CN112347148A

CN112347148A - Expert recommendation method, device and system based on expert database

Info

Publication number: CN112347148A
Application number: CN202011191025.6A
Authority: CN
Inventors: 张冀兰; 郭强; 刘华; 杨加东; 皮敏; 杨沥铭; 熊伟; 富会佳; 李强; 张立侠
Original assignee: CNNC Nuclear Power Operation Management Co Ltd
Current assignee: CNNC Nuclear Power Operation Management Co Ltd
Priority date: 2020-10-30
Filing date: 2020-10-30
Publication date: 2021-02-09

Abstract

The disclosure belongs to the technical field of nuclear power, and particularly relates to an expert recommendation method, device and system based on an expert database. The expert recommendation system based on the expert database can widely obtain expert information from the equipment management system, the work order management system and the portal website, has wide coverage range, adopts information such as maintenance record data, titles, working years, qualification certificates, prize winning conditions and the like of personnel for the capability evaluation of the personnel, evaluates and displays the capability of the expert more objectively and accurately, and is beneficial to a user to select a maintenance expert with more appropriate capability. In addition, the method and the system can also acquire the conditions of post change, post departure and the like of the expert in time, and reduce the influence on the decision of the user to the maximum extent, thereby integrating the factors of the ability, the time arrangement, the cost and the like of the personnel and seeking the most suitable expert support.

Description

Expert recommendation method, device and system based on expert database

Technical Field

The invention belongs to the technical field of nuclear power, and particularly relates to an expert recommendation method, device and system based on an expert database.

Background

The equipment is the core asset of an asset-intensive enterprise, and the normal production activities of the enterprise cannot leave the good operation of the equipment. In actual production, due to factors such as abrasion, aging and corrosion, equipment is always accompanied by hidden dangers of different degrees, and faults are inevitable. As the guarantee of the stable operation of the equipment, the equipment maintenance work has important significance for the safety production of enterprises.

When equipment breaks down, when equipment engineers and maintenance engineers can not handle according to self skills and experience, proper experts need to be found in time to provide technical support, and the expanded risk of accidents is avoided. At present, equipment maintenance experts are searched through communication modes such as telephone, mail, chat software and the like. This approach has the following problems: 1. the search range is small: the current communication mode has small search range and small quantity of selectable experts, can not integrate factors such as expert ability, time arrangement, cost and the like, and seeks the most suitable expert support. 2. The communication efficiency is low: the current communication mode needs to wait for the feedback of the other party, only a small amount of expert information can be obtained, and the communication efficiency is low. 3. The acquired expert information lags: the expert information acquired by the current mode has hysteresis, so that conditions such as expert post change and job leaving cannot be mastered in time, and the decision of a user is influenced. 4. The acquired expert information is not comprehensive: the expert capability evaluation needs to obtain the information of the expert such as the adequacy equipment type, the working life, the maintenance quality and the like, the expert information obtained in the current communication mode is not comprehensive, and the expert capability cannot be accurately evaluated.

Disclosure of Invention

In order to overcome the problems in the related art, an expert recommendation method, device and system based on an expert database are provided.

According to an aspect of the embodiments of the present disclosure, there is provided an expert recommendation method based on an expert database, the method being applied to an expert recommendation subsystem, the method including:

acquiring an expert recommendation request sent by a maintenance management subsystem;

determining request information according to the acquired expert recommendation request, wherein the request information comprises the equipment type and the maintenance field of the fault to be processed and demand information for describing the requirements on experts;

sending an inquiry request to a maintenance expert database, wherein the inquiry request comprises the equipment type and the maintenance field;

receiving a first selection expert list sent by the maintenance expert database in response to the query request, wherein the first selection expert list comprises expert information of a plurality of experts, each expert information comprises an equipment type and a maintenance field which are mastered by the expert and resume information used for describing the maintenance capability of the expert, and the equipment type and the maintenance field which are contained in each expert information are matched with the equipment type and the maintenance field which are contained in the query request;

determining the matching degree of the historical information of each expert in the primary selection expert list and the demand information;

and forming a recommended expert list according to the expert information corresponding to the historical information of which the matching degree meets the preset conditions, and sending the recommended expert list to the maintenance management subsystem.

In one possible implementation manner, the dimension of the demand information includes any one or more of fault type, fault keyword, one-time maintenance passing rate, high rating rate, maintenance quantity, job condition, affiliated company, unit price, job title, working age, qualification certificate, prize winning level and participation major project level;

the dimension of the resume information comprises any one or more of fault type, fault keywords, one-time maintenance passing rate, high rating rate, maintenance quantity, job condition, affiliated company, unit price, job title, working age, qualification certificate, prize winning level and participation major project level;

the dimensionality of the requirement information is consistent with the number and the type of the dimensionality of the expert information;

determining the matching degree of the resume information of each expert and the demand information, wherein the matching degree comprises the following steps:

and determining the dimension matching degree between each dimension of the historical information of the expert and the dimension of the same type as the dimension in the demand information aiming at each expert, and determining the matching degree between the historical information of the expert and the demand information according to the dimension matching degree.

