sample point on the coordinate system, determining the distance between the sample point and the target straight line, and determining the difference between the ordinate value and the abscissa value of the sample point; and determining the time weight of the user to be queued corresponding to the sample point according to the distance between the sample point and the target straight line and the difference value between the ordinate value and the abscissa value of the sample point.
Further, the calculation formula of the time weight is as follows:
wherein T (i) is the time weight of the user to be queued corresponding to the ith sample point, norm is a linear normalization function, alpha is a first preset parameter weight, |is an absolute value function, s (i) is the abscissa value of the ith sample point, e (i) is the ordinate value of the ith sample point,/> For the distance between the i-th sample point and the target straight line, arctan is an arctangent function, and [ e (i) -s (i) ] is the difference between the ordinate and abscissa values of the i-th sample point.
Further, selecting all target users to be queued according to the time weight of each user to be queued, including:
And comparing the time weight of each user to be queued with a preset weight threshold, and taking the user to be queued with the time weight greater than the preset weight threshold as a target user to be queued.
Further, analyzing the time distribution characteristics of the target users to be queued according to the service start time and the service end time of each target user to be queued, and determining the service weight of each target user to be queued comprises:
Dividing the coordinate system into a preset number of areas, and determining the service weight of the target users to be queued corresponding to each target sample point according to the distribution condition of each target sample point in the coordinate system in the areas; the target sample point is a sample point formed by the service start time and the service end time of the target user to be queued.
Further, according to the distribution condition of each target sample point in the region on the coordinate system, determining the service weight of the target user to be queued corresponding to each target sample point includes:
marking any one target sample point as a selected target sample point, and respectively selecting a preset number of adjacent areas in the transverse direction and the longitudinal direction of the area where the selected target sample point belongs;
And determining the service weight of the target user to be queued corresponding to the selected target sample point according to the number of the target sample points in the area to which the selected target sample point belongs, the number of the target sample points in the adjacent areas corresponding to the transverse and longitudinal directions of the area to which the selected target sample point belongs and the number of the target sample points in the target area.
Further, the target area is an area with the largest number of target sample points on a coordinate system, and the preset number of adjacent areas are a plurality of areas closest to the area to which the selected target sample point belongs.
Further, the calculation formula of the service weight of the target user to be queued corresponding to the selected target sample point is as follows:
Wherein Z j is the service weight of the target user to be queued corresponding to the jth target sample point, Q max is the number of target sample points in the target area, Q j is the number of target sample points in the area to which the jth target sample point belongs, Q1 j,c is the number of target sample points in the C-th adjacent area corresponding to the transverse direction of the area to which the jth target sample point belongs, Q2 j,c is the number of target sample points in the C-th adjacent area corresponding to the longitudinal direction of the area to which the jth target sample point belongs, C is the number of adjacent areas of the area to which the jth target sample point belongs, namely the preset number, beta is the preset super parameter, I is the absolute value function, and norm is the linear normalization function.
Further, determining the contribution degree of each target user to be queued according to the fusion characteristics of the service weight and the time weight of each target user to be queued, including:
Setting a second preset parameter weight for any target user to be queued, and calculating the product of the second preset parameter weight and the time weight of the target user to be queued as a first product; taking the difference value between the 1 and the second preset parameter weight as a third preset parameter weight, and calculating the product of the third preset parameter weight and the service weight of the target user to be queued as a second product; and taking the value obtained by adding the first product and the second product as the contribution degree of the target user to be queued.
Further, queuing and number calling guiding is carried out on each user to be queued in each cluster, which comprises the following steps:
and determining a service time period corresponding to each user to be queued in each cluster by utilizing an Internet platform according to the user characteristic information of each cluster, and pushing the service time period to the corresponding user to be queued.
The invention has the following beneficial effects:
