CN115081766A - Work order scheduling method and system - Google Patents
Work order scheduling method and system Download PDFInfo
- Publication number
- CN115081766A CN115081766A CN202110261227.1A CN202110261227A CN115081766A CN 115081766 A CN115081766 A CN 115081766A CN 202110261227 A CN202110261227 A CN 202110261227A CN 115081766 A CN115081766 A CN 115081766A
- Authority
- CN
- China
- Prior art keywords
- maintenance
- assembly
- maintenance personnel
- work order
- satisfaction
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a work order scheduling method and a work order scheduling system, wherein the method comprises the following steps: obtaining key influence factors according to historical work data of assembly and maintenance personnel in the target area and a customer satisfaction influence key factor model; obtaining a satisfaction recommendation index of the maintenance personnel according to the key influence factors; acquiring an efficiency recommendation index of the maintenance personnel according to the historical maintenance efficiency working data and the maintenance efficiency model of the maintenance personnel; acquiring a comprehensive recommendation index of the maintenance personnel according to the satisfaction recommendation index and the effectiveness recommendation index; and distributing the assembly and maintenance orders to be distributed to the assembly and maintenance personnel according to the comprehensive recommendation index. The invention takes customer satisfaction improvement as the leading factor, excavates key factors influencing customer satisfaction, combines maintenance efficiency data and customizes work order scheduling strategies according to regions, and selects optimal maintenance personnel for the maintenance work order to carry out home construction.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a work order scheduling method and system.
Background
The intelligent work order scheduling method aims to select the optimal maintenance personnel for the maintenance work order to carry out home construction through centralized scheduling of the work order scheduling center so as to reduce the situations that the work order scheduling is unreasonable, manual work is required to be dispatched, the installation is not timely and the work order scheduling efficiency is low.
According to the existing technical scheme, a scheduling center selects a residual capacity value to meet the workload of a new assembly maintenance work order and dispatches the new assembly maintenance work order to an assembly maintenance worker closest to the workload according to the residual capacity value of the assembly maintenance worker and the distance between the current position of the assembly maintenance worker and the new assembly maintenance position. However, the scheduling strategy is only suitable for the scenes of real-time order receiving and distribution, the scenes are few in actual production, and most of the scenes adopt a mode of reserving in advance and installing and maintaining. Because the dispatch rule of the existing scheme is based on the capability value and the assembly and maintenance position of the assembly and maintenance personnel, the following problems can exist: the distributed installation and maintenance address does not belong to the administration range of the installation and maintenance personnel, the installation and maintenance personnel need to manually dispatch the work order for the unreasonable installation and maintenance work order, and when the installation and maintenance personnel are in construction or on vacation, the condition of work order overstock is caused when the work order is not dispatched in time; the work order scheduling rule is dominated by assembly and maintenance personnel, other factors influencing customer satisfaction are not fully considered, and the customer satisfaction is possibly reduced.
The work order scheduling of the existing scheme is mainly from the perspective of assembly and maintenance personnel, and factors influencing customer satisfaction are not considered. The work order scheduling rule is based on the remaining capacity value of the assembly and maintenance personnel and the position of a new assembly and maintenance, but when a customer issues an assembly and maintenance work order, the customer often reserves the construction time of the next several days, and the assembly and maintenance position, the road and the weather condition at the time are unpredictable. The assignment of servicemen without considering the customer satisfaction factor does not improve the customer satisfaction as much as possible.
Disclosure of Invention
The invention provides a work order scheduling method and a work order scheduling system, which are used for solving the defect of low customer satisfaction in the prior art and achieving the purpose of improving the customer satisfaction.
The invention provides a work order scheduling method, which comprises the following steps:
obtaining key influence factors according to historical working data of maintenance personnel in a target area and a customer satisfaction degree key factor model, wherein the customer satisfaction degree key factor model is obtained by training with the historical working data of the maintenance personnel in the target area as a sample and the customer satisfaction degree as a label, and the target area is an area where a maintenance order is to be distributed;
obtaining a satisfaction recommendation index of the maintenance personnel according to the key influence factors;
acquiring an efficiency recommendation index of the maintenance personnel according to the historical maintenance efficiency working data and a maintenance efficiency model of the maintenance personnel, wherein the maintenance efficiency model is obtained by training by taking the historical maintenance efficiency working data of the maintenance personnel as a sample and taking a maintenance efficiency index as a label;
acquiring a comprehensive recommendation index of the maintenance personnel according to the satisfaction recommendation index and the effectiveness recommendation index;
and distributing the assembly and maintenance orders to be distributed to assembly and maintenance personnel according to the comprehensive recommendation index.
The work order scheduling method provided by the invention further comprises the following steps:
and after the dispatching of the to-be-distributed assembly and maintenance order is finished, updating the work order amount and scheduling information of the assembly and maintenance personnel to obtain the assembly and maintenance capability value of the assembly and maintenance personnel again, wherein the assembly and maintenance capability value is one of the historical assembly and maintenance efficiency working data.