In one possible implementation, the expert recommendation request includes a fault description, the fault description being a natural language describing the to-be-processed fault;

determining request information according to the acquired expert recommendation request, wherein the request information comprises:

and performing semantic recognition on the fault description to obtain the fault type in the demand information.

According to another aspect of the embodiments of the present disclosure, there is provided an expert database-based expert recommendation method, which is applied to a service expert database, the method including:

receiving an inquiry request sent by an expert recommendation subsystem;

determining the equipment type and the maintenance field contained in the query request according to the query request;

determining expert information of an expert of which the equipment type and the maintenance field are matched with the equipment type and the maintenance field of the query request in the maintenance expert library;

and forming a primary selection expert list according to the determined expert information, and sending the primary selection expert list to the expert recommendation subsystem.

In one possible implementation, the method further includes:

acquiring the identifications of a plurality of target personnel from the equipment management system, the work order management system and the portal website to form an expert list;

for each expert in the list of experts, performing the following:

determining the one-time maintenance passing rate and the maintenance quantity of the expert according to the maintenance record data corresponding to the identification of the expert, which is obtained from the work order management system, the quality defect management system and the change management system;

acquiring the corresponding working condition, the affiliated company, the unit price, the title, the working age, the qualification certificate, the prize winning level and the participation major project level of the identification of the expert from a personnel management system;

determining the available time of the expert according to a personnel management system and a work order management system;

acquiring the equipment type corresponding to the identification of the expert from the equipment management system;

acquiring a maintenance field, a fault type and a fault keyword corresponding to the identification of the expert from the work order management system;

determining the good appraisal rate of the expert according to the comment data corresponding to the identification of the expert and acquired from the maintenance management subsystem

And establishing an expert database according to the fault type, the one-time maintenance passing rate, the rating rate, the maintenance quantity, the working condition, the affiliated company, the unit price, the title, the working age, the qualification certificate, the prize winning level, the participation major project level, the equipment type and the maintenance field corresponding to each expert.

In a possible implementation manner, determining a one-time repair passing rate and a repair number of the expert according to repair record data corresponding to the identification of the expert, which is acquired from the work order management system, the quality defect management system, and the change management system, includes:

determining the maintenance quantity of the expert according to the quantity of the completed work orders corresponding to the work order management system by the identification of the expert, the quantity of the completed quality defect reports corresponding to the quality defect management system by the identification of the expert and the quantity of the completed equipment change design schemes corresponding to the change management system by the identification of the expert;

and determining the one-time maintenance passing rate of the expert according to the number of the work orders which are passed by the expert at one time, the number of quality defect reports which are passed by the expert at one time, the number of the equipment change design schemes which are passed by the expert at one time and the maintenance number of the expert.

In one possible implementation, the method further includes:

aiming at each expert, taking the work order which has no rollback record from the state to be approved to the approved state and has no rollback record from the state in work to the finished state in the finished work order corresponding to the identification of the expert as a one-time passing work order;

aiming at each expert, taking the quality defect report of which the applied state is not recorded in a return-free way from the approved state and the construction state is not recorded in a return-free way from the closed state in the finished quality defect report corresponding to the identification of the expert as a one-time passing quality defect report;

aiming at each expert, in the finished equipment change design scheme corresponding to the identification of the expert, no backspacing record is generated in the approval process, and the equipment change design scheme without a construction question list from the implementation state to the changed state is installed as a one-time-through equipment change design scheme.

In one possible implementation, determining the available time of the expert based on the personnel management system and the work order management system includes:

acquiring leave-asking date data corresponding to the expert identification from a personnel management system;

acquiring scheduling data corresponding to the expert identification from a work order management system;

and determining the available time of the expert according to the leave-asking date data and the scheduling data corresponding to the expert.

In a possible implementation manner, determining the goodness of the expert according to the comment data corresponding to the identification of the expert, which is acquired from the maintenance management subsystem, includes:

aiming at each expert in the maintenance expert base, after the expert is recommended and hired to finish maintenance, obtaining evaluation and comment information of a hirer aiming at the expert from the maintenance management subsystem;

judging the effectiveness of the evaluation corresponding to the expert according to the comment information corresponding to the expert;

and determining the good evaluation rate of the expert according to the determined effective evaluation.

According to another aspect of the embodiments of the present disclosure, there is provided an expert database-based expert recommendation system including: the system comprises an expert recommending subsystem, a maintenance expert database and a maintenance management subsystem;

the expert recommending subsystem is respectively connected with the maintenance management subsystem and the maintenance expert database and is used for executing the expert recommending method based on the expert database;

the maintenance expert database is used for executing the expert recommendation method based on the expert database;

and the maintenance management subsystem is used for displaying the received recommendation expert list.

According to another aspect of the embodiments of the present disclosure, there is provided an expert recommendation apparatus based on an expert database, the apparatus including:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to perform the method described above.

According to another aspect of embodiments of the present disclosure, there is provided a non-transitory computer-readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the above-described method.