the invention provides a queuing and number calling guiding system based on an Internet platform, which eliminates the adverse effect that a clustering result does not contain user data characteristics by constructing self-adaptive weights in a clustering process according to the user data characteristics and improves the accuracy of the queuing and number calling guiding result. Firstly, in order to enable the cluster obtained subsequently to have the user characteristics, reservation time information of all users to be queued in a preset time period needs to be obtained, and meanwhile, the cluster is beneficial to increasing and enriching the data characteristics of the users to be queued; secondly, in order not to erase the information characteristics of the users, the weights of different users in the time dimension are required to be analyzed, namely, the time weight of each user to be queued is determined by analyzing the service time abnormal characteristics of the users to be queued; then, in order to enable the service time to be contained in the guide time, screening out target users to be queued with longer service duration by utilizing time weights, and taking the target users to be queued as a trunk part for determining the cluster center, which is helpful for providing more optimal queuing guide; then, in order to obtain a more objective clustering result, analyzing the time distribution characteristics of the target users to be queued, and determining the service weight of each target user to be queued; in addition, the contribution degree of each target user to be queued is determined through the fusion characteristics of the service weight and the time weight of each target user to be queued, and the two angles of weights are combined to obtain the contribution degree with high reliability and higher accuracy; and finally, taking the contribution degree of each target user to be queued as a weight in the determination process of the cluster center, obtaining each cluster through clustering, and queuing and calling each user to be queued in each cluster, wherein each cluster is provided with user characteristic information, the accuracy in queuing and calling the user based on a clustering result is higher, the flow of people when the user is queuing is less, and the time for waiting for service of the user is shortened.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the execution of the queuing and number calling guide system based on the Internet platform;
Fig. 2 is a schematic diagram of a distribution of sample points on a coordinate system according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following detailed description is given below of the specific implementation, structure, features and effects of the technical solution according to the present invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The specific scene aimed by the invention is as follows:
On the premise of a large number of users, the ISODATA algorithm is used for clustering the user data, different user characteristic information is easily classified in the clustering process, so that the clustering result loses the characteristic information of the user data, namely the clustering result does not have the user characteristic, and further errors are generated in guiding the queuing result.
The embodiment provides a queuing and number calling guiding system based on an internet platform, which comprises a memory and a processor, wherein the processor executes a computer program stored in the memory to realize the following steps:
Acquiring reservation time information of all users to be queued in a preset time period, wherein the reservation time information comprises service start time and service end time;
Analyzing the abnormal service time characteristics of the users to be queued according to the service start time and the service end time of each user to be queued, and determining the time weight of each user to be queued; selecting all target users to be queued according to the time weight of each user to be queued;
Analyzing the time distribution characteristics of the target users to be queued according to the service start time and the service end time of each target user to be queued, and determining the service weight of each target user to be queued; determining the contribution degree of each target user to be queued according to the fusion characteristics of the service weight and the time weight of each target user to be queued;
clustering is carried out on all the users to be queued, and the contribution degree of each target user to be queued is used as the weight in the process of determining the cluster center, so that each cluster is obtained; and queuing and number calling guiding is carried out on each user to be queued in each cluster.
The following detailed development of each step is performed:
referring to fig. 1, there is shown an execution flow chart of a queuing and number calling guide system based on an internet platform, which comprises the following steps:
S1, acquiring reservation time information of all users to be queued in a preset time period.
It should be noted that, the user information is mainly represented by a service stage and a service type, and different service types will affect the time used by the service, so the factors that mainly affect the queuing guiding result are the start time and the end time corresponding to the service, and the service duration may be the difference between the end time and the start time. According to the embodiment, the reservation time information of all the users to be queued is acquired, and the information features of different users to be queued are integrated to perform clustering.
In this embodiment, the preset time period is set as one day, the one day is taken as one period, and reservation time information of all users to be queued in the current day is counted, wherein the reservation time information includes service start time and service end time, and the reservation time information is time information data filled in when the users to be queued reserve the service. Of course, the implementer may also use reservation information of other dimensions of the users to be queued to perform the subsequent steps. After obtaining the service start time and the service end time of each user to be queued, denoising all obtained time data by using a median filtering method to obtain the reserved time information after denoising, and performing clustering analysis on the basis of the reserved time information after denoising in the subsequent steps. The implementation process of the median filtering method is the prior art, and is not in the scope of the present invention, and will not be described in detail here.
It is worth noting that the main purpose of acquiring the reservation time information is to cluster all users to be queued based on the reservation time information of each user to be queued, and provide a corresponding service time period of the user to be queued for each user to be queued according to the clustering result, wherein the owned people in the service time period of the user have less flow, namely the users to be queued are sparse, and the users do not need to wait for a long time.