The work order scheduling method provided by the invention further comprises the following steps:
and after the dispatching of the assembly and maintenance order to be distributed is finished, updating the historical working data of the assembly and maintenance personnel so as to update the customer satisfaction influence key factor model.
According to the work order scheduling method provided by the invention, the customer satisfaction degree key influence factor model is obtained by training by taking historical work data of maintenance personnel in the target area as a sample and taking customer satisfaction degree as a label, and comprises the following steps:
and modeling and training historical working data of the maintenance personnel based on a multi-factor ANOVA (analysis of variance) method to obtain a key influence factor model of the customer satisfaction.
According to the work order scheduling method provided by the invention, the step of obtaining the comprehensive recommendation index of the maintenance personnel according to the satisfaction recommendation index and the effectiveness recommendation index comprises the following steps:
f(P,T)＝C 1 ·g(X(P,T))+C 2 ·h(Y(P，T))；
wherein P represents the comprehensive recommendation index, T represents a work order, C 1 Weight coefficient, C, representing satisfaction recommendation index 2 A weight coefficient representing a performance recommendation index, g represents a satisfaction index function, h represents a performance index function, X (P, T) represents the satisfaction recommendation index, and Y (P, T) represents the performance recommendation index.
According to the work order scheduling method provided by the invention, the satisfaction index function and the efficiency index function are obtained by applying the following formulas:
wherein i represents a reference number, n represents the number of all key influencing factors, x i Denotes the ith key influencing factor, alpha i Weight, y, representing the ith key influencing factor i Denotes the ith performance index, beta i Represents the weight of the ith performance indicator.
According to the work order scheduling method provided by the invention, the satisfaction index function and/or the efficiency index function are/is determined according to the target area.
The invention also provides a work order scheduling system, comprising:
the key influence factor screening module is used for obtaining key influence factors according to historical working data of maintenance personnel in a target area and a customer satisfaction influence key factor model, wherein the customer satisfaction key influence factor model is obtained by training with the historical working data of the maintenance personnel in the target area as a sample and the customer satisfaction as a label, and the target area is an area where a maintenance order to be distributed is located;
the satisfaction index calculation module is used for acquiring a satisfaction recommendation index of the maintenance personnel according to the key influence factors;
the efficiency index calculation module is used for obtaining an efficiency recommendation index of the maintenance personnel according to the historical assembly and maintenance efficiency working data of the maintenance personnel and an assembly and maintenance efficiency model, wherein the assembly and maintenance efficiency model is obtained by training by taking the historical assembly and maintenance efficiency working data of the maintenance personnel as a sample and taking the assembly and maintenance efficiency index as a label;
the comprehensive recommendation index calculation module is used for acquiring a comprehensive recommendation index of the maintenance personnel according to the satisfaction recommendation index and the effectiveness recommendation index;
and the order distribution module is used for distributing the assembly and maintenance orders to be distributed to the assembly and maintenance personnel according to the comprehensive recommendation index.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of any of the work order scheduling methods.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the work order scheduling method as described in any of the above.
The invention provides a work order scheduling method and system, and provides a method and system for carrying out intelligent work order scheduling based on key factors of satisfaction degree aiming at the problems that work order distribution does not conform to a multi-dimensional working habit, and work order backlog and low customer satisfaction degree are caused by untimely work order transfer. The method takes customer satisfaction improvement as a guide, mines key factors influencing the customer satisfaction, combines the assembly maintenance efficiency data and the regional customized work order scheduling strategy, and selects the optimal assembly maintenance personnel for the assembly maintenance work order to carry out home construction.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flowchart of a work order scheduling method according to the present invention;
FIG. 2 is a second flowchart of a work order scheduling method according to the present invention;
FIG. 3 is a schematic structural diagram of a work order scheduling system according to the present invention;
fig. 4 is a schematic physical structure diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The existing technical scheme has the defects that the existing technical scheme has the condition that the work order is unreasonably scheduled and needs to be transferred and dispatched except the defects recorded in the background technology. The work order scheduling only selects the maintenance personnel to assign the work order according to the capacity value of the maintenance personnel and the newly added maintenance position, and the working habits of the maintenance personnel, such as the maintenance range, the shift arrangement and the like, are not considered, so that the wrong and unreasonable work order scheduling is caused.
For unreasonable order dispatching situations such as the order dispatching address does not belong to the jurisdiction range of the assembly and maintenance personnel, the assembly and maintenance personnel are required to be dispatched to other assembly and maintenance personnel for implementation, and the workload of unnecessary dispatching work orders is increased. If the assembly and maintenance personnel are in construction or on vacation, the assembly and maintenance work order with unreasonable scheduling cannot be dispatched in time, so that the work order overstock and the like influence the assembly and maintenance work efficiency, the customer satisfaction and the like.
In addition, the existing scheme uses a fixed scheduling strategy to perform work order scheduling. Different regions and cities have different attention points according to self conditions, a fixed scheduling strategy is used, various scene differences are not considered, and the individual requirements of work order scheduling in different regions cannot be met in an all-round manner.