The beneficial effect of this disclosure lies in: the expert recommendation system based on the expert database can widely obtain expert information from the equipment management system, the work order management system and the portal website, has wide coverage range, adopts information such as maintenance record data, titles, working years, qualification certificates, prize winning conditions and the like of personnel for the capability evaluation of the personnel, evaluates and displays the capability of the expert more objectively and accurately, and is beneficial to a user to select a maintenance expert with more appropriate capability. In addition, the method and the system can also acquire the conditions of post change, post departure and the like of the expert in time, and reduce the influence on the decision of the user to the maximum extent, thereby integrating the factors of the ability, the time arrangement, the cost and the like of the personnel and seeking the most suitable expert support.

Drawings

Fig. 1 is a flow chart illustrating a method of expert recommendation based on an expert database according to an exemplary embodiment.

FIG. 2 is a flow diagram illustrating a method for expert recommendation based on an expert database in accordance with an exemplary embodiment.

FIG. 3 is a block diagram illustrating an expert database based expert recommendation system in accordance with an exemplary embodiment.

Fig. 4 is a block diagram illustrating an expert database based expert recommender in accordance with an exemplary embodiment.

Detailed Description

The invention is described in further detail below with reference to the figures and the embodiments.

Fig. 1 is a flow chart illustrating a method of expert recommendation based on an expert database according to an exemplary embodiment. As shown in fig. 1, the method may include:

step 100, acquiring an expert recommendation request sent by a maintenance management subsystem;

step 101, determining request information according to the acquired expert recommendation request, wherein the request information comprises the equipment type and the maintenance field of the fault to be processed and requirement information for describing requirements on experts;

step 102, sending an inquiry request to a maintenance expert database, wherein the inquiry request comprises the equipment type and the maintenance field;

103, receiving a list of first-choice experts sent by the maintenance expert database in response to the query request, wherein the list of first-choice experts comprises expert information of a plurality of experts, each expert information comprises an equipment type and a maintenance field which are good for the experts to handle, and history information for describing the maintenance capability of the experts, and the equipment type and the maintenance field which are contained in each expert information are matched with the equipment type and the maintenance field which are contained in the query request;

104, determining the matching degree of the historical information of each expert in the primary selection expert list and the demand information;

and 105, forming a recommended expert list according to expert information corresponding to the historical information of which the matching degree meets the preset conditions, and sending the recommended expert list to the maintenance management subsystem.

In this disclosure, the expert recommendation subsystem, the expert database, and the maintenance management subsystem may be implemented by one or more terminal devices, where the terminal device may be, for example, a server, a desktop computer, a laptop computer, a tablet computer, or the like, and the terminal device may also be, for example, a user device, a vehicle-mounted device, or a wearable device, and the type of the terminal device is not limited in the embodiment of the present disclosure.

As an example of this embodiment, the expert recommendation subsystem may be connected to the maintenance management subsystem and the expert repository, respectively. The maintenance management subsystem may generate expert recommendation requests based on user input, which may include equipment type, maintenance area, and demand information.

In the present disclosure, the device types may include a major, a middle, and a minor class of devices to handle faults, for example, if the major class of devices is valves, the middle class may be, for example, pneumatic valves, and the minor class may be, for example, diaphragm pneumatic heads; the maintenance field may be expressed as a classification of maintenance categories according to equipment maintenance specialties, technical characteristics, for example, the maintenance field may include aging, corrosion protection, fire protection, communication, and the like. The requirement information can reflect various requirements of the user on experts. The demand information may include a plurality of dimensions, for example, the dimensions of the demand information may include any one or more of a fault type, a one-time maintenance pass rate, a good rate, a maintenance quantity, an occupational situation, an affiliated company, a unit price, a title, a working age, a certificate of merit, a prize winning level, and a participation major project level.

The expert recommending subsystem can receive and analyze the expert recommending request to obtain request information, wherein the request information can comprise the equipment type and the maintenance field of the fault to be processed and demand information;

the expert recommendation subsystem can generate an inquiry request according to the analyzed equipment type and the analyzed maintenance field, and sends the inquiry request to the maintenance expert database.

The service expert database may pre-store expert information of a plurality of experts, wherein the expert information of each expert may include a type of equipment and a service area where the expert is good at service, and history information describing a capability of the expert for service. The maintenance expert database can receive the query request and analyze the query request to obtain the equipment type and the maintenance field contained in the query request.

The service expert database may determine expert information of experts whose equipment types and maintenance fields are matched with the equipment types and maintenance fields of the query request in the service expert database, for example, if the equipment types and maintenance fields included in the query request are vertical centrifugal pumps and the maintenance fields are aging, the service expert database may query and obtain expert information of experts who are good at aging problems of the vertical centrifugal pumps. And then, the maintenance expert database can form a primary selection expert list according to the determined expert information, and sends the generated primary selection expert list to the expert recommendation subsystem.