Thus far, the present embodiment obtains the reservation time information after the preprocessing.
S2, analyzing the abnormal service time characteristics of the users to be queued according to the reservation time information of each user to be queued so as to select all target users to be queued.
The first step is to analyze the abnormal characteristics of service time of the users to be queued according to the service start time and the service end time of each user to be queued, and determine the time weight of each user to be queued.
It should be noted that, in order not to erase the information features of the users to be queued in the clustering process, the weights of different users in the time dimension need to be analyzed, the weights in the time dimension can be characterized as service duration, and if the longer the service duration of a certain service class is, the higher the duty ratio of the service class in the clustering process is, the higher the corresponding time weight of the user of the service class is; conversely, the shorter the service duration, the smaller its duty cycle in constructing a cluster should be. The shorter the service duration, the greater the likelihood that the corresponding reservation time information of the user to be queued is anomalous data.
It should also be noted that the reason why the weight is higher for a longer service duration is that: for users to be queued with a longer service duration, the service duration needs to be taken as the backbone part for determining the cluster center in order for the service duration to contain the lead time. By quantifying the contribution degree of each user to be queued with longer service duration in constructing the cluster center, the clustering result obtained at this time is spread around the users to be queued with longer service duration, so as to provide better guiding time for each user to be queued.
In order to eliminate partial abnormal data users and amplify the characteristics of the users in the time dimension, the time weight is required to be determined by analyzing the abnormal characteristics of the service time consumption, and the time weight not only can amplify the characteristic information of the users, but also can avoid the influence of the abnormal data on the cluster center to a certain extent.
The first substep builds a coordinate system and determines a target line on the coordinate system.
Constructing a coordinate system by taking the service start time as a horizontal axis and the service end time as a vertical axis; mapping each user to be queued onto a coordinate system based on the service start time and the service end time of each user to be queued, and obtaining each sample point on the coordinate system; the angular bisector of the first quadrant determined on the coordinate system is the target straight line.
In this embodiment, a single user to be queued may be represented as a sample point on the coordinate system; the function corresponding to the target straight line may be e=s (t), and since the service end time of the user is longer than the service start time, the sample points on the coordinate system are all distributed on the upper half of the target straight line y=x, and the distribution diagram of the sample points on the coordinate system is shown in fig. 2, the horizontal axis is denoted as s (t), and the vertical axis is denoted as e (t).
It should be noted that, the coordinate system is established to facilitate the subsequent global analysis of all the users to be queued, measure the distance between each sample point and the target straight line, i.e. the boundary distance, and determine the time weight.
A second sub-step of, for any sample point on the coordinate system, determining the distance between the sample point and the target straight line, and determining the difference between the ordinate and abscissa values of the sample point.
In this embodiment, as for the distance between the sample point and the target straight line, the normal service duration is not too low in terms of service logic, so the closer the sample point is to the target straight line, the greater the degree of abnormality of the sample point. The degree of the sample point approaching to the target straight line can be quantified as the difference between the service start time and the service end time, the larger the difference is, the smaller the characterization abnormality degree is, the larger the obtained time weight is, and the larger the weight of the subsequent corresponding sample point when participating in the cluster center determining process is;
For the difference between the ordinate and abscissa values, the intersection with the target straight line e=s (t) when the sample point is perpendicular to the horizontal axis, the distance between the sample point and the intersection may be taken as the service duration, i.e., the difference between the ordinate and abscissa values. The larger the service duration, the larger the time weight of the sample points, because the larger the time span of the service time weight, in order to facilitate the accurate time guidance through clustering, the larger the corresponding sample points need to occupy in the clustering process, so as to preserve the reservation time information characteristics of the users to be queued.
And a third sub-step of determining the time weight of the user to be queued corresponding to the sample point according to the distance between the sample point and the target straight line and the difference between the ordinate value and the abscissa value of the sample point.
As an example, the calculation formula of the time weight of the user to be queued corresponding to the sample point may be:
wherein T (i) is the time weight of the user to be queued corresponding to the ith sample point, norm is a linear normalization function, alpha is a first preset parameter weight, |is an absolute value function, s (i) is the abscissa value of the ith sample point, e (i) is the ordinate value of the ith sample point,/> For the distance between the i-th sample point and the target straight line, arctan is an arctangent function, and [ e (i) -s (i) ] is the difference between the ordinate and abscissa values of the i-th sample point.
