CN113657805A

CN113657805A - Method, device, equipment and storage medium for constructing weights of assessment index system

Info

Publication number: CN113657805A
Application number: CN202111005933.6A
Authority: CN
Inventors: 王腾宽
Original assignee: Ping An Medical and Healthcare Management Co Ltd
Current assignee: Shenzhen Ping An Medical Health Technology Service Co Ltd
Priority date: 2021-08-30
Filing date: 2021-08-30
Publication date: 2021-11-16

Abstract

The invention relates to the field of artificial intelligence, is applied to the field of intelligent medical treatment, and provides a construction method, a device, equipment and a storage medium for a performance assessment index system weight, which are used for solving the problem that the performance assessment index system weight lacks objectivity. The construction method of the assessment index system weight comprises the following steps: screening key performance index data of original medical personnel according to index requirements corresponding to the post types to obtain target post performance index data; performing performance index value operation on input item data comprising medical staff attendance data and post value data and post index output item data comprising target post performance index data to obtain a post main performance index value; and calculating the weight of each post performance index based on the post main performance index value through a preset hierarchical analysis algorithm to obtain the weight of a target index system. In addition, the invention also relates to a block chain technology, and the target index system weight can be stored in the block chain.

Description

Method, device, equipment and storage medium for constructing weights of assessment index system

Technical Field

The invention relates to the field of intelligent decision of artificial intelligence, in particular to a construction method, a device, equipment and a storage medium for weights of an assessment index system.

Background

The construction of the medical association or the medical personnel individual performance assessment index system of the medical association is of great significance. Indexes in the performance assessment logic framework of each post personnel can reflect the personal working quality and efficiency, and can objectively evaluate personal contribution and post capability. The performance assessment index system weight of the medical personnel plays a key role in the performance assessment of the medical personnel.

Currently, the performance assessment index system weight of medical personnel is generally calculated by all the associated pointers in a linear mathematical mode. However, the weight of each index in the middle is determined too coarsely, and the weight of each index is mostly obtained after comprehensive scoring, so that the weight of the performance assessment index system is lack of objectivity.

Disclosure of Invention

The invention provides a construction method, a device, equipment and a storage medium for a performance assessment index system weight, which are used for solving the problem that the performance assessment index system weight lacks objectivity.

The invention provides a method for constructing the weights of an assessment index system in a first aspect, which comprises the following steps:

acquiring post data to be analyzed of a target intelligent hospital cluster, and acquiring post value data of the post data to be analyzed, which is estimated based on a preset post value estimation factor;

acquiring original medical personnel key performance index data and medical personnel attendance data of the target intelligent hospital cluster, and screening the original medical personnel key performance index data according to index requirements corresponding to the post types to obtain target post performance index data, wherein the target post performance index data is used for indicating target key performance index data of each post type, and the target key performance index data comprises each main post performance index and slave post performance index data corresponding to each main post performance index;

classifying the medical staff attendance data and the post value data into input item data, classifying the target post performance index data into post index production item data, and performing performance index value operation on the input item data and the post index production item data to obtain a post main performance index value, wherein the post index production item data is used for indicating data corresponding to each main post performance index of each post type and slave post performance index data corresponding to each main post performance index, and the post main performance index value is used for indicating a performance index value corresponding to each main post performance index of each post type;

and calculating the weight of each post performance index based on the post main performance index value through a preset hierarchical analysis algorithm to obtain a target index system weight, wherein the target index system weight comprises each target key performance index of each post type and the weight value corresponding to each target key performance index of each post type.

Optionally, in a first implementation manner of the first aspect of the present invention, the classifying the medical staff attendance data and the post value data into input item data, classifying the target post performance index data into post index production item data, and performing performance index value operation on the input item data and the post index production item data to obtain a post master performance index value includes:

classifying the medical staff attendance data and the post value data into input item data, and classifying the target post performance index data into post index output item data;

sequentially carrying out post value numerical calculation and post type numerical fusion on the medical staff attendance data and the post value data in the input item data to obtain an initial input item value, and acquiring slave post performance index data corresponding to each main post performance index from the post index output item data;

normalizing the initial input item values to obtain target input item values, and fusing and normalizing the slave post performance index data corresponding to the main post performance indexes to obtain output item values corresponding to the main post performance indexes;

and calculating the ratio of the target input item value to the output item value corresponding to each main post performance index to obtain a post main performance index value.

Optionally, in a second implementation manner of the first aspect of the present invention, the performing fusion normalization processing on the slave post performance indicator data corresponding to each master post performance indicator to obtain the output item value corresponding to each master post performance indicator includes:

carrying out numerical value normalization processing on the slave post performance index data corresponding to each main post performance index to obtain each slave post performance index normalization value set corresponding to each main post performance index;

performing arithmetic mean calculation on each secondary post performance index normalization value set corresponding to each primary post performance index to obtain each secondary post performance index fusion value corresponding to each primary post performance index;

and performing arithmetic mean calculation on the fusion value of the performance indexes of the slave posts corresponding to the performance indexes of the main posts to obtain the output item value corresponding to the performance index of the main post.

Optionally, in a third implementation manner of the first aspect of the present invention, the obtaining of the key performance indicator data of the original medical staff and the attendance data of the medical staff of the target intelligent hospital cluster, and screening the key performance indicator data of the original medical staff according to the indicator requirement corresponding to the post type to obtain the target post performance indicator data includes:

acquiring key performance index data of original medical personnel and attendance data of medical personnel of a target intelligent hospital cluster from a preset target intelligent hospital cluster alliance chain, acquiring index requirements corresponding to the post types, and creating index screening prefix trees of all the post types based on the index requirements corresponding to the post types through a preset prefix tree algorithm;

screening a prefix tree through the indexes of each post type, and performing index data matching of each post type on the key performance index data of the original medical personnel to obtain initial post performance index data;

and acquiring a verification post performance index of the original medical personnel key performance index data, and checking the initial post performance index data through the verification post performance index to obtain target post performance index data.