An embodiment of the present invention further provides a work order scheduling method, as shown in fig. 1, the method includes:
step 140, obtaining a comprehensive recommendation index of the maintenance personnel according to the satisfaction recommendation index and the effectiveness recommendation index;
and 150, distributing the assembly and maintenance order to be distributed to assembly and maintenance personnel according to the comprehensive recommendation index.
The method comprises the steps of firstly, modeling the key factors of the customer satisfaction according to historical working data such as customer installation information, installation geographical environment, installation setting information, installation and maintenance construction process data, installation and maintenance personnel data and installation and maintenance assessment data and customer satisfaction survey data, and mining the key factors influencing the customer satisfaction by using a multi-factor variance analysis AI method.
And then constructing a mounting and maintenance efficiency evaluation model, wherein the mounting and maintenance efficiency evaluation model comprises basic mounting and maintenance information, a mounting and maintenance capacity value, historical mounting habits, mounting and maintenance star rating and the like, indexes are selected according to expert experience, and the indexes are labels of the working efficiency and working habits of the mounting and maintenance personnel and provide important support for recommending the mounting and maintenance personnel.
The actual conditions and the attention points of different cities and areas are different, and for the scene differences, the work order scheduling cannot be comprehensively met by using a fixed scheduling strategy, so a parameter configurable scheme is provided, and the most reasonable strategy is customized for the work order scheduling.
And determining the optimal assembly and maintenance personnel for the new assembly and maintenance work order according to the obtained data of the personalized scheduling, the assembly and maintenance capability value, the assembly and maintenance scheduling condition and the like customized according to each region. The newly added filing work data has a positive feedback function, and key factors influencing customer satisfaction can be dynamically adjusted through newly added work order data, so that the purpose of continuously optimizing the work order scheduling model is achieved.
The AI scheduling strategy takes the improvement of customer satisfaction as a leading factor, the working habit of maintenance personnel is respected, the satisfaction influence factors can be dynamically updated according to the current working data, and the effects of continuously optimizing the working efficiency of maintenance and improving the customer satisfaction are achieved.
The invention provides a work order scheduling method, which aims at the problems that work order overstock and customer satisfaction are low due to the fact that work order distribution does not accord with combination maintenance working habits and work orders are not dispatched in time, mainly improves customer satisfaction, excavates key factors influencing customer satisfaction, combines combination maintenance efficiency data and customizes a work order scheduling strategy according to regions, and selects optimal maintenance personnel to carry out on-site construction for a maintenance work order.
The existing scheme has the problems of non-conformity to the combined maintenance working habit, untimely work order distribution and low customer satisfaction. The invention provides a method and a system for carrying out work order intelligent scheduling based on key factors of satisfaction aiming at the current situation of the prior art. The method comprises five steps of customer satisfaction influence key factor model training, installation and maintenance efficiency model construction, intelligent scheduling strategy customization, intelligent scheduling implementation and installation and maintenance work data feedback scheduling strategy, and has the advantages of improving customer satisfaction and improving installation and maintenance work efficiency.
The scheme mainly comprises the following five parts:
first, satisfaction influence key factor model training
The method and the device for intelligently scheduling the work orders take customer satisfaction as a main factor, so that the customer satisfaction including key factors and the influence degree of each factor need to be clearly influenced. The AI method is used for mining key factors influencing the customer satisfaction, so that the independent influence of each key factor on the customer satisfaction can be analyzed, whether the interaction of a plurality of influence factors can generate obvious influence on the customer satisfaction can be analyzed, the influence degree of each factor is finally determined, and the optimal combination influencing the customer satisfaction is mined.
In multi-factor analysis of variance, the variation of the value of an observed variable is influenced by three aspects: firstly, the influence of the independent action of the control variables refers to the influence of the independent action of a single control variable on the observation variable; secondly, the influence of interaction of the control variables refers to the influence on the observation variables after the control variables are mutually matched; third, the influence of random factors mainly refers to the influence caused by sampling errors. Based on the above principles, the multi-factor analysis of variance decomposes the total variation of observed variables into (taking two control variables A, B as an example):
SST＝SSA+SSB+SSAB+SSE；
wherein SST is the total variation of the observed variable; SSA, SSB are the deteriorations caused by the independent action of control variable A, B, respectively; SSAB is the variation caused by the interaction of control variable A, B; SSE is the variation caused by random factors. In general, SSA + SSB + SSAB is the main effect, SSAB is the N-directional interaction effect, and SSE is the residual effect. Wherein SST is defined as:
k is the level of the control variable A, r is the level of the variable B, x ijv For the ith and jth sample values, n, at A and B ij For the number of samples at the ith level of a and the jth level of B,
is the mean value of the observed variables. SSA is defined as:
n ij for the number of samples at the ith level of a and the jth level of B,
the mean of the observed variables at the ith level of variable a. SSB is defined as:
SSAB＝SST-SSA-SSB-SSE；
then, the observed value of the test statistic and the accompanying probability p value are calculated by comparing the square sum of the total dispersion of the observed variables and the proportion of each part. The test statistic used for multifactor analysis of variance is the F statistic. Two control variables, typically corresponding to three F-test statistics:
l is the degree of freedom in the group. The algorithm finally gives an accompanying probability p value according to an F distribution table, and according to a statistical theory, variables with p values smaller than 0.05 have significant influence on dependent variables (satisfaction).