In the calculation formula of the time weight, a first preset parameter weight alpha can be used for distinguishing and amplifying two different types of distances, can be set to be 0.4, can be set by an implementer according to specific actual conditions, and is not particularly limited; Can be used to characterize the extent to which the ith sample point is close to the target line, obtained by calculation of the existing point-to-line distance formula,/> The larger the sample point is, the closer to the target straight line is, and the larger the time weight of the user to be queued is; e (i) -s (i) can be used to characterize service duration, the larger e (i) -s (i) the longer the service duration of the user to be queued, the greater the time weight; the arctan function arctan can realize normalization and normalize independent variables in the function to form angles; the linear normalization function norm can limit the value range of the time weight between 0 and 1, and the closer the normalized value is to 1, the larger the time weight of the corresponding sample point is; and referring to the calculation process of the time weights of the users to be queued corresponding to the ith sample point, the time weight of each user to be queued can be obtained, and each user to be queued has the corresponding time weight.
And secondly, selecting all target users to be queued according to the time weight of each user to be queued.
And comparing the time weight of each user to be queued with a preset weight threshold, and taking the user to be queued with the time weight greater than the preset weight threshold as a target user to be queued.
In this embodiment, the preset weight threshold is set to 0.5, and the practitioner may set the preset weight threshold according to a specific practical situation, which is not limited herein. Comparing the time weight of each user to be queued with a preset weight threshold value of 0.5, and taking the user to be queued as a selected target user to be queued if the time weight of any user to be queued is greater than 0.5; if the time weight of the user to be queued is not more than 0.5, the user to be queued is taken as an abnormal user and does not participate in the calculation in the process of generating the cluster center by ISODATA.
Thus, in this embodiment, the boundary distance of each sample point on the coordinate system is analyzed, and the target users to be queued that can be used for determining the cluster center are selected from all the users to be queued.
And S3, analyzing the time distribution characteristics of the target users to be queued according to the reservation time information of each target user to be queued, and obtaining the contribution degree of each target user to be queued.
The first step, analyzing the time distribution characteristics of the target users to be queued according to the service start time and the service end time of each target user to be queued, and determining the service weight of each target user to be queued.
After eliminating the influence of the abnormal sample points on the cluster center, the selected target users to be queued need to quantify the importance degree based on the time distribution characteristics to further determine the service weight in order to obtain more objective clustering results. The service weight is determined in order to further consider the influence of the feature information of the target to-be-queued users with higher service time weight degree on the cluster center selection, namely, the influence of the feature points of the isolated points in the target sample points after the abnormal sample points on the cluster center selection is eliminated, wherein the target sample points refer to sample points with time weight greater than a preset weight threshold value of 0.5 on a coordinate system.
The queuing guidance is to recommend service time for sample points with similar characteristics, the acquisition mode of the sample points with similar characteristics is based on a clustering result, the clustering result needs to contain characteristic information of single sample points, and the sample points in the same local area have similar characteristics and have the same service time requirement. Thus, the greater the service weight of sample points located in the same local region when constructing a cluster center.
Dividing the coordinate system into a preset number of areas, and determining the service weight of the target users to be queued corresponding to each target sample point according to the distribution condition of each target sample point in the coordinate system in the areas. The target sample point is a sample point formed by the service start time and the service end time of the target user to be queued.
In this embodiment, the coordinate system is divided into regions in the transverse direction and then divided into regions in the longitudinal direction, so that the coordinate system is divided into regions in the transverse direction, the number of the transverse regions is 100 in the transverse direction, and the number of the longitudinal regions is 100 in the longitudinal direction, so that the number of the regions corresponding to the coordinate system is 100×100. The number of the areas may be set by the practitioner according to the specific actual situation, and is not particularly limited herein. The coordinate system is divided into various areas by bisecting, so as to analyze the distribution condition of the target sample points in the areas with different positions, the number of the target sample points in the areas with different positions is different, and the compactness of the sample points in the areas is different.
It is worth to say that, for a plurality of target sample points, the user service time is only reflected by transverse division, and the weight of all the target sample points after transverse division is greater than that after longitudinal division; in addition, the number of target sample points in actual situations is huge, so the number of sample points in one area block is not the number of sample points marked on the coordinate system.