The expert recommending subsystem can receive a list of primarily selected experts sent by the maintenance expert database in response to the query request, and analyze the list to obtain the historical information of each expert in the list of primarily selected experts;

the expert recommending subsystem can determine the matching degree of the historical information of each expert in the primary selection expert list and the demand information;

for example, the requirement information of the user comprises dimensions, and the dimensions of the requirement information comprise any one or more of fault type, fault keywords, one-time maintenance passing rate, high rating rate, maintenance quantity, job condition, affiliated company, unit price, job title, working age, qualification certificate, prize winning level and participation major project level; the dimension of the history information of the expert can comprise any one or more of fault type, one-time maintenance passing rate, high rating rate, maintenance quantity, job condition, affiliated company, unit price, job title, working age, qualification certificate, prize winning level and participation major project level; wherein the dimension of the demand information of the user is consistent with the number and type of the dimension of the expert information of the expert.

The expert recommending subsystem can determine the matching condition between a certain dimension in the historical information and the dimension in the demand information, which is of the same type as the dimension, and determine the matching degree between the dimension and the dimension of the same type as the demand information according to the corresponding relation between the matching condition and the matching degree.

For example, table 1 is an example of the correspondence between the matching case and the matching degree when the dimension is the company to which the matching case belongs.

TABLE 1

Matching situation	Degree of matching
		Corporate matching	100
Company mismatch	0

Table 2 is an example of the correspondence between the matching condition and the matching degree when the dimension is the fault type.

TABLE 2

Matching situation	Degree of matching
		Fault type matching	10
Failure type mismatch	0

Table 3 shows an example of the correspondence between the matching condition and the matching degree when the dimension is the keyword.

In a possible implementation manner, the fault type of the history information may correspond to a plurality of keyword expert recommendation requests, and may include fault descriptions, in which the user may explain a fault to be processed by using a natural language, and the expert recommendation subsystem may perform semantic recognition on the received fault descriptions, extract keywords in the fault descriptions, such as incapability of starting, abnormal sound, and the like, and match the keywords with the fault keywords in the history information of the experts. When the number of keywords is multiple, the matching degree is increased by 5 every time the keywords are matched, and the upper limit of the matching degree can be 100.

TABLE 3

Matching situation	Degree of matching
		Keyword matching	5
Keyword mismatch	0

Table 4 is an example of the correspondence between the matching situation and the degree of matching when the dimension is the job situation and the user selects a type of the job situation in the demand information. The job type may include, among others, job, retirement, and leave.

TABLE 4

Matching situation	Degree of matching
		Job condition matching	100
Job status mismatch	0

Table 5 is another example of the correspondence between the matching case and the degree of matching when the dimension is the job case and the user does not select the job case in the requirement information.

TABLE 5

Matching situation	Degree of matching
		At the job	100
Retire	60
		Leave job	10

Therefore, when the user selects the job condition, the expert can be recommended according to the selection of the user, and when the user does not select the job condition, the more appropriate expert can be recommended to the user according to the job condition of the expert.

Table 6 shows an example of the correspondence between the matching condition and the degree of matching when the dimension is the unit price. Where x1 is the difference between the unit price in the demand information of the user and the unit price of the history information of the expert.

TABLE 6

Matching situation	Degree of matching
		x1<5000	90
5000≤x1<7000	80
		7000≤x1<8500	60
8500≤x1<10000	40
		x1≥10000	20

As shown in table 6, the smaller the difference between the unit price of the expert and the unit price expected by the user is, the higher the matching degree of the corresponding dimension of the expert is, which is beneficial to pushing a more appropriate expert to the user.

Table 7 is an example of the correspondence between the matching condition and the matching degree when the dimension is job title and the user selects a type of job title in the demand information.

TABLE 7

Matching situation	Degree of matching
		Job title matching	100
Mismatch of job title	0

Table 8 shows another example of the correspondence between the matching condition and the degree of matching when the job type is not selected by the user in the demand information when the dimension is job title.

TABLE 8

Matching situation	Degree of matching
		Primary stage	40
Middle stage	60
		Advanced	100

Table 9 shows an example of the correspondence between the matching condition and the matching degree when the dimension is the number of repairs. In one possible implementation manner, the number of repairs of the demand information may be set to be null, and the matching degree may be determined only according to the matching situation between the rank of the number of repairs in the history information of the expert and each threshold interval shown in table 9. x2 ranks the number of repairs of the expert.

TABLE 9

Matching situation	Degree of matching
		x2≤10	100
11≤x2≤20	80
		21≤x2≤30	60
31≤x2≤50	40
		x2＞50	20

Table 10 shows an example of the correspondence between the matching condition and the degree of matching when the dimension is the one-time pass rate. In one possible implementation, the one-time pass rate of the demand information may be set to null, and the matching degree may be determined only based on the matching of the one-time pass rate in the history information of the expert with each threshold section shown in table 10. x3 is the expert's one-time pass rate.

Watch 10

Matching situation	Degree of matching
		x3＜60％	0
60％≤x3<75％	30
		75％≤x3<85％	60
85％≤x3<95％	80
		x3≥95％	100

Table 11 shows an example of the correspondence between the matching condition and the degree of matching when the dimension is the operating year. In one possible implementation manner, the working life of the demand information may be set to be null, and the matching degree may be determined only according to the matching condition between the working life in the history information of the expert and each threshold interval shown in table 11. x4 is the working life of the expert.