The method comprises the steps of firstly collecting historical working data and satisfaction investigation results, wherein the historical working data comprise historical working data such as customer installation information, installation geographical environment, installation equipment information, installation and maintenance construction process data, installation and maintenance personnel data, installation and maintenance assessment data and the like, and customer satisfaction investigation data.
And then modeling and training the information by using a multi-factor ANOVA (analysis of variance) method, gradually determining the influence degree of each factor on the customer satisfaction, and finally sequencing the information according to the influence degree, so that the key factors influencing the customer satisfaction can be obtained, wherein the number of the key factors is generally not more than 5.
Key factors affecting customer satisfaction may include door entry construction duration, service performance rate, testing optical power values, and the like. Calculating the key factor index value of the satisfaction degree of each assembly and maintenance worker by using the assembly and maintenance historical work data, wherein the index value is related to the assembly and maintenance worker P and the dispatching information T and is recorded as X (P, T) ═ X (X) 1 ,x 2 ,…,x n ) Where n is the number of critical factors for satisfaction. X (P, T) is used for calculating the serviceman satisfaction recommendation index.
Meanwhile, the newly filed assembly and maintenance work order has a positive feedback function, relevant work data and satisfaction survey results are used as incremental samples to be supplemented to a training data set, and customer satisfaction influence factors are dynamically adjusted.
Secondly, constructing a packing and maintaining efficiency model
The loading and maintenance efficiency model selects indexes according to expert experience, the indexes comprise loading and maintenance basic information (such as sex, age and academic calendar), loading and maintenance capacity values (such as total capacity value and available capacity value), historical loading habits (such as loading address, loading time period and loading time length), loading and maintenance star rating and the like, and the indexes are labels for describing the working efficiency indexes and the working habits of each loading and maintenance worker.
Part of the labels can be directly obtained through personnel basic information, such as information of sex, age and the like; and other labels are obtained through algorithm calculation, such as installation duration, installation and maintenance capacity values and the like.
The index value is related to the maintenance person P and the order information T and is marked as Y (P, T) ═ Y 1 ,y 2 ,…,y m ) Where m is the number of performance indicators. And Y is used for calculating the efficiency recommendation index of the maintenance personnel.
If the new additional installation and maintenance work order T address belongs to the installation and maintenance person P 1 And P 2 Normal installation area of, however, P 1 If the calendar installed time at the address is shorter, the work order T, P is matched 1 There will be a higher performance recommendation index.
In addition, the suggested capability value of the maintenance personnel is calculated according to the historical maintenance efficiency, the maintenance quality and other data of the maintenance personnel, and the higher the capability value is, the more maintenance worksheets can be processed in the same time period. The system suggests the ability value to provide reference for the agent maintenance manager to evaluate the assembly and maintenance ability value.
The assembly and maintenance efficiency model can be continuously corrected according to the change of the basic data and the construction data, so that the assembly and maintenance efficiency model is more and more three-dimensional, and assembly and maintenance personnel can be more accurately selected.
Third, intelligent scheduling strategy customization
And the intelligent scheduling strategy uses the assembly and maintenance personnel satisfaction recommendation index and the assembly and maintenance personnel effectiveness recommendation index for weighting to obtain an assembly and maintenance personnel recommendation index, and selects a proper assembly and maintenance personnel allocation task for the new assembly and maintenance work order through the assembly and maintenance recommendation index. The AI scheduling strategy is formally a formula, and the recommendation index of the assembly and maintenance work order T corresponding to the assembly and maintenance personnel P is calculated by the following formula:
f(P,T)＝C 1 ·g(X(P,T))+C 2 ·h(Y(P，T))；
where g is a satisfaction index function, h is a performance index function, C 1 And C 2 Respectively, a satisfaction index and a performance index weighting factor. Each city and region manager can define appropriate g and h and form according to the self condition, such as defining g and h as weighted sum of components:
wherein alpha is i And beta i Is each indexAnd (4) weighting. And the scheduling strategy is customized according to the city and the region, so that the work order scheduling is more consistent with the specific conditions of each region, and the aim of flexibly and efficiently scheduling the work orders is fulfilled.
Fourth, intelligent scheduling implementation
When a customer has a loading and maintenance requirement, a loading and maintenance work order is generated, the work order comprises information such as a loading and maintenance address, loading and maintenance reservation construction time, installation product requirements and the like, and the work order can be transferred to an AI dispatching center for centralized dispatching. And the scheduling center calculates the recommendation index of each optional assembly and maintenance worker according to the formula and the combination of the assembly and maintenance worker capability value and the scheduling table according to the AI scheduling strategy customized in the last step, allocates the assembly and maintenance worker with the optimal recommendation index to carry out home construction in the assembly and maintenance work order reservation time period, and achieves the aims of maximizing assembly and maintenance efficiency and improving the overall satisfaction degree of customers as much as possible.