According to the distribution condition of each target sample point in the region on the coordinate system, determining the service weight of the target user to be queued corresponding to each target sample point, wherein the specific implementation steps comprise:
and a first substep, marking any one target sample point as a selected target sample point, and respectively selecting a preset number of adjacent areas in the transverse direction and the longitudinal direction of the area where the selected target sample point belongs. The preset number of adjacent areas are a plurality of areas nearest to the area to which the selected target sample point belongs.
In this embodiment, for convenience of description, an arbitrary target sample point is selected from all target sample points as an example, and the arbitrary target sample point is denoted as a selected target sample point. In addition, in order to facilitate the subsequent calculation of the service weight of the selected target sample point, 10 regions closest to the region to which the selected target sample point belongs are selected as adjacent regions in the lateral direction, and 10 regions closest to the region to which the selected target sample point belongs are selected as adjacent regions in the longitudinal direction.
It should be noted that, the above-mentioned lateral and longitudinal directions are the lateral area and the longitudinal area where the selected target sample point belongs is located, and the number of adjacent areas selected laterally and longitudinally may be set by the practitioner according to specific practical situations, which is not specifically limited herein.
And a second sub-step of determining the service weight of the target user to be queued corresponding to the selected target sample point according to the number of the target sample points in the area to which the selected target sample point belongs, the number of the target sample points in the adjacent areas corresponding to the preset number of the area to which the selected target sample point belongs in the transverse direction and the longitudinal direction, and the number of the target sample points in the target area. The target area is the area with the largest number of target sample points on the coordinate system.
As an example, the calculation formula of the service weight of the target user to be queued may be:
Wherein Z j is the service weight of the target user to be queued corresponding to the jth target sample point, Q max is the number of target sample points in the target area, Q j is the number of target sample points in the area to which the jth target sample point belongs, Q1 j,c is the number of target sample points in the C-th adjacent area corresponding to the transverse direction of the area to which the jth target sample point belongs, Q2 j,c is the number of target sample points in the C-th adjacent area corresponding to the longitudinal direction of the area to which the jth target sample point belongs, C is the number of adjacent areas of the area to which the jth target sample point belongs, namely the preset number, beta is the preset super parameter, I is the absolute value function, and norm is the linear normalization function.
In a service weight calculation formula, service weights of target sample points in the same area are the same; the I Q1 j,c-Qj can represent the transverse compactness difference between the region of the jth target sample point in the transverse direction and other regions, and the larger the transverse compactness difference is, the more discrete the transverse target sample point number distribution of the region of the jth target sample point is, and the worse the regularity is; because the arrival time of the target sample point with poor regularity is discrete, the target sample point should not be divided into the same class of clusters, so the service weight of the jth target sample point should be low. The I Q2 j,c-Qj can represent the longitudinal compactness difference between the region to which the jth target sample point belongs in the longitudinal direction and other regions, and the smaller the longitudinal compactness difference is, the more compact the longitudinal target sample point number distribution of the region to which the jth target sample point belongs is, the more concentrated the distribution is, and the stronger the regularity is; because the arrival time of the target sample points with stronger regularity is more concentrated and the service duration time with the same requirement is needed, the target sample points should be divided into the same class of clusters, so the service weight of the jth target sample point should be higher; q max-Qj may represent the difference between the maximum target sample point and the number of target sample points in the region to which the jth target sample point belongs, the smaller the difference, which indicates that the region to which the jth target sample point belongs is closer to the denser target sample point distribution feature. The preset super parameter beta is used for preventing the special case that the denominator is zero, and can be set to be 0.1; and referring to the calculation process of the service weight of the target user to be queued corresponding to the jth target sample point, the service weight of the target user to be queued corresponding to each target sample point can be obtained.
It should be noted that, for the target sample points located on the same boundary of two adjacent areas, the target sample points may belong to two corresponding adjacent areas together, that is, when the number of the target sample points in the two adjacent areas is counted, the target sample points located on the same boundary may be counted on the two adjacent areas. For example, there are 3 target sample points on the same boundary of two adjacent regions a and b, and the 3 target sample points at this time belong to both region a and region b.
And secondly, determining the contribution degree of each target user to be queued according to the fusion characteristics of the service weight and the time weight of each target user to be queued.
