CN110543996A - job salary assessment method, apparatus, server and storage medium - Google Patents
job salary assessment method, apparatus, server and storage medium Download PDFInfo
- Publication number
- CN110543996A CN110543996A CN201810521480.4A CN201810521480A CN110543996A CN 110543996 A CN110543996 A CN 110543996A CN 201810521480 A CN201810521480 A CN 201810521480A CN 110543996 A CN110543996 A CN 110543996A
- Authority
- CN
- China
- Prior art keywords
- salary
- matrix
- similarity
- company
- different
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
- G06Q10/1057—Benefits or employee welfare, e.g. insurance, holiday or retirement packages
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the invention discloses a method, a device, a server and a storage medium for estimating position salary, wherein the method comprises the following steps: acquiring target position data; inputting the target position data into a pre-constructed salary calculation model to obtain target salary information; the salary calculation model is constructed according to the historical position data and the salary range of the historical positions. The embodiment of the invention constructs the salary calculation model by extracting a large amount of real position related data, can carry out multi-angle, high-efficiency and dynamic salary analysis on the historical position data and the corresponding salary range, and realizes automatic evaluation of the market salary of each position. The accuracy and the efficiency of the position salary evaluation are improved, and the waste of manpower and material resources is reduced.
Description
Technical Field
The embodiment of the invention relates to the technical field of internet, in particular to a position salary assessment method, a device, a server and a storage medium.
Background
The position salary evaluation is an important work of each company for remunerating and welfare departments, and the work content of the position salary evaluation is to effectively and accurately measure and calculate the market salary of each position so as to provide reasonable salary treatment for the staff of each position.
The existing job position salary evaluation mode generally obtains a limited amount of market research data according to a government department or a third party consulting company, or performs long-term market research on the salary data by depending on a large amount of manpower and material resources in the company, and obtains the salary treatment corresponding to each job position approximately by analyzing, summarizing and processing the market research data.
however, in the existing job position salary evaluation mode, the research period of market data is long, the data arrangement and analysis process is too tedious, and the data arrangement and analysis process completely depends on manpower and material resources, so that a large amount of time, manpower and material resources are wasted. Meanwhile, because the salary data obtained by the market research method is often limited, the manpower capacity is limited, and the salary is influenced by more factors, the possibility that tens of millions of combinations of the factors are considered, the existing position salary evaluation method cannot efficiently and accurately cope with the actual variable market conditions, and the accurate salary evaluation result cannot be obtained.
Disclosure of Invention
the embodiment of the invention provides a position salary evaluation method, a device, a server and a storage medium, which can efficiently and accurately automatically evaluate the market salary of each position.
in a first aspect, an embodiment of the present invention provides a method for evaluating position salary, including:
Acquiring target position data;
Inputting the target position data into a pre-constructed salary calculation model to obtain target salary information; the salary calculation model is constructed according to the historical position data and the salary range of the historical positions.
In a second aspect, an embodiment of the present invention provides an apparatus for evaluating position salary, including:
The target position data acquisition module is used for acquiring target position data;
The target salary calculation module is used for inputting the target position data into a pre-constructed salary calculation model to obtain target salary information; the salary calculation model is constructed according to the historical position data and the salary range of the historical positions.
In a third aspect, an embodiment of the present invention provides a server, including:
One or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method for position salary evaluation as described in any of the embodiments of the present invention.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the position salary evaluation method according to any embodiment of the present invention.
According to the embodiment of the invention, a salary calculation model is pre-constructed according to the historical position data and the salary range of the historical positions, and the target position data is input into the salary calculation model, so that the market salary corresponding to the target position is obtained. The embodiment of the invention constructs the salary calculation model by extracting a large amount of real position related data, can carry out multi-angle, high-efficiency and dynamic salary analysis on the historical position data and the corresponding salary range, and realizes automatic evaluation of the market salary of each position. The accuracy and the efficiency of the position salary evaluation are improved, and the waste of manpower and material resources is reduced.
Drawings
Fig. 1 is a flowchart of a position salary evaluation method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a salary calculation model according to a second embodiment of the present invention;
Fig. 3 is an exemplary diagram of a salary matrix of "position (time) -company (place)" provided in the second embodiment of the present invention;
FIG. 4 is an exemplary diagram of an HSBMF model provided in the second embodiment of the present invention;
Fig. 5 is a flowchart of a position salary evaluation method according to a third embodiment of the present invention;
fig. 6 is a flowchart of a position salary evaluation method according to a fourth embodiment of the present invention;
Fig. 7 is a schematic structural diagram of a position salary evaluation apparatus according to a fifth embodiment of the present invention;
fig. 8 is a schematic structural diagram of a server according to a sixth embodiment of the present invention.
Detailed Description
the embodiments of the present invention will be described in further detail with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the embodiments of the invention and that the invention is not limited thereto. It should be further noted that, for convenience of description, only some structures related to the embodiments of the present invention are shown in the drawings, not all of the structures are shown.
example one
Fig. 1 is a flowchart of a position salary evaluation method according to an embodiment of the present invention, which is applicable to a situation of evaluating market salaries of various positions, and the method can be executed by a position salary evaluation device. The method specifically comprises the following steps:
and S110, acquiring target position data.
in an embodiment of the present invention, the target position refers to a position for which market salary assessment is to be performed. For the positions, the diversity of the positions leads to different salaries of different positions, and meanwhile, the salaries of the positions are influenced by various factors such as companies, time, places and the like, so that even if the positions are the same but the working companies or the places are different or the working periods are different, the salaries are different, and therefore the market salaries of the positions in actual conditions show diversity, the differences of the companies providing the positions, the time differences of position release and the regional differences of the working places where the positions are located. In this embodiment, when evaluating the market salary of the target position, the related data of the target position needs to be acquired.