After a new additional work order is assigned, the capacity value of the maintenance personnel is updated in real time according to the work order quantity, scheduling and other information of the maintenance personnel, the next additional work order is accurately scheduled, and the unreasonable work order scheduling caused by the fact that the capacity value of the maintenance personnel is not updated in time is avoided.
After receiving the assembly and maintenance task, the assembly and maintenance personnel actively plan the route according to the original geographical distribution of the work order, the emergency degree of the newly-added work order and the assembly and maintenance address distance, and then contact the customer to carry out construction at home, so that the subjective initiative is fully exerted, the assembly and maintenance are more timely and efficient, and the effect of improving the customer satisfaction is achieved.
Five-dimension work data feedback scheduling strategy
After the assembly and maintenance work order is filed, the assembly and maintenance work order information, the customer assembly information, the assembly geographic environment, the installation equipment information, the assembly and maintenance personnel information, the assessment data, the assembly and maintenance efficiency data, the customer satisfaction survey information and other data are arranged and used as incremental samples to be supplemented to the model training data set. The newly added filing working data has a positive feedback effect on the training of the key factor model, and the key factor model and the installation and maintenance efficiency model influencing the customer satisfaction can be continuously adjusted and optimized through dynamic data training, so that the model is more and more accurate and reliable. Through dynamic dress dimension working data feedback scheduling strategies, the AI scheduling strategies can be adjusted at any place and any region according to the latest customer satisfaction influence key factors and the dress dimension efficiency model, and the purposes of reasonably and evenly scheduling dress dimension personnel and improving dress dimension efficiency are achieved.
As shown in FIG. 2, the invention realizes a method for intelligent work order scheduling based on critical factors of satisfaction, which mainly comprises five steps of customer satisfaction influence critical factor model training, equipment maintenance efficiency model construction, intelligent scheduling strategy customization, intelligent scheduling implementation and equipment maintenance work data feedback scheduling strategy.
First, satisfaction influences key factor type training
The method comprises the steps of firstly, collecting historical working data and satisfaction investigation results, wherein the historical working data comprises customer installation information, installation geographical environment, installation equipment information, installation and maintenance construction process data, installation and maintenance personnel data, installation and maintenance assessment data and the like, and the customer satisfaction investigation data. And performing key factor analysis and mining on the information by using a multi-factor variance analysis method, and sorting the extracted data according to an analysis result, namely the influence degree of each variable on the customer satisfaction, wherein the larger the influence degree is, the more important the variable is, and the closer the relationship with the customer satisfaction is. After the satisfaction influence factors are determined, calculating the satisfaction key factor index value of each maintenance worker by using the historical work data of the maintenance worker, wherein the index value is related to the maintenance worker P and the dispatching information T and is recorded as X (P, T) ═ X (X) 1 ,x 2 ,…,x n ) Where n is the number of critical factors for satisfaction. And X is used as a key input parameter of the work order intelligent scheduling strategy.
Secondly, constructing a packing and maintaining efficiency model
The installation and maintenance efficiency model carries out all-round description on the efficiency and the service quality of installation and maintenance personnel, and indexes are selected according to expert experience and comprise installation and maintenance basic information (such as sex, age and academic calendar), installation and maintenance capacity values (such as total capacity value and available capacity value), historical installation habits (such as installation address, installation time period and installation time length), installation and maintenance star-level evaluation and other working efficiency and working habit labels. Part of the labels can be directly obtained through personnel basic information, such as information of sex, age and the like; other tags are obtained by algorithmic calculations, e.g. installed duration andassembly ability values, etc. The index value is related to the maintenance person P and the order information T and is recorded as Y (P, T) or (Y) 1 ,y 2 ,…,y m ) Where m is the number of performance indicators. And Y is used for calculating the efficiency recommendation index of the maintenance personnel.
The assembly and maintenance efficiency model can be continuously corrected according to the variation of the assembly and maintenance basic data and the construction data, so that the model is more and more three-dimensional, and is more accurate and reasonable when the information of assembly and maintenance personnel is matched.
Third, intelligent scheduling strategy customization
And the intelligent scheduling strategy allocates the most suitable assembly and maintenance personnel for the newly added assembly and maintenance work order by calculating the recommended index of each optional assembly and maintenance personnel. The assembly and maintenance personnel recommendation index is calculated by the formula, and the scheme provides a default scheduling strategy. And different cities and areas can flexibly adjust the scheduling strategy according to the actual conditions, the installation and maintenance task types and other information, so that the work order scheduling is more reasonable. And calculating a satisfaction recommendation index and a effectiveness recommendation index. And allocating more appropriate assembly and maintenance personnel for the new assembly and maintenance work order according to the scheduling strategy customized in the local city and the region, thereby improving the assembly and maintenance efficiency and improving the customer satisfaction.