Setting a second preset parameter weight for any target user to be queued, and calculating the product of the second preset parameter weight and the time weight of the target user to be queued as a first product; taking the difference value between the 1 and the second preset parameter weight as a third preset parameter weight, and calculating the product of the third preset parameter weight and the service weight of the target user to be queued as a second product; and taking the value obtained by adding the first product and the second product as the contribution degree of the target user to be queued.
As an example, the calculation formula of the contribution degree of the target user to be queued may be:
Cov (j) = (1-epsilon) Z j +epsilon T (j); wherein Cov (j) is the contribution degree of the target user to be queued corresponding to the jth target sample point, epsilon is a second preset parameter weight, 1-epsilon is 1-epsilon, Z j is the service weight of the target user to be queued corresponding to the jth target sample point, (1-epsilon) Z j is a second product, T (j) is the time weight of the target user to be queued corresponding to the jth target sample point, and epsilon T (j) is a first product.
In the calculation formula of the contribution degree, the second preset parameter weight epsilon is set to be 0.4, and an implementer can set the size of the second preset parameter weight according to specific practical conditions, so that the calculation formula is not particularly limited; and referring to the contribution degree of the target to-be-queued user corresponding to the jth target sample point, the contribution degree of the target to-be-queued user corresponding to each target sample point can be obtained. When the contribution degree is calculated, not only the time weight determined by the abnormal feature of the service time consumption is considered, but also the service weight determined by the time distribution feature is considered, so that the comprehensiveness and accuracy of the calculated contribution degree are effectively improved, and the cluster with the user feature information can be obtained conveniently.
So far, the embodiment determines the service weight of each target user to be queued by analyzing the time distribution characteristics of the target users to be queued, and further fuses the time weight and the service weight to obtain the contribution degree which is convenient for the subsequent determination of the cluster center.
S4, clustering is carried out on all the users to be queued, and the contribution degree of each target user to be queued is used as the weight in the process of determining the cluster center, so that each cluster is obtained; and queuing and number calling guiding is carried out on each user to be queued in each cluster.
The first step, clustering is carried out on all users to be queued, and the contribution degree of each target user to be queued is used as the weight in the process of determining the cluster center, so that each cluster is obtained.
In this embodiment, an ISODATA clustering algorithm is utilized to perform clustering processing on all users to be queued, only each target sample point is considered when determining a cluster center in the clustering processing, and the contribution degree corresponding to each target sample point is used as a weight, that is, the weight of each target sample point when participating in obtaining the cluster center is used as the corresponding contribution degree, so as to obtain each cluster center, and further obtain each cluster based on each cluster center. The implementation process of the ISODATA clustering algorithm is the prior art, and is not within the scope of the present invention, and will not be described in detail herein.
And secondly, queuing and number calling guiding is carried out on each user to be queued in each cluster.
And determining a service time period corresponding to each user to be queued in each cluster by utilizing an Internet platform according to the user characteristic information of each cluster, and pushing the service time period to the corresponding user to be queued.
In this embodiment, different sample points are divided into different clusters, and the clusters contain information features of users. Each cluster is a group, for the number of sample points and the group to which the sample points belong, the guiding time of the individual sample points is the same as the group, but different groups correspond to different queuing number calling guiding times, a corresponding user service time period can be provided for different groups, the flow of people in the user service time period is less, and the users to be queued are sparse. For example, a certain user to be queued reserves 10:00 am to 11:00 am, the required service duration is 20 minutes, the service time period of the cluster to which the user to be queued belongs is 10:20 to 10:40, and the service of the user to be queued is the optimal time period from 10:20 to 10:40.
It should be noted that, the process of setting the appropriate service period for each cluster is prior art, for example, window analysis in time series cluster, which is not included in the protection scope of the present invention, and will not be described herein. The number of users to be queued in each cluster has a certain upper limit, and normal users to be queued cannot be jammed in the service time period corresponding to the cluster.
This embodiment ends.
The invention provides a queuing and number calling guiding system based on an Internet platform, which is used for determining time weight and service weight by analyzing preset time information characteristics of all users to be queued so as to obtain contribution degree with fusion characteristics; based on the contribution degree of the target users to be queued, determining each clustering center of all the users to be queued in the clustering process to obtain a clustering cluster with user characteristic information, which is beneficial to improving the accuracy of queuing and calling guidance and avoiding errors of the guiding queuing results of the users.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention and are intended to be included within the scope of the invention.