TABLE 11

Matching situation	Degree of matching
		x4<5	20
5≤x4<10	40
		10≤x4<15	60
15≤x4<20	80
		x4≥20	100

Table 12 shows an example of the correspondence between the matching condition and the matching degree when the dimension is the certification. In a possible implementation manner, the qualification certificate of the demand information may be set to be null, and the matching degree may be determined only according to the matching condition between the qualification certificate in the history information of the expert and each qualification certificate type shown in table 12.

TABLE 12

Matching situation	Degree of matching
		National professional qualifications five levels (primary skill)	20
National professional qualifications four-level (middle skill)	40
		National professional qualification three-level (high-grade skill)	60
National professional qualifications level two (technician)	80
		National professional qualification level one (senior technician)	100

Table 13 shows an example of the correspondence between the matching condition and the degree of matching when the dimension is the winning level. In one possible implementation, the winning level of the demand information may be set to null, and the matching degree may be determined only based on the matching between the winning level in the history information of the expert and each winning level type shown in table 13.

Watch 13

Matching situation	Degree of matching
		Company level	10
Group level	20
		Provincial level	35
National level	50

Table 14 is an example of the correspondence between the matching condition and the degree of matching when the dimension is the level of participating in the big item. In one possible implementation, the participation major item level of the demand information may be set to be null, and the matching degree may be determined only according to the matching condition between the participation major item level in the history information of the expert and each of the participation major item level types shown in table 14.

TABLE 14

Table 15 shows an example of the correspondence between the matching condition and the degree of matching when the dimension is a good rating.

In one possible implementation, the rating of the demand information may be set to null, and the matching degree may be determined only based on the matching condition between the rating in the history information of the expert and each threshold section shown in table 15.

Watch 15

Good rate (expressed by x)	Degree of matching
		x＝100％	100
80％≤x＜100％	80
		60％≤x＜80％	40
x＜60％	0

And finally, the expert recommending subsystem can take the experts with the matching degrees larger than a preset threshold value as recommending experts, and forms a recommending expert list according to the expert information of each recommending expert and sends the recommending expert list to the maintenance management subsystem.

S＝V1*A1+V2*A2+V3*A3+V4*A4+V5*A5+V6*A6+V7*A7+V8*A8+V9*A9+V10*A10+V11*A11+V12*A12+V13*A13

Wherein, V1 is the matching degree of the fault type of the expert, V2 is the matching degree of the fault keyword of the expert, V3 is the matching degree of the one-time maintenance passing rate of the expert, V4 is the matching degree of the rating rate of the expert, V5 is the matching degree of the maintenance quantity of the expert, V6 is the matching degree of the job condition of the expert, V7 is the matching degree of the company to which the expert belongs, V8 is the matching degree of the unit price of the expert, V9 is the matching degree of the title of the expert, V10 is the matching degree of the working year of the expert, V11 is the matching degree of the qualification certificate of the expert, V12 is the matching degree of the winning prize level of the expert, and V13 is the matching degree of the participation major project level of the expert; a1 is the weight of the matching degree of the fault type of the expert, A2 is the weight of the matching degree of the fault key words of the expert, A3 is the weight of the matching degree of the one-time maintenance passing rate of the expert, A4 is the weight of the matching degree of the good rating rate of the expert, A5 is the weight of the matching degree of the maintenance number of the expert, A6 is the weight of the matching degree of the situation under the job of the expert, A7 is the weight of the matching degree of the company to which the expert belongs, A8 is the weight of the matching degree of the unit price of the expert, A9 is the weight of the matching degree of the job name of the expert, A10 is the weight of the matching degree of the working year of the expert, A11 is the weight of the matching degree of the certificate of the expert, A12 is the weight of the matching degree of the prize winning level of the expert, and A13 is the matching degree of the major item participation level of the expert.

FIG. 2 is a flow diagram illustrating a method for expert recommendation based on an expert database in accordance with an exemplary embodiment. The method is applied with respect to a service expert repository, as shown in FIG. 2, and may include

200, receiving a query request sent by an expert recommendation subsystem;

step 201, determining the equipment type and the maintenance field contained in the query request according to the query request;

step 202, determining expert information of an expert whose equipment type and maintenance field are matched with the equipment type and maintenance field of the query request in the maintenance expert library;

and 203, forming a primary selection expert list according to the determined expert information, and sending the primary selection expert list to the expert recommendation subsystem.

The above description may be referred to for the description of step 200 to step 203, and will not be repeated herein.

In one possible implementation manner, the maintenance expert database may obtain the identifications of a plurality of target persons from the equipment management system, the work order management system, and the portal website to form an expert list;

for each expert in the list of experts, performing the following:

determining the favorable rating of the expert according to the comment data corresponding to the identification of the expert, which is acquired from the maintenance management subsystem;

and establishing a maintenance expert database according to the fault type, the one-time maintenance passing rate, the rating rate, the maintenance quantity, the working condition, the affiliated company, the unit price, the job title, the working age, the qualification certificate, the prize winning level, the participation major project level, the equipment type and the maintenance field corresponding to each expert.