Fourth, intelligent scheduling implementation
When a customer has a loading and maintenance requirement, a loading and maintenance work order is generated, the work order comprises information such as a loading and maintenance address, loading and maintenance reservation construction time, installation product requirements and the like, and then the work order is transferred to an AI dispatching center to wait for dispatching and dispatching. And the scheduling center calculates the recommendation index of each optional assembly and maintenance person according to the formula by combining the assembly and maintenance person capability value and the scheduling table according to the configured scheduling strategy, and assigns the assembly and maintenance person with the best recommendation index to the new assembly and maintenance work order. After the work order scheduling is finished, the ability value of the maintenance personnel can be updated in real time according to the work order quantity, scheduling and other information of the maintenance personnel. Meanwhile, the assembly and maintenance personnel receive the assembly and maintenance task in time, and can actively plan the assembly and maintenance route according to the geographical distribution of the work order and the newly added work order information, so that the assembly and maintenance are more timely and efficient.
Five-dimension work data feedback scheduling strategy
After the dress dimension work order is filed, the dress dimension work data is arranged, including: and the data such as the assembly and maintenance work order information, the customer assembly information, the assembly and maintenance geographic environment, the installation equipment information, the assembly and maintenance personnel information, the assessment data, the assembly and maintenance construction process data, the customer satisfaction survey information and the like are used as incremental samples to be supplemented to the model training data set. And dynamic data training is carried out on the key factor model by using newly added filing data, so that the aims of continuously adjusting and optimizing the key factor model of the customer satisfaction degree and the installation and maintenance efficiency model are fulfilled, and the model is more and more accurate and reliable. Through the continuous assembly and maintenance work data feedback scheduling strategy, the AI scheduling strategy can be adjusted at any place and any region according to the latest customer satisfaction influence key factors and the assembly and maintenance efficiency model, so that the purposes of reasonably and uniformly scheduling assembly and maintenance personnel and improving the scheduling efficiency are achieved.
The main key points of the embodiment of the invention are as follows:
(1) the intelligent scheduling method and the intelligent scheduling device take customer satisfaction as a leading factor, mine the key factors influenced by the satisfaction, and achieve the purpose of improving the customer satisfaction by monitoring or optimizing the mined key factors.
(2) Labeling basic information, star rating, working efficiency, working habit and other information of the maintenance personnel through analysis and calculation, and constructing a maintenance efficiency model according to the labeling information, so as to provide support data for selecting the optimal maintenance personnel.
(3) Different cities or grids can be combined with the characteristics and conditions of the areas per se to customize different scheduling strategies, so that the purposes of improving the scheduling efficiency and flexibly formulating the scheduling strategies can be achieved.
(4) Newly filed dimension work data are used as an increment sample to be supplemented to a training data set, and a key factor model and a dimension efficiency model are influenced by continuous adjustment and optimization of the satisfaction degree, so that the model is more and more accurate and reliable.
The invention has the advantages of improving the customer satisfaction degree and the assembly and maintenance efficiency. By using the AI scheduling strategy, the assembly maintenance personnel can be matched from multiple dimensions, and the existing scheduling rule according to the capability value and the assembly maintenance position of the assembly maintenance personnel is changed, so that the work order scheduling is more intelligent, reasonable and efficient; continuously adjusting and optimizing customer satisfaction influence key factors and a packaging and maintenance efficiency model through dynamic model training; the city and grid managers can make work order dispatching strategies according to the regional conditions of the city and grid managers, and a more reasonable and efficient dispatching method is found for work order dispatching.
An embodiment of the present invention provides a work order scheduling system, as shown in fig. 3, the system includes: a key influence factor screening module 301, a satisfaction index calculation module 302, a performance index calculation module 303, a comprehensive recommendation index calculation module 304 and an order allocation module 305, wherein:
the key influence factor screening module 301 is configured to obtain a key influence factor according to historical work data of maintenance personnel in a target area and a customer satisfaction degree influence key factor model, where the customer satisfaction degree key influence factor model is obtained by training with the historical work data of the maintenance personnel in the target area as a sample and the customer satisfaction degree as a label, and the target area is an area where a maintenance order to be allocated is located;
the satisfaction index calculation module 302 is configured to obtain a satisfaction recommendation index of the maintenance staff according to the key influence factor;
the efficiency index calculation module 303 is configured to obtain an efficiency recommendation index of the maintenance worker according to the historical maintenance efficiency working data of the maintenance worker and a maintenance efficiency model, where the maintenance efficiency model is obtained by training with the historical maintenance efficiency working data of the maintenance worker as a sample and the maintenance efficiency index as a label;
the comprehensive recommendation index calculation module 304 is configured to obtain a comprehensive recommendation index of the maintenance worker according to the satisfaction recommendation index and the effectiveness recommendation index;
the order distribution module 305 is configured to distribute the assembly and maintenance order to be distributed to the assembly and maintenance staff according to the comprehensive recommendation index.
The present embodiment is a system embodiment corresponding to the above method, and the specific implementation thereof is the same as the above method embodiment, and please refer to the above method embodiment for details, which is not described herein again.