Optionally, in a fourth implementation manner of the first aspect of the present invention, the acquiring post data to be analyzed of the target intelligent hospital cluster, and acquiring post value data of the post data to be analyzed, which is evaluated based on a preset post value evaluation factor, includes:

retrieving a preset hospital post structure tree according to a target intelligent hospital cluster to obtain corresponding post data to be analyzed, preprocessing the post data to be analyzed to obtain preprocessed post data to be analyzed, wherein the target intelligent hospital cluster is used for indicating a medical complex and/or a medical community;

calling a preset Hai's post value evaluation system, and performing classification data fusion and weight selection on the preprocessed post data to be analyzed based on a preset post value evaluation factor to obtain target evaluation data;

and acquiring the post value data corresponding to the target evaluation data from a preset post value system database.

Optionally, in a fifth implementation manner of the first aspect of the present invention, the performing, by using a preset hierarchical analysis algorithm, weight calculation of each post performance indicator based on the post master performance indicator value to obtain a target indicator system weight, where the target indicator system weight includes each target key performance indicator of each post type and a weight value corresponding to each target key performance indicator of each post type, and the method includes:

calling a preset hierarchical analysis algorithm, and sequentially constructing a target hierarchical structure chart and a judgment matrix based on the post main performance index values for each target key performance index corresponding to each post type to obtain a target judgment matrix;

and carrying out iterative weight coefficient calculation, consistency check assignment updating and hierarchical total sequencing through the target judgment matrix to obtain a target index system weight, wherein the target index system weight comprises each target key performance indicator of each post type and a weight value corresponding to each target key performance indicator of each post type.

Optionally, in a sixth implementation manner of the first aspect of the present invention, after the performing, by using a preset hierarchical analysis algorithm, weight calculation of each post performance indicator based on the post master performance indicator value to obtain a target indicator system weight, the method further includes:

acquiring performance data of a medical staff cluster to be evaluated, and calculating performance values of the performance data of the medical staff cluster to be evaluated through the target index system weight to obtain the performance values of the medical staff corresponding to the medical staff to be evaluated;

and sequencing the medical personnel clusters to be evaluated according to the medical personnel performance values corresponding to the medical personnel to be evaluated to obtain medical personnel cluster performance assessment information, wherein the medical personnel cluster performance assessment information comprises the sequenced medical personnel to be evaluated and the sequenced medical personnel performance values of the medical personnel to be evaluated.

The second aspect of the present invention provides a device for constructing a weight of an assessment index system, comprising:

the acquisition module is used for acquiring post data to be analyzed of the target intelligent hospital cluster and acquiring post value data of the post data to be analyzed, which is estimated based on a preset post value estimation factor;

the system comprises a screening module, a processing module and a processing module, wherein the screening module is used for acquiring key performance index data of original medical personnel and attendance data of the medical personnel of the target intelligent hospital cluster, screening the key performance index data of the original medical personnel according to index requirements corresponding to the post types to obtain target post performance index data, the target post performance index data is used for indicating the target key performance index data of each post type, and the target key performance index data comprises each main post performance index and slave post performance index data corresponding to each main post performance index;

the operation module is used for classifying the medical staff attendance data and the post value data into input item data, classifying the target post performance index data into post index output item data, and performing performance index value operation on the input item data and the post index output item data to obtain a post main performance index value, wherein the post index output item data is used for indicating data corresponding to each main post performance index of each post type and slave post performance index data corresponding to each main post performance index, and the post main performance index value is used for indicating a performance index value corresponding to each main post performance index of each post type;

and the weight calculation module is used for calculating the weight of each post performance index based on the post main performance index value through a preset hierarchical analysis algorithm to obtain a target index system weight, and the target index system weight comprises each target key performance index of each post type and a weight value corresponding to each target key performance index of each post type.

Optionally, in a first implementation manner of the second aspect of the present invention, the operation module includes:

the classification unit is used for classifying the attendance data of the medical staff and the post value data into input item data and classifying the target post performance index data into post index output item data;

the calculation fusion unit is used for sequentially carrying out post value numerical calculation and post type numerical fusion on the medical staff attendance data and the post value data in the input item data to obtain an initial input item value, and acquiring slave post performance index data corresponding to each main post performance index from the post index output item data;

the normalization unit is used for carrying out normalization processing on the initial input item values to obtain target input item values, and carrying out fusion normalization processing on the slave post performance index data corresponding to each main post performance index to obtain an output item value corresponding to each main post performance index;

and the calculating unit is used for calculating the ratio of the target input item value to the output item value corresponding to each main post performance index to obtain the post main performance index value.

Optionally, in a second implementation manner of the second aspect of the present invention, the normalization unit is specifically configured to:

Optionally, in a third implementation manner of the second aspect of the present invention, the screening module is specifically configured to:

Optionally, in a fourth implementation manner of the second aspect of the present invention, the obtaining module is specifically configured to:

Optionally, in a fifth implementation manner of the second aspect of the present invention, the weight calculating module is specifically configured to:

Optionally, in a sixth implementation manner of the second aspect of the present invention, the apparatus for constructing the assessment index system weight further includes:

the performance calculation module is used for acquiring performance data of the medical staff cluster to be evaluated, and performing performance value calculation on the performance data of the medical staff cluster to be evaluated through the target index system weight to obtain the performance value of the medical staff corresponding to each medical staff to be evaluated;

and the sequencing module is used for sequencing the medical personnel clusters to be evaluated according to the medical personnel performance values corresponding to the medical personnel to be evaluated to obtain medical personnel cluster performance assessment information, and the medical personnel cluster performance assessment information comprises the sequenced medical personnel to be evaluated and the sequenced medical personnel performance values of the medical personnel to be evaluated.