Claims (2)

1. The queuing and number calling guide system based on the Internet platform is characterized by comprising a memory and a processor, wherein the processor executes a computer program stored in the memory to realize the following steps:
Acquiring reservation time information of all users to be queued in a preset time period, wherein the reservation time information comprises service start time and service end time;
Analyzing the abnormal service time characteristics of the users to be queued according to the service start time and the service end time of each user to be queued, and determining the time weight of each user to be queued; selecting all target users to be queued according to the time weight of each user to be queued;
Analyzing the time distribution characteristics of the target users to be queued according to the service start time and the service end time of each target user to be queued, and determining the service weight of each target user to be queued; determining the contribution degree of each target user to be queued according to the fusion characteristics of the service weight and the time weight of each target user to be queued;
clustering is carried out on all the users to be queued, and the contribution degree of each target user to be queued is used as the weight in the process of determining the cluster center, so that each cluster is obtained; queuing and number calling guiding is carried out on each user to be queued in each cluster;
analyzing the abnormal service time characteristics of the users to be queued according to the service start time and the service end time of each user to be queued, and determining the time weight of each user to be queued, including:
constructing a coordinate system by taking the service start time as a horizontal axis and the service end time as a vertical axis; mapping each user to be queued onto a coordinate system based on the service start time and the service end time of each user to be queued, and obtaining each sample point on the coordinate system; the angular bisector of the first quadrant determined on the coordinate system is a target straight line;
For any sample point on the coordinate system, determining the distance between the sample point and the target straight line, and determining the difference between the ordinate value and the abscissa value of the sample point; determining the time weight of the user to be queued corresponding to the sample point according to the distance between the sample point and the target straight line and the difference between the longitudinal coordinate value and the horizontal coordinate value of the sample point;
The calculation formula of the time weight is as follows:
wherein T (i) is the time weight of the user to be queued corresponding to the ith sample point, norm is a linear normalization function, alpha is a first preset parameter weight, |is an absolute value function, s (i) is the abscissa value of the ith sample point, e (i) is the ordinate value of the ith sample point,/> Arctan is an arctangent function for the distance between the i-th sample point and the target straight line, and [ e (i) -s (i) ] is the difference between the ordinate and abscissa values of the i-th sample point;
selecting all target users to be queued according to the time weight of each user to be queued, including:
Comparing the time weight of each user to be queued with a preset weight threshold, and taking the user to be queued with the time weight greater than the preset weight threshold as a target user to be queued;
Analyzing the time distribution characteristics of the target users to be queued according to the service start time and the service end time of each target user to be queued, and determining the service weight of each target user to be queued, including:
Dividing the coordinate system into a preset number of areas, and determining the service weight of the target users to be queued corresponding to each target sample point according to the distribution condition of each target sample point in the coordinate system in the areas; the target sample point is a sample point formed by the service start time and the service end time of the target user to be queued;
According to the distribution condition of each target sample point in the region on the coordinate system, determining the service weight of the target user to be queued corresponding to each target sample point comprises the following steps:
marking any one target sample point as a selected target sample point, and respectively selecting a preset number of adjacent areas in the transverse direction and the longitudinal direction of the area where the selected target sample point belongs;
Determining the service weight of a target user to be queued corresponding to the selected target sample point according to the number of the target sample points in the area to which the selected target sample point belongs, the number of the target sample points in the adjacent areas corresponding to the transverse and longitudinal directions of the area to which the selected target sample point belongs and the number of the target sample points in the target area;
The target area is the area with the largest number of target sample points on the coordinate system, and the preset number of adjacent areas are a plurality of areas closest to the area where the selected target sample points belong;
The calculation formula of the service weight of the target user to be queued corresponding to the selected target sample point is as follows:
Wherein Z j is the service weight of a target user to be queued corresponding to the jth target sample point, Q max is the number of target sample points in a target area, Q j is the number of target sample points in the area to which the jth target sample point belongs, Q1 j,c is the number of target sample points in the C-th adjacent area corresponding to the transverse direction of the area to which the jth target sample point belongs, Q2 j,c is the number of target sample points in the C-th adjacent area corresponding to the longitudinal direction of the area to which the jth target sample point belongs, C is the number of adjacent areas of the area to which the jth target sample point belongs, namely the preset number, beta is the preset super parameter, I is an absolute value function, and norm is a linear normalization function;
determining the contribution degree of each target user to be queued according to the fusion characteristics of the service weight and the time weight of each target user to be queued, comprising:
Setting a second preset parameter weight for any target user to be queued, and calculating the product of the second preset parameter weight and the time weight of the target user to be queued as a first product; taking the difference value between the 1 and the second preset parameter weight as a third preset parameter weight, and calculating the product of the third preset parameter weight and the service weight of the target user to be queued as a second product; and taking the value obtained by adding the first product and the second product as the contribution degree of the target user to be queued.
2. The internet platform-based queuing and number guiding system as set forth in claim 1, wherein queuing and number guiding is performed for each user to be queued in each cluster, comprising:
and determining a service time period corresponding to each user to be queued in each cluster by utilizing an Internet platform according to the user characteristic information of each cluster, and pushing the service time period to the corresponding user to be queued.
CN202311545492.8A 2023-11-20 2023-11-20 Queuing and number calling guiding system based on Internet platform Active CN117576822B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311545492.8A CN117576822B (en) 2023-11-20 2023-11-20 Queuing and number calling guiding system based on Internet platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311545492.8A CN117576822B (en) 2023-11-20 2023-11-20 Queuing and number calling guiding system based on Internet platform