An embodiment of the present invention provides an electronic device, as shown in fig. 4, the electronic device may include: a processor (processor)410, a communication Interface 420, a memory (memory)430 and a communication bus 440, wherein the processor 410, the communication Interface 420 and the memory 430 are communicated with each other via the communication bus 440. The processor 410 may call logic instructions in the memory 430 to perform a work order scheduling method comprising:
obtaining key influence factors according to historical working data of maintenance personnel in a target area and a customer satisfaction degree key factor model, wherein the customer satisfaction degree key factor model is obtained by training with the historical working data of the maintenance personnel in the target area as a sample and the customer satisfaction degree as a label, and the target area is an area where a maintenance order is to be distributed;
obtaining a satisfaction degree recommendation index of the maintenance personnel according to the key influence factors;
acquiring an efficiency recommendation index of the maintenance personnel according to the historical maintenance efficiency working data and a maintenance efficiency model of the maintenance personnel, wherein the maintenance efficiency model is obtained by training by taking the historical maintenance efficiency working data of the maintenance personnel as a sample and taking a maintenance efficiency index as a label;
acquiring a comprehensive recommendation index of the maintenance personnel according to the satisfaction recommendation index and the effectiveness recommendation index;
and distributing the assembly and maintenance orders to be distributed to assembly and maintenance personnel according to the comprehensive recommendation index.
In addition, the logic instructions in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention or a part thereof which substantially contributes to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform a method for scheduling work orders provided by the above methods, the method comprising:
obtaining key influence factors according to historical working data of maintenance personnel in a target area and a customer satisfaction degree key factor model, wherein the customer satisfaction degree key factor model is obtained by training with the historical working data of the maintenance personnel in the target area as a sample and the customer satisfaction degree as a label, and the target area is an area where a maintenance order is to be distributed;
obtaining a satisfaction recommendation index of the maintenance personnel according to the key influence factors;
acquiring an efficiency recommendation index of the maintenance personnel according to the historical maintenance efficiency working data and a maintenance efficiency model of the maintenance personnel, wherein the maintenance efficiency model is obtained by training by taking the historical maintenance efficiency working data of the maintenance personnel as a sample and taking a maintenance efficiency index as a label;
acquiring a comprehensive recommendation index of the maintenance personnel according to the satisfaction recommendation index and the effectiveness recommendation index;
and distributing the assembly and maintenance orders to be distributed to assembly and maintenance personnel according to the comprehensive recommendation index.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor is implemented to perform a method of work order scheduling as provided above, the method comprising:
obtaining key influence factors according to historical working data of maintenance personnel in a target area and a customer satisfaction degree key factor model, wherein the customer satisfaction degree key factor model is obtained by training with the historical working data of the maintenance personnel in the target area as a sample and the customer satisfaction degree as a label, and the target area is an area where a maintenance order is to be distributed;
obtaining a satisfaction recommendation index of the maintenance personnel according to the key influence factors;
acquiring an efficiency recommendation index of the maintenance personnel according to the historical maintenance efficiency working data and a maintenance efficiency model of the maintenance personnel, wherein the maintenance efficiency model is obtained by training by taking the historical maintenance efficiency working data of the maintenance personnel as a sample and taking a maintenance efficiency index as a label;
acquiring a comprehensive recommendation index of the maintenance personnel according to the satisfaction recommendation index and the effectiveness recommendation index;
and distributing the assembly and maintenance orders to be distributed to assembly and maintenance personnel according to the comprehensive recommendation index.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present 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 solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A work order scheduling method is characterized by comprising the following steps:
obtaining key influence factors according to historical working data of maintenance personnel in a target area and a customer satisfaction degree key factor model, wherein the customer satisfaction degree key factor model is obtained by training with the historical working data of the maintenance personnel in the target area as a sample and the customer satisfaction degree as a label, and the target area is an area where a maintenance order is to be distributed;
obtaining a satisfaction recommendation index of the maintenance personnel according to the key influence factors;
acquiring an efficiency recommendation index of the maintenance personnel according to the historical maintenance efficiency working data and a maintenance efficiency model of the maintenance personnel, wherein the maintenance efficiency model is obtained by training by taking the historical maintenance efficiency working data of the maintenance personnel as a sample and taking a maintenance efficiency index as a label;
acquiring a comprehensive recommendation index of the maintenance personnel according to the satisfaction recommendation index and the effectiveness recommendation index;
and distributing the assembly and maintenance orders to be distributed to assembly and maintenance personnel according to the comprehensive recommendation index.
2. The work order scheduling method of claim 1, further comprising:
and after the dispatching of the to-be-distributed assembly and maintenance order is finished, updating the work order amount and scheduling information of the assembly and maintenance personnel to obtain the assembly and maintenance capability value of the assembly and maintenance personnel again, wherein the assembly and maintenance capability value is one of the historical assembly and maintenance performance working data.
3. The work order scheduling method of claim 1, further comprising:
and after the dispatching of the assembly and maintenance order to be distributed is finished, updating the historical working data of the assembly and maintenance personnel so as to update the customer satisfaction influence key factor model.
4. The work order scheduling method of claim 1, wherein the customer satisfaction key influence factor model is obtained by training with historical work data of maintenance personnel in the target area as a sample and customer satisfaction as a label, and comprises:
and modeling and training historical working data of the maintenance personnel based on a multi-factor ANOVA (analysis of variance) method to obtain a key influence factor model of the customer satisfaction.