The third aspect of the present invention provides an apparatus for constructing a weight of an assessment index system, comprising: a memory and at least one processor, the memory having stored therein a computer program; the at least one processor calls the computer program in the memory to cause the construction device of the assessment index system weight to execute the construction method of the assessment index system weight.

A fourth aspect of the present invention provides a computer-readable storage medium having stored therein a computer program which, when run on a computer, causes the computer to execute the above-described assessment index system weight construction method.

According to the technical scheme, the method comprises the steps of obtaining to-be-analyzed position data of a target intelligent hospital cluster, and obtaining position value data of the to-be-analyzed position data estimated based on a preset position value estimation factor; acquiring original medical personnel key performance index data and medical personnel attendance data of a target intelligent hospital cluster, and screening the original medical personnel key performance index data according to index requirements corresponding to the post types to obtain target post performance index data, wherein the target post performance index data is used for indicating target key performance index data of each post type, and the target key performance index data comprises each main post performance index and slave post performance index data corresponding to each main post performance index; classifying the attendance data and the post value data of medical personnel into input item data, classifying the target post performance index data into post index output item data, and performing performance index value operation on the input item data and the post index output item data to obtain a post main performance index value, wherein the post index output item data is used for indicating data corresponding to each main post performance index of each post type and slave post performance index data corresponding to each main post performance index, and the post main performance index value is used for indicating a performance index value corresponding to each main post performance index of each post type; and calculating the weight of each post performance index based on the post main performance index value through a preset hierarchical analysis algorithm to obtain a target index system weight, wherein the target index system weight comprises each target key performance index of each post type and a weight value corresponding to each target key performance index of each post type. In the embodiment of the invention, the post value data is obtained to lay a foundation for accurate and effective calculation of subsequent weight, the performance index data is screened according to the index requirements corresponding to the post types, the accuracy of the target post performance index data and the multi-dimensional fine granularity are ensured, and after the input items and the output items are split in the measuring mode, the weighted value is calculated by a hierarchical analysis algorithm, so that the weight of each intermediate index is determined to be fine, accurate and objective, the effect that the weight of a performance assessment index system has objectivity is realized, and the problem that the weight of the performance assessment index system lacks objectivity is solved.

Drawings

FIG. 1 is a schematic diagram of an embodiment of a method for constructing weights of an assessment index system in an embodiment of the invention;

FIG. 2 is a schematic diagram of another embodiment of the method for constructing the weights of the assessment index system in the embodiment of the invention;

FIG. 3 is a schematic diagram of an embodiment of a device for constructing the weights of the assessment indicators in the embodiment of the invention;

FIG. 4 is a schematic diagram of another embodiment of the device for constructing the weights of the assessment indicators in the embodiment of the invention;

FIG. 5 is a schematic diagram of an embodiment of a device for constructing the weights of the assessment index system in the embodiment of the invention.

Detailed Description

The embodiment of the invention provides a construction method, a device, equipment and a storage medium for the weight of an assessment index system, and solves the problem that the weight of a performance assessment index system is lack of objectivity.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

For easy understanding, a specific flow of the embodiment of the present invention is described below, and referring to fig. 1, an embodiment of the method for constructing the check index system weight in the embodiment of the present invention includes:

101. and acquiring the post data to be analyzed of the target intelligent hospital cluster, and acquiring the post value data of the post data to be analyzed, which is estimated based on a preset post value estimation factor.

It is understood that the executing subject of the present invention may be a device for constructing the evaluation index system weight, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), and a big data and artificial intelligence platform.

The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

The target intelligent hospital cluster is used for indicating a medical union and/or a medical community, the station data to be analyzed is used for indicating information of each station of each hospital in the target intelligent hospital cluster, the station data to be analyzed can include but is not limited to names, definition descriptions, work responsibilities, work summaries and the like of each station to be analyzed, the preset station value evaluation factors can include but is not limited to professional quality factors, professional skill factors and professional comprehensive capacity factors, the professional quality factors are used for indicating knowledge skills, the professional skill factors are used for indicating problem solving, the professional comprehensive capacity factors are used for indicating responsibility, the station value data comprises target evaluation data and work compensation data corresponding to the target evaluation data, and the target evaluation data comprises evaluation grades, evaluation scores and preset station value evaluation factor weights of the stations.

The server generates a structured query statement of the target intelligent hospital cluster and the post, and retrieves the preset database through the structured query statement to obtain corresponding post data to be analyzed. Performing multi-dimensional grade data matching (evaluation of post labor intensity and labor environment) on post data to be analyzed based on a preset post value evaluation factor and preset grade evaluation data by a preset Hai's system method to obtain grade data corresponding to each dimension, fusing the grade data corresponding to each dimension to obtain dimension evaluation data (namely evaluation grade and evaluation score), performing post evaluation factor weight distribution on the post data to be analyzed to obtain preset post value evaluation factor weight, determining the dimension evaluation data and the preset post value evaluation factor weight as target evaluation data, and obtaining work compensation data corresponding to the target evaluation data to obtain the post value data, wherein the preset Hai's system method is applied to a preset Hai's system, and the grade data comprises the evaluation grade and the evaluation score corresponding to the evaluation grade, one preset post value evaluation factor corresponds to one dimension.

102. The method comprises the steps of obtaining original medical staff key performance index data and medical staff attendance data of a target intelligent hospital cluster, screening the original medical staff key performance index data according to index requirements corresponding to post types to obtain target post performance index data, wherein the target post performance index data is used for indicating target key performance index data of each post type, and the target key performance index data comprises each main post performance index and slave post performance index data corresponding to each main post performance index.