Publications (2)

Publication Number Publication Date
CN117576822A CN117576822A (en) 2024-02-20
CN117576822B true CN117576822B (en) 2024-04-30

Family

ID=89860112

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311545492.8A Active CN117576822B (en) 2023-11-20 2023-11-20 Queuing and number calling guiding system based on Internet platform

Country Status (1)

Country Link
CN (1) CN117576822B (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107153819A (en) * 2017-05-05 2017-09-12 中国科学院上海高等研究院 A kind of queue length automatic testing method and queue length control method
CN113012336A (en) * 2021-03-30 2021-06-22 中信银行股份有限公司 Queuing reservation method of banking business and device, storage medium and equipment thereof
CN114118496A (en) * 2021-11-30 2022-03-01 四川恒升信达科技有限公司 Method and system for automatically scheduling queuing reservation based on big data analysis
CN114581130A (en) * 2022-03-02 2022-06-03 中国工商银行股份有限公司 Bank website number assigning method and device based on customer portrait and storage medium
CN115423019A (en) * 2022-09-01 2022-12-02 西安电子科技大学 Fuzzy clustering method and device based on density
WO2023050779A1 (en) * 2021-09-29 2023-04-06 康键信息技术（深圳）有限公司 Quantity analysis method and apparatus for reservation service, device and storage medium
CN116244609A (en) * 2022-12-29 2023-06-09 深圳云天励飞技术股份有限公司 Passenger flow volume statistics method and device, computer equipment and storage medium
US11775344B1 (en) * 2020-12-04 2023-10-03 Inspur Suzhou Intelligent Technology Co., Ltd. Training task queuing cause analysis method and system, device and medium
CN116934060A (en) * 2023-09-18 2023-10-24 北京融威众邦科技股份有限公司 Hospital call intelligent queuing method and system

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107153819A (en) * 2017-05-05 2017-09-12 中国科学院上海高等研究院 A kind of queue length automatic testing method and queue length control method
US11775344B1 (en) * 2020-12-04 2023-10-03 Inspur Suzhou Intelligent Technology Co., Ltd. Training task queuing cause analysis method and system, device and medium
CN113012336A (en) * 2021-03-30 2021-06-22 中信银行股份有限公司 Queuing reservation method of banking business and device, storage medium and equipment thereof
WO2023050779A1 (en) * 2021-09-29 2023-04-06 康键信息技术（深圳）有限公司 Quantity analysis method and apparatus for reservation service, device and storage medium
CN114118496A (en) * 2021-11-30 2022-03-01 四川恒升信达科技有限公司 Method and system for automatically scheduling queuing reservation based on big data analysis
CN114581130A (en) * 2022-03-02 2022-06-03 中国工商银行股份有限公司 Bank website number assigning method and device based on customer portrait and storage medium
CN115423019A (en) * 2022-09-01 2022-12-02 西安电子科技大学 Fuzzy clustering method and device based on density
CN116244609A (en) * 2022-12-29 2023-06-09 深圳云天励飞技术股份有限公司 Passenger flow volume statistics method and device, computer equipment and storage medium
CN116934060A (en) * 2023-09-18 2023-10-24 北京融威众邦科技股份有限公司 Hospital call intelligent queuing method and system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
医院门诊分时段全预约系统的设计与实现;赵芮;中国优秀硕士学位论文全文库;20230215;全文 *

Also Published As

Publication number Publication date
CN117576822A (en) 2024-02-20

Similar Documents

Publication Publication Date Title
WO2019233189A1 (en) Method for detecting sensor network abnormal data
WO2021012930A1 (en) Voting node configuration method and system
CN108009972B (en) Multi-mode travel O-D demand estimation method based on multi-source data check
CN106067034B (en) Power distribution network load curve clustering method based on high-dimensional matrix characteristic root
CN116418882B (en) Memory data compression method based on HPLC dual-mode carrier communication
CN113033110B (en) Important area personnel emergency evacuation system and method based on traffic flow model
CN106507406A (en) A kind of equipment of wireless network accesses the Forecasting Methodology of number and equipment
CN110598775A (en) Prediction method, system and storage medium based on fuzzy clustering and BP neural network
CN117576822B (en) Queuing and number calling guiding system based on Internet platform
CN117454671A (en) Artificial intelligence-based field effect transistor life assessment method
CN114912720A (en) Memory network-based power load prediction method, device, terminal and storage medium
CN117575684B (en) Passenger flow volume prediction method and system
CN109065176A (en) A kind of blood glucose prediction method, device, terminal and storage medium
Chen et al. Determining simulation run length with the runs test
CN108802845B (en) A kind of indoor occupant occupation rate estimation method based on infrared sensor array
CN116468138A (en) Air conditioner load prediction method, system, electronic equipment and computer storage medium
CN108109675B (en) Laboratory quality control data management system
CN115153476A (en) Sleep evaluation method and device based on multi-dimensional data, electronic equipment and medium
CN112016971B (en) Mobile crowd sensing data reliability guarantee method based on Etheng GAS principle
CN110705924B (en) Wind measuring data processing method and device of wind measuring tower based on wind direction sector
CN112784785A (en) Multi-sample fitting image sharpening processing method
CN107979818B (en) Method for processing initial data of wireless fingerprint database
CN111582379A (en) Intelligent layering method and system for rock and soil layers based on clustering algorithm
CN117331705B (en) Data prediction analysis method and system based on big data
CN116843368B (en) Marketing data processing method based on ARMA model

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