In the embodiment of the present disclosure, the work order management system may be represented as a system that integrates information such as work flow, human resources, materials (inventory, purchase), technology (standard work plan, maintenance guide), safety (safety standard corresponding to the corresponding work order), cost (including human resource cost, cost of spare parts, and tool cost), and the like, which are related to a work order, and records all service data and information related to maintenance. Because the equipment maintenance management mainly takes the work order execution as a main line, the work order management system improves the scientific management level of the equipment to the maximum extent.

The equipment management system can be a standard equipment asset information structure established for all equipment, and is a database of equipment technology, management and operation standards established by taking equipment and parts as data objects, and can integrate equipment, operation, maintenance and spare part management. The device management system has administrative field information associated with personnel information. Such as: equipment management engineers, equipment maintenance engineers.

The change management system may be represented as an information base for recording all change data, and in general, the change may be referred to as a modification made to any aspect of materials, processes, functions, efficacies, dimensions, technical indexes, and the like of the equipment according to actual conditions, and a system, a field, and an equipment management engineer are generally responsible for issuing an equipment change design scheme.

The quality defect management system may be denoted as a system for recording an approved quality defect report, which may be denoted as a report of a defect description, handling measures, of a recording device. The quality defect management system forms a closed-loop management system for finding, reporting, processing, gradually progressing and closing the problems according to the quality defect report and the approval process.

Portal site: the method can be expressed as providing a uniform application entrance for enterprise employees, and realizing functions of service presentation, information presentation and the like. The employee winning information may be distributed at the enterprise.

Personnel management system: the personnel management system can comprise modules of personnel files, movement management, salary management, attendance management and the like, and can be used for maintaining basic information of personnel and managing procedures of post movement, attendance, leave requests and the like.

For example, the service expert database may be in communication with a work order management system, an equipment management system, a change management system, a quality defect management system, a web portal, and a personnel management system, respectively. The terminal device may extract an identification of a device management engineer (an example of a target person) from the device management system to form a device management expert list (an example of an expert list); the terminal device may extract an identification of a device maintenance engineer (an example of a target person) from the device management system to form a device maintenance expert list (an example of an expert list); the terminal device can extract the identification of a work responsible person (an example of a target person) from the work order management system to form a device field expert list (an example of an expert list); the identification of the winning person (example of the target person) is extracted from the web portal, forming a list of maintenance teachers (example expert list).

Wherein the identification of the expert may be represented as a field for uniquely identifying the expert, e.g., the identification of the expert may include a certificate number and/or name of the expert, etc. An equipment management expert may be said to be adept at managing work for a particular piece of equipment, tracking equipment defects, and making equipment changes. An equipment servicing expert may be said to be skilled in field servicing work for a particular piece of equipment, typically the job leader of a service order. The domain expert may be expressed as a maintenance expert who excels in a particular domain work order, without limitation to the equipment type. The service master may be denoted as a service specialist recognized in the industry.

The service record data corresponding to each expert may include a work order for the expert in the work order management system, a quality defect report for the expert in the quality defect management system, and a design change for equipment for the expert in the change management system.

For example, for each expert, the maintenance expert database may search, according to the identification of the expert, all work orders corresponding to the identification of the expert in the work order management system, and count the number of all work orders corresponding to the expert; the maintenance expert base can also search all quality defect reports corresponding to the identification of the expert in the quality defect management system according to the identification of the expert, and count the number of all quality defect reports corresponding to the expert; the maintenance expert database can also search all equipment change design schemes corresponding to the expert identification in the change management system according to the expert identification, and count the number of all equipment change design schemes corresponding to the expert; the maintenance expert database may use the sum of the number of work orders, the number of quality defect reports, and the number of equipment change design plans corresponding to the expert as the maintenance number of the expert. The number of repairs by the expert may be set to a weighted sum of the number of work orders, the number of quality defect reports, and the number of equipment change design plans corresponding to the expert.

For each maintenance expert of the nuclear power plant, in addition to the work order processed by the expert, the quality defect report and the equipment change design scheme processed by the expert can embody the maintenance work undertaken by the expert, so that the quantity of the maintenance work undertaken by the expert can be more comprehensively obtained by counting the work order of each expert in the work order management system, the quality defect report in the quality defect management system and the equipment change design scheme in the change management system.

For example, the service expert repository may determine a one-time service pass rate for the expert based on the number of work orders that the expert has passed at one time, the number of quality defect reports that have passed at one time, the number of equipment change designs that have passed at one time, and the number of services for the expert. The one-time maintenance passing rate can be expressed as the ratio of the passing maintenance to all the maintenance quantities of an expert when the expert performs maintenance and only performs one maintenance. The more the maintenance experience of a maintenance expert is rich, the higher the maintenance skill is, the higher the probability that the maintenance expert completes the maintenance work successfully at one time in the maintenance process is, so that the real maintenance capability level of the expert can be more accurately reflected by adopting the one-time maintenance passing rate as one of the evaluation dimensions to evaluate the maintenance capability of the expert.