The server extracts original medical staff key performance index data and medical staff attendance data of a target intelligent hospital cluster from a preset target intelligent hospital cluster alliance chain to ensure that the data of the original medical staff key performance index data and the medical staff attendance data of the target intelligent hospital cluster are safely, efficiently and accurately obtained, wherein the preset target intelligent hospital cluster alliance chain is a set formed by private chains of the target intelligent hospital cluster, the preset target intelligent hospital cluster alliance chain stores the original key performance index data and the medical staff attendance data of the target intelligent hospital cluster, the original medical staff key performance index data comprises Key Performance Index (KPI) data of the medical staff cluster corresponding to the post type, and the key performance index data of the medical staff cluster can be data (namely comprehensive data) obtained by arithmetically averaging the key performance index data of each medical staff, the key performance indicator data of the medical personnel cluster can also be key performance indicator data of all medical personnel, and the key performance indicator data comprises key performance indicators and numerical values corresponding to the key performance indicators.

Matching the key performance index data of the original medical personnel with the index requirements corresponding to the post types through a preset matching algorithm to obtain the performance index data of the target post, the matching algorithm may be a string matching algorithm, a prefix tree algorithm, or other matching algorithms, which are not limited herein, or, through a preset classification algorithm, according to the index requirements corresponding to the post types, classifying and filtering the key performance index data of the original medical personnel to obtain the performance index data of the target post, the classification algorithm may be a classification algorithm based on association rules, or a classification model composed of a deep convolutional neural network, or other classification algorithms, which are not limited herein, the index requirement corresponding to the post type is used for indicating an index required by the post type for performance assessment, the post type is used for indicating a general term of the post, and the post type is, for example: clinicians and caregivers. The target post performance index data is used for indicating target key performance index data corresponding to each post type, the target post performance index data (target key performance index data) comprises each main post performance index and slave post performance index data corresponding to each main post performance index, the slave post performance index data can comprise the comprehensive values (namely average values) of all medical staff corresponding to the slave post performance indexes and the slave post performance indexes, and the slave post performance index data can also comprise the numerical values of all medical staff corresponding to the slave post performance indexes and the slave post performance indexes.

103. The method comprises the steps of classifying medical staff attendance data and post value data into input item data, classifying target post performance index data into post indicator production item data, and performing performance index value operation on the input item data and the post indicator production item data to obtain a post main performance index value, wherein the post indicator production item data are used for indicating data corresponding to each main post performance index of each post type and slave post performance index data corresponding to each main post performance index, and the post main performance index value is used for indicating a performance index value corresponding to each main post performance index of each post type.

The server classifies the attendance data and the post value data of the medical personnel into input item data, classifies the target post performance index data into output item data corresponding to the key performance indexes of each post type, and obtains post index output item data; calculating a target input item value according to the attendance data of the medical staff and the post value data, wherein the target input item value is a post value comprehensive value of all the medical staff corresponding to each post type, calculating an output value corresponding to each main post performance index of each post type according to the slave post performance index data corresponding to each main post performance index to obtain an output item value corresponding to each main post performance index, and the output item value corresponding to each main post performance index is a slave post performance index comprehensive value corresponding to each main post performance index of each post type; and calculating the ratio of the target input item value to the output item value corresponding to each main post performance index to obtain a performance index value corresponding to each main post performance index of each post type, namely the post main performance index value.

104. And calculating the weight of each post performance index based on the post main performance index value through a preset hierarchical analysis algorithm to obtain a target index system weight, wherein the target index system weight comprises each target key performance index of each post type and a weight value corresponding to each target key performance index of each post type.

The server calls a preset hierarchical analysis algorithm, and sequentially carries out target layer decomposition and hierarchical structure chart establishment on each target key performance index corresponding to each post type to obtain a target hierarchical structure chart; constructing a target judgment matrix according to the post main performance index values and the target level structure chart, wherein the target judgment matrix comprises each main post performance index of each post type in the target level structure chart and the post main performance index values corresponding to each main post performance index of each post type; calculating a weight coefficient by judging the target matrix to obtain an initial weight coefficient of each index in the target level structure chart; carrying out consistency check on the judgment matrix to obtain a check result, and carrying out assignment updating on the initial weight coefficient of each index in the target level structure chart according to the check result to obtain a candidate weight coefficient of each index in the target level structure chart; and performing hierarchical total ordering on the candidate weight coefficients of each index in the target hierarchical structure chart to obtain an optimal scheme, namely a target index system weight, wherein the target index system weight comprises each target key performance index of each post type and a weight value corresponding to each target key performance index of each post type.

In the embodiment of the invention, the post value data is obtained to lay a foundation for accurate and effective calculation of subsequent weight, the performance index data is screened according to the index requirements corresponding to the post types, the accuracy of the target post performance index data and the multi-dimensional fine granularity are ensured, and after the input items and the output items are split in the measuring mode, the weighted value is calculated by a hierarchical analysis algorithm, so that the weight of each intermediate index is determined to be fine, accurate and objective, the effect that the weight of a performance assessment index system has objectivity is realized, and the problem that the weight of the performance assessment index system lacks objectivity is solved. This scheme can be applied to in the wisdom medical field to promote the construction in wisdom city.

Referring to fig. 2, another embodiment of the method for constructing the assessment index system weight according to the embodiment of the present invention includes:

201. and acquiring the post data to be analyzed of the target intelligent hospital cluster, and acquiring the post value data of the post data to be analyzed, which is estimated based on a preset post value estimation factor.

Specifically, the server searches a preset hospital post structure tree according to a target intelligent hospital cluster to obtain corresponding post data to be analyzed, the post data to be analyzed is preprocessed to obtain preprocessed post data to be analyzed, and the target intelligent hospital cluster is used for indicating a medical union and/or a medical community; calling a preset Hai's post value evaluation system, and performing classification data fusion and weight selection on the preprocessed post data to be analyzed based on a preset post value evaluation factor to obtain target evaluation data; and acquiring the post value data corresponding to the target evaluation data from a preset post value system database.