5. The work order scheduling method according to any one of claims 1 to 4, wherein the obtaining of the comprehensive recommendation index for the maintenance personnel according to the satisfaction recommendation index and the effectiveness recommendation index comprises:
f(P,T)＝C 1 ·g(X(P,T))+C 2 ·h(Y(P,T))；
wherein P represents the comprehensive recommendation index, T represents a work order, C 1 Weight coefficient, C, representing satisfaction recommendation index 2 A weight coefficient representing a performance recommendation index, g represents a satisfaction index function, h represents a performance index function, X (P, T) represents the satisfaction recommendation index, and Y (P, T) represents the performance recommendation index.
6. The work order scheduling method of claim 5, wherein the satisfaction index function and the performance index function are derived using the following equations:
wherein i represents a reference number, n represents the number of all key influencing factors, x i Denotes the ith key influencing factor, alpha i Weight, y, representing the ith key influencing factor i Denotes the ith performance index, beta i Represents the weight of the ith performance indicator.
7. The work order scheduling method of claim 5 wherein said satisfaction index function and/or said performance index function is determined based on said target area.
8. A work order scheduling system, comprising:
the key influence factor screening module is used for obtaining key influence factors according to historical working data of maintenance personnel in a target area and a customer satisfaction influence key factor model, wherein the customer satisfaction key influence factor model is obtained by training with the historical working data of the maintenance personnel in the target area as a sample and the customer satisfaction as a label, and the target area is an area where a maintenance order to be distributed is located;
the satisfaction index calculation module is used for acquiring a satisfaction recommendation index of the maintenance personnel according to the key influence factors;
the efficiency index calculation module is used for obtaining an efficiency recommendation index of the maintenance personnel according to the historical assembly and maintenance efficiency working data of the maintenance personnel and an assembly and maintenance efficiency model, wherein the assembly and maintenance efficiency model is obtained by training by taking the historical assembly and maintenance efficiency working data of the maintenance personnel as a sample and taking the assembly and maintenance efficiency index as a label;
the comprehensive recommendation index calculation module is used for acquiring a comprehensive recommendation index of the maintenance personnel according to the satisfaction recommendation index and the effectiveness recommendation index;
and the order distribution module is used for distributing the assembly and maintenance orders to be distributed to the assembly and maintenance personnel according to the comprehensive recommendation index.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the work order scheduling method according to any of claims 1 to 7.
10. A non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the work order scheduling method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110261227.1A CN115081766A (en) | 2021-03-10 | 2021-03-10 | Work order scheduling method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110261227.1A CN115081766A (en) | 2021-03-10 | 2021-03-10 | Work order scheduling method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115081766A true CN115081766A (en) | 2022-09-20 |
Family
ID=83240890
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110261227.1A Pending CN115081766A (en) | 2021-03-10 | 2021-03-10 | Work order scheduling method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115081766A (en) |
-
2021
- 2021-03-10 CN CN202110261227.1A patent/CN115081766A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109272276B (en) | Inventory replenishment management method and device | |
| Baringo et al. | Risk-constrained multi-stage wind power investment | |
| US7987105B2 (en) | Traffic based labor allocation method and system | |
| US7984441B2 (en) | Method and system for tuning a taskscheduling process | |
| CN107506880B (en) | Method and device for scheduling assembly and maintenance work order | |
| EP3309724A1 (en) | Methods and systems related to allocating field engineering resources for power plant maintenance | |
| US8326447B2 (en) | Advanced planning system | |
| CN111915254A (en) | Inventory optimization control method and system suitable for automobile after-sales accessories | |
| CN110689217B (en) | Intelligent manufacturing system for computer production | |
| CN114971356A (en) | Electric power engineering project progress prediction system and method | |
| CN111695842A (en) | Distribution scheme determination method and device, electronic equipment and computer storage medium | |
| US20170039498A1 (en) | Systems and methods to forecast and improve product on-shelf availability | |
| CN115438966A (en) | SEM model-based old age care service institution configuration optimization method and system | |
| CN111105050B (en) | Fan maintenance plan generation method, device, equipment and storage medium | |
| US7580766B1 (en) | Manufacturing resource planning by entity | |
| CN111652471B (en) | List distribution control method and device, electronic equipment and storage medium | |
| CN113191533A (en) | Warehouse employment prediction method, device, equipment and storage medium | |
| CN115081766A (en) | Work order scheduling method and system | |
| CN111738507A (en) | Bank clearing position fund payment amount prediction method, device, equipment and medium | |
| CN116502830A (en) | Scheduling plan generation method, scheduling plan generation system and scheduling plan generation product | |
| KR102638339B1 (en) | System and method for managing bid based on intelligent demand response | |
| CN114444782A (en) | Enterprise asset management method and device, storage medium and computer equipment | |
| WO2020235150A1 (en) | Power consumption prediction device | |
| Jánošíková et al. | Emergency medical system design using kernel search | |
| CN117252446B (en) | Method and system for process index extraction and index intelligent operation |
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 |