In a possible implementation manner, for each expert, the service expert library may obtain all work orders corresponding to the expert in the work order management system, and the work order in which the to-be-approved state is recorded without rollback from the to-be-approved state and the in-work state is recorded without rollback from to-the-completed state in the work order corresponding to the expert is used as a one-time passing work order. The service expert repository may then count the number of all one-time-pass work orders for that expert.

In the work order management system, each work order can correspond to a plurality of states, and a rollback record (the rollback record can be represented as a record for rolling back from a next state to a previous state in a flow) may exist between two adjacent states, wherein when the rollback record exists between a to-be-approved state and an approved state corresponding to the work order or the rollback record exists between a working state and a working state, it is indicated that the maintenance quality corresponding to the work order has a problem and needs to be reworked.

In a possible implementation manner, for each expert, the service expert database may further obtain all quality defect reports corresponding to the expert in the quality defect management system, and the quality defect report of which the applied state is recorded in the approved state without rollback and the construction state is recorded in the closed state without rollback in the quality defect report corresponding to the identification of the expert is used as a one-time-pass quality defect report. The service expert repository may then count the number of quality defect reports for all one-time passes to which the expert corresponds.

In the quality defect management system, each quality defect report may correspond to a plurality of states, and a rollback record may exist between two adjacent states, wherein when a rollback record exists between an applied state and an approved state or between a construction state and a closing state corresponding to a quality defect report, it is indicated that the quality defect report has a defect and cannot pass through once.

In a possible implementation manner, for each expert, the service expert database may further obtain all equipment change design schemes corresponding to the expert in the change management system, and install, as a one-time-pass equipment change design scheme, an equipment change design scheme in which there is no rollback record in the approval process and no construction problem sheet between the implementation state and the changed state in the equipment change design schemes corresponding to the identification of the expert. The service expert database may then count the number of all single-pass equipment change designs to which the expert corresponds.

In the change management system, each equipment change design scheme can correspond to a plurality of states, and a rollback record may exist between two adjacent states, wherein when a rollback record exists in an approval process corresponding to the equipment change design scheme or a construction problem sheet exists between an installation implementation state and a changed state, it is indicated that the equipment change design scheme has a defect and cannot pass through once.

Finally, for each expert, the repair expert database may, for example, use the sum of the number of work orders that the expert has passed at one time, the number of quality defect reports that have passed at one time, and the number of equipment change designs that have passed at one time as the one-time pass repair number for the expert, and use the ratio between the one-time repair pass number for the expert and the repair number for the expert as the one-time repair pass rate for the expert.

The number of work orders that the expert has passed at one time, the number of quality defect reports that the expert has passed at one time, and the number of equipment change design plans that the expert has passed at one time may be weighted and used as the number of repair work orders that the expert has passed at one time.

In one possible implementation manner, for each expert, the maintenance expert database may obtain data of a leave-asking date corresponding to the identification of the expert from the personnel management system; acquiring scheduling data corresponding to the expert identification from the work order management system; the service expert database can prestore a working calendar, and can remove the leave-asking date corresponding to the expert and the occupied date in the scheduling data from the working calendar, and the remaining date is used as the available time for determining the expert.

Therefore, the built nuclear power plant maintenance expert library can display the available time of the experts, a demander can master the time arrangement of the maintenance experts, and the time arrangement conflict is effectively reduced.

Finally, a maintenance expert database can be established according to the fault type, the one-time maintenance passing rate, the rating rate, the maintenance quantity, the job condition, the affiliated company, the unit price, the job title, the working age, the qualification certificate, the prize winning level, the participation major project level, the equipment type and the maintenance field corresponding to each expert

The method and the system can widely obtain expert information from an equipment management system, a work order management system and a portal site, have wide coverage range, adopt the maintenance record data, the job title, the working age, the qualification certificate, the prize winning condition and other information of the expert for the capability evaluation of the expert, objectively and accurately evaluate and display the capability of the expert, and are beneficial to a user to select a maintenance expert with more appropriate capability. In addition, the method and the system can also acquire the conditions of post change, job leaving and the like of the expert in time, and reduce the influence on the decision of the user to the maximum extent, thereby integrating the factors of the ability, the time arrangement, the cost and the like of the expert and seeking the most suitable expert support.

In one possible implementation manner, the repair expert database may obtain, for each expert in the repair expert database, evaluation and comment information of an hirer for the expert from the repair management subsystem after the expert is recommended and hired to complete repair; judging the effectiveness of the evaluation corresponding to the expert according to the comment information corresponding to the expert; and determining the good evaluation rate of the expert according to the determined effective evaluation.

For example, the terminal device may employ the expert in the target expert list, and after the maintenance is completed, display a comment interface to prompt the hirer to evaluate the expert and submit comment information corresponding to the evaluation, where the comment information may be used to prove the validity of the comment. The terminal device may determine the validity of the evaluation according to the comment information. And taking the ratio of the number of good evaluations in the effective evaluations to the total number of effective evaluations as the good evaluation rate of the expert. According to the method and the system, after the expert is engaged to participate in maintenance, the evaluation aiming at the expert can be collected in time, the effectiveness judgment is carried out on the evaluation, the effective evaluation is obtained according to screening, and the good evaluation rate of the expert is obtained on the basis of the effective evaluation, so that the capability of the expert can be evaluated more objectively.