The server generates key values of a target intelligent hospital cluster, retrieves a preset hospital post structure tree to obtain corresponding post data to be analyzed, wherein the preset hospital post structure tree comprises the post data of all hospitals in the target intelligent hospital cluster, and the target intelligent hospital cluster is used for indicating a medical union and/or a medical community; abnormal value detection, null value filling and data format standardization are carried out on the post data to be analyzed so as to realize the pretreatment of the post data to be analyzed and obtain the pretreated post data to be analyzed; and calling a preset feature extraction model, and performing feature extraction on the preprocessed post data to be analyzed to obtain post feature information, wherein the feature extraction model is formed based on an artificial intelligence neural network, and the feature extraction model can be used for performing multi-level feature extraction and multi-level feature fusion on the preprocessed post data to be analyzed, so that the post feature information is obtained.

Calling a preset Hai's station value evaluation system, carrying out multi-dimensional grade data matching (evaluation of station labor intensity and labor environment) on the station characteristic information and preset grade evaluation data of the preset Hai's station value evaluation system based on a preset station value evaluation factor to obtain grade data corresponding to each dimension; carrying out weighted summation on the evaluation scores in the grade data corresponding to the dimensions, and merging the evaluation grades in the grade data corresponding to the dimensions, or determining the grade data corresponding to the dimensions as dimension evaluation data so as to obtain dimension evaluation data (namely the evaluation grades and the evaluation scores) to realize classification data fusion; performing post evaluation factor weight distribution on the post characteristic information to obtain a preset post value evaluation factor weight, and determining dimension evaluation data and the preset post value evaluation factor weight as target evaluation data; and retrieving a preset post value system database according to the target evaluation data to obtain corresponding work compensation data, namely the post value data, wherein the preset Hai's system method is applied to a preset Hai's post value evaluation system, the grade data comprises evaluation grades and evaluation scores corresponding to the evaluation grades, one preset post value evaluation factor corresponds to one dimension, and the preset post value system database comprises the work compensation data of each post in the post compensation system. The standard unification and the relative internal fairness of the post value data are ensured.

202. The method comprises the steps of obtaining original medical staff key performance index data and medical staff attendance data of a target intelligent hospital cluster, screening the original medical staff key performance index data according to index requirements corresponding to post types to obtain target post performance index data, wherein the target post performance index data is used for indicating target key performance index data of each post type, and the target key performance index data comprises each main post performance index and slave post performance index data corresponding to each main post performance index.

Specifically, the server acquires key performance index data and attendance data of original medical personnel of a target intelligent hospital cluster from a preset target intelligent hospital cluster alliance chain, acquires index requirements corresponding to the post types, and creates index screening prefix trees of all the post types based on the index requirements corresponding to the post types through a preset prefix tree algorithm; screening the prefix tree through the indexes of each post type, and performing index data matching of each post type on the key performance index data of the original medical personnel to obtain initial post performance index data; and obtaining a verification post performance index of the key performance index data of the original medical personnel, and verifying the initial post performance index data through the verification post performance index to obtain target post performance index data.

The server extracts original medical staff key performance index data and medical staff attendance data of a target intelligent hospital cluster from a preset target intelligent hospital cluster alliance chain, and desensitizes the original medical staff key performance index data and the medical staff attendance data respectively to obtain preprocessed original medical staff key performance index data and preprocessed medical staff attendance data; the index requirements corresponding to the post types can be obtained by receiving the index requirements corresponding to the post types input by the user and sent by the target terminal; constructing an index screening prefix tree of each post type based on index requirements corresponding to the post types through a preset prefix tree algorithm; traversing the index screening prefix trees of all the post types according to the key performance index data of the original medical personnel to obtain the initial post performance index data, wherein the initial post performance index data is used for indicating the key performance index data of the medical personnel matched with the index screening prefix trees of all the post types.

Calling a preset classification algorithm, classifying the key performance index data of the original medical personnel based on the index requirements corresponding to the post types to obtain the performance index data of the verification post, wherein the classification algorithm can be a classification algorithm based on association rules or a classification model formed by a deep convolutional neural network or other classification algorithms, and is not limited herein; the execution process for verifying the initial post performance indicator data by verifying the post performance indicator comprises the following steps: judging whether the post performance index in the initial post performance index data is consistent with the verification post performance index, if so, determining the initial post performance index data as target post performance index data; and if not, sending the inconsistent initial post performance index data to the target terminal, receiving the corrected initial post performance index data returned by the target terminal, and determining the consistent initial post performance index data and the corrected initial post performance index data as the target post performance index data.

203. The medical staff attendance data and the post value data are classified into input item data, and the target post performance index data is classified into post index output item data.

The server classifies the attendance data and the post value data of the medical personnel into input item data, classifies the target post performance index data into output item data corresponding to the key performance indexes of each post type, and obtains post index output item data.

204. And sequentially carrying out post value numerical value calculation and post type numerical value fusion on the medical staff attendance data and the post value data in the input item data to obtain an initial input item value, and acquiring the slave post performance index data corresponding to each main post performance index from the post index output item data.

When the medical staff attendance data comprise the attendance rate, the server calculates the product of the medical staff attendance data and the post value data in the input item data to obtain the post value numerical value of each medical staff of each post type; when the medical staff attendance data comprises attendance days, acquiring the total attendance days, calculating the ratio of the attendance days to the total attendance days to obtain the attendance rate, and calculating the product of the attendance rate and the staff value data to obtain the staff value values of the medical staff of each staff type; calculating the arithmetic mean value of the post value values of the medical personnel of each post type to obtain an initial input item value; and extracting the slave post performance index data corresponding to the master post performance indexes from the post index production item data.

205. And normalizing the initial input item values to obtain target input item values, and fusing and normalizing the slave post performance index data corresponding to the main post performance indexes to obtain output item values corresponding to the main post performance indexes.

The server normalizes the initial input item value through a preset normalization algorithm to obtain a target input item value, and numerically normalizes the initial input item value, wherein the normalization algorithm can be a (0, 1) normalization algorithm or a Z-score normalization algorithm or a Sigmoid function.

Specifically, the server carries out numerical value normalization processing on the slave post performance index data corresponding to each master post performance index to obtain each slave post performance index normalization value set corresponding to each master post performance index; carrying out arithmetic mean calculation on each secondary post performance index normalization value set corresponding to each primary post performance index to obtain each secondary post performance index fusion value corresponding to each primary post performance index; and performing arithmetic mean calculation on the fusion value of the performance indexes of the slave posts corresponding to the performance indexes of the main posts to obtain the output item value corresponding to the performance index of the main post.

For example, the post type is the clinician, the main post performance index corresponding to the clinician is the post professional ability, the sub-post performance index corresponding to the post professional ability is the professional base and the clinical ability (problem solving ability), the sub-post performance index data is the professional base and the professional base value 60 of the medical staff 1, the clinical ability and the clinical ability value 80 of the medical staff 1, the professional base and the professional base value 90 of the medical staff 2, the clinical ability and the clinical ability value 85 of the medical staff 2, the professional base and the professional base value 80 of the medical staff 3, and the clinical ability value 94 of the medical staff 3, and the professional base value 60 of the medical staff 1, the professional base value 90 of the medical staff 2, and the professional base value 80 of the medical staff 3 are numerically normalized to obtain the professional base normalized value 0.60, and the professional base normalized value 94 of the medical staff 1, The medical staff 2 professional basic normalization value is 0.90, the medical staff 3 professional basic normalization value is 0.80, namely each of the main post performance indicators corresponds to each of the post performance indicator normalization value sets, the medical staff 1 clinical ability value 80, the medical staff 2 clinical ability value 85 and the medical staff 3 clinical ability value 94 are subjected to numerical value normalization processing, and the medical staff 1 clinical ability normalization value is 0.80, the medical staff 2 clinical ability normalization value is 0.85 and the medical staff 3 clinical ability normalization value is 0.94, namely each of the main post performance indicators corresponds to each of the post performance indicator normalization value sets; performing arithmetic mean calculation on a professional basic normalized value 0.60 of the medical staff 1, a professional basic normalized value 0.90 of the medical staff 2 and a professional basic normalized value 0.80 of the medical staff 3 to obtain a professional basic fusion value 0.767, namely, a fusion value of each slave post performance index corresponding to each master post performance index, and performing arithmetic mean calculation on a clinical capability normalized value 0.80 of the medical staff 1, a clinical capability normalized value 0.85 of the medical staff 2 and a clinical capability normalized value 0.94 of the medical staff 3 to obtain a clinical capability fusion value 0.863, namely, a fusion value of each slave post performance index corresponding to each master post performance index; and performing arithmetic mean calculation on the professional basic fusion value 0.767 and the clinical ability fusion value 0.863 to obtain the post professional ability output item value 0.815, namely the output item value corresponding to each main post performance index.

206. And calculating the ratio of the target input item value to the output item value corresponding to each main post performance index to obtain the post main performance index value.

For example, taking the post type as the clinician and the main post performance index corresponding to the clinician as the post professional ability as an example, the target input item value is 0.780, the output item value of the post professional ability is 0.815, and the calculated target input item value of 0.780/output item value of the post professional ability of 0.815 is equal to the post professional ability index value of 0.957 corresponding to the clinician, that is, the post main performance index value.

207. And calculating the weight of each post performance index based on the post main performance index value through a preset hierarchical analysis algorithm to obtain a target index system weight, wherein the target index system weight comprises each target key performance index of each post type and a weight value corresponding to each target key performance index of each post type.

Specifically, the server calls a preset hierarchical analysis algorithm, and sequentially constructs a target hierarchical structure diagram and a judgment matrix based on post main performance index values for each target key performance index corresponding to each post type to obtain a target judgment matrix; and carrying out iterative weight coefficient calculation, consistency check assignment updating and hierarchical total sequencing through the target judgment matrix to obtain a target index system weight, wherein the target index system weight comprises each target key performance indicator of each post type and a weight value corresponding to each target key performance indicator of each post type.

For example, step one: the server calls a preset hierarchical analysis algorithm, and sequentially carries out target layer decomposition and hierarchical structure chart establishment on each target key performance index corresponding to each post type to obtain a target hierarchical structure chart; step two: constructing a target judgment matrix according to the post main performance index values and the target hierarchical structure chart, wherein the target judgment matrix comprises the ratio of each main post performance index of each post type in the target hierarchical structure chart to the post main performance index value corresponding to each main post performance index of each post type, such as: taking the post type as a clinician, taking the main post performance index corresponding to the clinician as one of the target judgment matrixes corresponding to the economic benefit, the post professional ability, the quality and the efficiency and the workload as an example, the post main performance index value of the economic benefit is A, the post main performance index value of the post professional ability is B, the post main performance index value of the quality and the efficiency is C, the post main performance index value of the workload is D, and the target judgment matrix is D

Step three: for example, taking the initial weight coefficient of economic benefit as an example, if the initial weight coefficient of economic benefit is (1/E + B/a/E + C/a/G + D/a/H)/4 is 0.451, and so on, the initial weight coefficient of post professional ability is 0.217, the initial weight coefficient of quality and efficiency is 0.235, the initial weight coefficient of workload is 0.097, and the initial weight coefficients corresponding to the target judgment matrix are as shown in table 1 below:

table 1: initial weight coefficient corresponding to target judgment matrix

(ii) a Step four: carrying out consistency check on the judgment matrix to obtain a check result, carrying out assignment updating on the initial weight coefficient of each index in the target level structure chart according to the check result to obtain a candidate weight coefficient of each index in the target level structure chart, further determining the initial weight coefficient of each index in the target level structure chart as the candidate weight coefficient of each index in the target level structure chart if the check result is that the consistency index CR is less than 0.1, and re-executing the third step if the check result is that the consistency index CR is greater than or equal to 0.1 until the check result is that the consistency index CR is less than 0.1 to obtain the candidate weight coefficient of each index in the target level structure chart; step five: and performing hierarchical total ordering on the candidate weight coefficients of each index in the target hierarchical structure chart to obtain an optimal scheme, namely an index system weight, wherein the index system weight comprises each target key performance index of each post type and a weight value corresponding to each target key performance index of each post type.