For example, the review information may be a quality defect report corresponding to the current maintenance, and if the evaluation is a bad evaluation or a medium evaluation and the state of the quality defect report corresponding to the evaluation is not a closed state, it is determined that the evaluation is valid; if the evaluation is poor evaluation or medium evaluation and the state of the quality defect report corresponding to the evaluation is a closing state, determining that the evaluation is invalid; if the evaluation is good evaluation and the state of the quality defect report corresponding to the evaluation is a closing state, determining that the evaluation is effective; and if the evaluation is good and the state of the quality defect report corresponding to the evaluation is not the closing state, determining that the evaluation is invalid.

The quality defect report corresponding to the maintenance is judged whether to be in the closed state or not by judging whether the quality defect report is in the closed state, so that whether the evaluation corresponding to the quality defect report is reasonable and effective or not can be effectively judged, more accurate screening can be facilitated, effective evaluation can be obtained, and the accuracy of expert capability evaluation is further improved.

FIG. 3 is a block diagram illustrating an expert database based expert recommendation system in accordance with an exemplary embodiment. As shown in fig. 3, the apparatus may include:

an expert recommendation subsystem 30, a service expert repository 31, and a service management subsystem 32;

the expert recommendation subsystem 30 is respectively connected with the maintenance management subsystem 32 and the maintenance expert database 31, and is configured to execute the expert recommendation method based on the expert database;

the service expert database 31 is used for executing the expert recommendation method based on the expert database;

the service management subsystem 32 is configured to display the received list of recommended experts.

Fig. 4 is a block diagram illustrating an expert database based expert recommender in accordance with an exemplary embodiment. For example, the apparatus 1900 may be provided as a server. Referring to fig. 4, the device 1900 includes a processing component 1922 further including one or more processors and memory resources, represented by memory 1932, for storing instructions, e.g., applications, executable by the processing component 1922. The application programs stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processing component 1922 is configured to execute instructions to perform the above-described method.

The device 1900 may also include a power component 1926 configured to perform power management of the device 1900, a wired or wireless network interface 1950 configured to connect the device 1900 to a network, and an input/output (I/O) interface 1958. The device 1900 may operate based on an operating system stored in memory 1932, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.

In an exemplary embodiment, a non-transitory computer readable storage medium, such as the memory 1932, is also provided that includes computer program instructions executable by the processing component 1922 of the apparatus 1900 to perform the above-described methods.

The present disclosure may be systems, methods, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement various aspects of the present disclosure.

The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.

The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.

The computer program instructions for carrying out operations of the present disclosure may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry that can execute the computer-readable program instructions implements aspects of the present disclosure by utilizing the state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).

Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein were chosen in order to best explain the principles of the embodiments, the practical application, or technical improvements to the techniques in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. An expert recommendation method based on an expert database, which is applied to an expert recommendation subsystem, and is characterized in that the method comprises the following steps:

2. The method according to claim 1, wherein the dimension of the requirement information comprises any one or more of fault type, fault keyword, one-time maintenance passing rate, rating rate, maintenance quantity, job condition, affiliated company, unit price, job title, working age, qualification certificate, prize winning level and important project participation level;

3. The method of claim 2, wherein the expert recommendation request includes a fault description, the fault description being a natural language describing the pending fault;

and performing semantic recognition on the fault description, and determining fault keywords in the demand information according to a semantic recognition result.

4. An expert recommendation method based on an expert database, wherein the method is applied to a maintenance expert database, and is characterized in that the method comprises the following steps:

receiving an inquiry request sent by an expert recommendation subsystem;

5. The method of claim 4, further comprising:

for each expert in the list of experts, performing the following:

6. The method of claim 5, wherein determining the one-time repair pass rate and repair quantity of the expert according to the repair record data corresponding to the identification of the expert, which is obtained from the work order management system, the quality defect management system and the change management system, comprises:

7. The method of claim 6, further comprising:

8. The method of claim 5, wherein determining the availability time of the expert based on the personnel management system and the work order management system comprises:

9. The method of claim 5, wherein determining the good rating of the expert based on the review data corresponding to the identification of the expert obtained from the service management subsystem comprises:

10. An expert recommendation system based on an expert database, the expert recommendation system based on an expert database comprising: the system comprises an expert recommending subsystem, a maintenance expert database and a maintenance management subsystem;

the expert recommendation subsystem is connected with the maintenance management subsystem and the maintenance expert database respectively and is used for executing the method according to any one of claims 1 to 3;

the service specialist library is used for carrying out the method according to any one of claims 4 to 9;

11. An expert recommendation apparatus based on an expert database, the apparatus comprising:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to perform the method of any of claims 1 to 3 or 4 to 9.

12. A non-transitory computer readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the method of any of claims 1 to 3 or claims 4 to 9.