Target index system weights are for example: the method is characterized in that the post type is used as a clinician, the main post performance indexes corresponding to the clinician are economic benefit, post professional ability, quality, efficiency and workload, the secondary post performance indexes of the economic benefit are gross income, the same-period ratio of the gross income in the month and the gross income in the last year and the per-person proportion, the secondary post performance indexes of the post professional ability are professional foundation and clinical ability (problem solving ability), the secondary post performance indexes of the quality and the efficiency are medical record quality, daily filing rate and 18 core system standard reaching rates, the secondary post performance indexes of the workload are outpatient service quantity, intermediate operation quantity (to be discussed), minor operation quantity (including medical beauty, oral root management and other service quantity (puncture and oral orthodontics), and the target index system weight of the clinician is taken as an example, and is shown in the following table 2:

table 2: target index system weight

Specifically, the server calculates the weight of each post performance index based on the post main performance index value through a preset hierarchical analysis algorithm to obtain the weight of a target index system, then obtains the performance data of the medical staff cluster to be evaluated, and calculates the performance value of the performance data of the medical staff cluster to be evaluated through the weight of the target index system to obtain the performance value of the medical staff corresponding to each medical staff to be evaluated; and sequencing the medical personnel clusters to be evaluated according to the medical personnel performance values corresponding to the medical personnel to be evaluated to obtain medical personnel cluster performance assessment information, wherein the medical personnel cluster performance assessment information comprises the sequenced medical personnel to be evaluated and the sequenced medical personnel performance values of the medical personnel to be evaluated.

The server acquires performance data of a medical staff cluster to be evaluated from a preset target intelligent hospital cluster alliance chain, performs post type classification on the medical staff cluster to be evaluated to obtain the post type of each medical staff to be evaluated, and performs index data classification on the performance data of the medical staff cluster to be evaluated to obtain post index data corresponding to each medical staff to be evaluated; acquiring corresponding index system weight from the target index system weight according to the post type of each medical worker to be evaluated to obtain the post index system weight corresponding to each medical worker to be evaluated; calculating a weighted summation value of the post index data corresponding to each medical staff to be evaluated and the post index system weight corresponding to the post index data corresponding to each medical staff to be evaluated to obtain a medical staff performance value corresponding to each medical staff to be evaluated; sequencing medical personnel clusters to be evaluated according to the sequence of the performance values of the medical personnel corresponding to the medical personnel to be evaluated from large to small to obtain a sequence of the medical personnel to be evaluated (namely the sequenced medical personnel to be evaluated), and determining the sequence of the medical personnel to be evaluated and the performance values of the medical personnel corresponding to the sequence of the medical personnel to be evaluated (namely the sequenced performance values of the medical personnel to be evaluated) as the performance assessment information of the medical personnel clusters. Based on the objective target index system weight, the accuracy of the performance assessment information of the medical personnel cluster is improved.

In the above description of the method for constructing the assessment index system weight in the embodiment of the present invention, the following description of the apparatus for constructing the assessment index system weight in the embodiment of the present invention refers to fig. 3, and an embodiment of the apparatus for constructing the assessment index system weight in the embodiment of the present invention includes:

the acquisition module 301 is configured to acquire post data to be analyzed of the target intelligent hospital cluster and acquire post value data of the post data to be analyzed, which is estimated based on a preset post value estimation factor;

the screening module 302 is configured to obtain original medical staff key performance indicator data and medical staff attendance data of a target intelligent hospital cluster, screen the original medical staff key performance indicator data according to indicator requirements corresponding to post types to obtain target post performance indicator data, where the target post performance indicator data is used to indicate target key performance indicator data of each post type, and the target key performance indicator data includes each main post performance indicator and slave post performance indicator data corresponding to each main post performance indicator;

the operation module 303 is configured to classify the medical staff attendance data and the post value data into input item data, classify the target post performance index data into post index output item data, and perform performance index value operation on the input item data and the post index output item data to obtain a post master performance index value, where the post index output item data is used to indicate data corresponding to each master post performance index of each post type and slave post performance index data corresponding to each master post performance index, and the post master performance index value is used to indicate a performance index value corresponding to each master post performance index of each post type;

and the weight calculation module 304 is configured to perform weight calculation on each post performance indicator based on the post master performance indicator value through a preset hierarchical analysis algorithm to obtain a target indicator system weight, where the target indicator system weight includes each target key performance indicator of each post type and a weight value corresponding to each target key performance indicator of each post type.

The function implementation of each module in the device for constructing the assessment index system weight corresponds to each step in the embodiment of the method for constructing the assessment index system weight, and the function and implementation process are not described in detail herein.

Referring to fig. 4, another embodiment of the apparatus for constructing an assessment index system weight according to the embodiment of the present invention includes:

the operation module 303 specifically includes:

a classification unit 3031, configured to classify the attendance data and the post value data of the medical staff as entry data, and classify the target post performance indicator data as post indicator production data;

a calculation fusion unit 3032, configured to sequentially perform post value numerical calculation and post type numerical fusion on the attendance data and the post value data of the medical staff in the investment item data to obtain an initial investment item value, and obtain slave post performance index data corresponding to each master post performance index from the post index production item data;

a normalization unit 3033, configured to perform normalization processing on the initial input item values to obtain target input item values, and perform fusion normalization processing on the slave post performance indicator data corresponding to each master post performance indicator to obtain output item values corresponding to each master post performance indicator;

a calculating unit 3034, configured to calculate a ratio between the target input item value and the output item value corresponding to each main post performance indicator, so as to obtain a post main performance indicator value;

Optionally, the normalizing unit 3033 may be further specifically configured to:

carrying out arithmetic mean calculation on each secondary post performance index normalization value set corresponding to each primary post performance index to obtain each secondary post performance index fusion value corresponding to each primary post performance index;

Optionally, the screening module 302 may be further specifically configured to:

screening the prefix tree through the indexes of each post type, and performing index data matching of each post type on the key performance index data of the original medical personnel to obtain initial post performance index data;

and obtaining a verification post performance index of the key performance index data of the original medical personnel, and verifying the initial post performance index data through the verification post performance index to obtain target post performance index data.

Optionally, the obtaining module 301 may be further specifically configured to:

retrieving the preset hospital post structure tree according to the target intelligent hospital cluster to obtain corresponding post data to be analyzed, preprocessing the post data to be analyzed to obtain preprocessed post data to be analyzed, wherein the target intelligent hospital cluster is used for indicating a medical union and/or a medical community;

Optionally, the weight calculating module 304 may be further specifically configured to:

calling a preset hierarchical analysis algorithm, and sequentially constructing a target hierarchical structure chart and a judgment matrix based on post main performance index values for each target key performance index corresponding to each post type to obtain a target judgment matrix;

Optionally, the apparatus for constructing the assessment index system weight further includes:

the performance calculation module 305 is used for acquiring performance data of the medical staff cluster to be evaluated, and performing performance value calculation on the performance data of the medical staff cluster to be evaluated through the weight of the target index system to obtain the performance value of the medical staff corresponding to each medical staff to be evaluated;

the sorting module 306 is configured to sort the medical staff clusters to be evaluated according to the medical staff performance values corresponding to the medical staff to be evaluated, so as to obtain medical staff cluster performance assessment information, where the medical staff cluster performance assessment information includes the sorted medical staff to be evaluated and the sorted medical staff performance values of the medical staff to be evaluated.

The function realization of each module and each unit in the device for constructing the assessment index system weight corresponds to each step in the embodiment of the method for constructing the assessment index system weight, and the function and the realization process are not repeated herein.

Fig. 3 and fig. 4 describe the construction device of the assessment index system weight in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the following describes the construction device of the assessment index system weight in the embodiment of the present invention in detail from the perspective of hardware processing.

Fig. 5 is a schematic structural diagram of an assessment index system weight constructing apparatus 500 according to an embodiment of the present invention, which may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) for storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a series of computer program operations in the construction apparatus 500 for applying weights to the assessment indices. Still further, the processor 510 may be configured to communicate with the storage medium 530, and execute a series of computer program operations in the storage medium 530 on the construction apparatus 500 for qualifying the weights of the index hierarchy.

The qualification index architecture weight building apparatus 500 may further include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, and the like. Those skilled in the art will appreciate that the configuration of the construction apparatus for the assessment index system weights shown in FIG. 5 does not constitute a limitation of the construction apparatus for the assessment index system weights, and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.

The application also provides a construction device for checking the weight of the index system, which comprises: a memory having a computer program stored therein and at least one processor, the memory and the at least one processor interconnected by a line; the at least one processor calls the computer program in the memory to cause the construction apparatus of the assessment index system weight to execute the steps in the construction method of the assessment index system weight. The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, or a volatile computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program runs on a computer, the computer program causes the computer to execute the steps of the method for constructing the assessment index system weight.

Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes several computer programs to enable 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: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; 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

1. A construction method of an assessment index system weight is characterized by comprising the following steps:

2. The method for constructing a assessment index system weight according to claim 1, wherein the classifying of the medical staff attendance data and the post value data into investment data, the classifying of the target post performance index data into post index production data, and the performing of the performance index value operation on the investment data and the post index production data to obtain a post master performance index value comprises:

3. The method for constructing a qualification system weight according to claim 2, wherein the step of performing fusion normalization on the slave post performance indicator data corresponding to each master post performance indicator to obtain the yield value corresponding to each master post performance indicator comprises the steps of:

4. The method for constructing the assessment index system weight according to claim 1, wherein the step of obtaining the key performance index data of the original medical staff and the attendance data of the medical staff of the target intelligent hospital cluster, and screening the key performance index data of the original medical staff according to the index requirements corresponding to the post types to obtain the target post performance index data comprises the following steps:

5. The method for constructing the assessment index system weight according to claim 1, wherein the steps of obtaining the post data to be analyzed of the target intelligent hospital cluster and obtaining the post value data of the post data to be analyzed, which is evaluated based on the preset post value evaluation factor, comprise:

6. The method for constructing a assessment index system weight according to claim 1, wherein the method for calculating the weight of each post performance index based on the post master performance index value through a preset hierarchical analysis algorithm to obtain a target index system weight, wherein the target index system weight includes each target key performance index of each post type and a weight value corresponding to each target key performance index of each post type, and comprises:

7. The method for constructing a assessment index system weight according to any one of claims 1-6, wherein after calculating the weight of each post performance index based on the post master performance index value by a preset hierarchical analysis algorithm to obtain a target index system weight, the method further comprises:

8. An assessment index system weight construction device is characterized by comprising the following components:

9. The equipment for constructing the examination index system weight is characterized by comprising the following steps: a memory and at least one processor, the memory having stored therein a computer program;

the at least one processor calls the computer program in the memory to cause the construction device of the qualifying index system weights to perform the construction method of the qualifying index system weights as claimed in any of claims 1-7.

10. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the method for constructing the assessment index system weight according to any one of claims 1-7.