Preferably, the target position data may include target position basic information, company basic information, office locations, and a publication time of the corresponding recruitment information. The basic information of the job may include information such as a job name and job requirement description, and further, the job requirement description may include information such as job responsibilities and job eligibility. The basic company information may include company name, company profile, company industry, company size, and financing information. The office location refers to a desired office location for the job or to an alternative office location for the job. The office place may be a prefecture city, an autonomous state, a union or a region under a province or an autonomous region, a prefecture city or a special administrative district, a lower-level county administrative district, or the like. The office location is subject to practical requirements and is not limited to the areas of the above-mentioned levels. Due to the fact that the market economy develops to cause different salary levels of residents in different periods, the release time of the recruitment information corresponding to positions also needs to be summarized as one of the factors influencing the salary condition. In addition to the above target position data acquisition, data information related to any other factors affecting position salary can be acquired.
The salary and welfare department of the company can acquire target position data when carrying out salary adjustment on the existing position or when carrying out salary setting on a novel position. The acquisition mode can be to combine the current release data of the current position with the current data information, or directly utilize the related data set for the novel position. The embodiment does not limit the manner of acquiring the target position data, and any manner that can acquire the target position data may be applied to the embodiment.
Illustratively, the target position data is acquired, and the basic position information is as follows: the job title is a software testing engineer, the job duty is to periodically submit a product defect statistical analysis report and complete a product testing summary report, and the job qualification is information of computer related professions, college subjects and the academic calendars, familiarity with related testing tools and the like. The basic company information is: the company name is Beijing A information technology company, the company belongs to the industry of software development, the company scale is 50-60 persons, and the financing condition is information such as completed Angel rotation financing. The release time of the recruitment information corresponding to the position is 2018, 4 months. The company is divided into Beijing and Tianjin office departments, and the office places can be selected. So far, the important data influencing target position salary are almost obtained, and salary information corresponding to Beijing or Tianjin in an office place corresponding to the target position can be respectively obtained through subsequent evaluation.
s120, inputting the target position data into a pre-constructed salary calculation model to obtain target salary information; the salary calculation model is constructed according to the historical position data and the salary range of the historical positions.
in the embodiment of the invention, the salary calculation model can automatically and efficiently calculate the target salary information according to the input target position data, so that a salary welfare department of a company can adjust or set salaries corresponding to the target position. The salary calculation model is constructed according to the historical position data and the salary range of the historical positions.
specifically, in the embodiment, firstly, the historical position data and the salary range of the historical position are acquired according to various factors having influence on position salary, and the existing position recruitment information and the corresponding salary information of the company are acquired by disclosing relevant data sources such as a recruitment market and the like, so as to construct a position salary database. Therefore, the position salary database at least comprises the basic information of each company, the basic information of the positions provided by each company, the office location of each position, the release time of the recruitment information corresponding to each position, and the lowest monthly salary and/or the highest monthly salary of the positions released by each company. Based on these online network data sources, the embodiment can capture job post release information on the relevant websites or webpages by using a crawler technology, and process the captured information by using a data extraction-Transform-Load (ETL) technology. The ETL technology is an important link for constructing a data warehouse, and is used for extracting required data from a data source, cleaning and converting the data, and finally loading the data into the data warehouse according to a predefined data warehouse model. In the ETL data processing process, the online recruitment website or webpage content is analyzed and extracted; cleaning the extracted historical position data to filter out incomplete data, wrong data and repeated data; the washed historical position data is converted according to a predefined data warehouse model, so that inconsistent data conversion, data granularity conversion, calculation of corresponding business rules and the like are realized; and finally, loading the processed historical position data into a data warehouse for storage, and integrating the scattered, disordered and non-uniform historical position data in the network according to a predefined data warehouse model to form a position salary database.
secondly, the embodiment further preprocesses the historical position data in the position salary database, filters out the position information which is not in accordance with normal logic and issues company and position information with extremely small number, and clusters similar positions so as to classify tens of thousands of position information in the position salary database, and simplifies and optimizes the position salary database. In this embodiment, a clustering method of historical position data is not limited, and positions with the same or similar position names may be clustered into one category by using but not limited to a regularization rule, or clustered by using a method of calculating similarity through a bag-of-words model according to position requirement description, and the like. For example, assume that a piece of historical job data is: the name of the job is restaurant waiter, the office location is Tianjin, and the monthly salary is 20 ten thousand. It can be judged according to the resident consumption level and the wage level of Tianjin city that the historical position data does not conform to the normal logic, so that the historical position data is filtered out. For another example, for the same office location but with the job names of the software testers and the software testing engineers, the bag-of-words model can be used to cluster the historical job data of the two jobs.
moreover, the embodiment can perform position salary evaluation based on the multi-factor constraint matrix decomposition model. Firstly, according to historical position data in a position salary database and the salary range of the historical positions, a position (time) -company (place) salary matrix is constructed by taking the positions and the companies as factors similarly according to a traditional user-project scoring matrix decomposition model. Secondly, according to the basic matrix decomposition with bias, a user-item scoring matrix with a defect value is decomposed into two low-rank hidden variable matrixes and three bias items, and similarly, an original salary matrix is decomposed into a salary prediction matrix containing hidden variable matrixes related to positions, hidden variable matrixes related to companies, bias items related to positions, bias items related to companies and total bias of the salary matrix. Then, unlike the conventional matrix decomposition model, the present embodiment considers the influence of similar correlations of positions, companies, places, and times on salaries, and constructs a corresponding similarity regular constraint according to the four factors. And finally, fusing multi-constraint salary matrixes of job, company, place and time similarity, combining the four regular constraint matrixes with the traditional matrix decomposition with bias to obtain a loss function, solving the solutions of the hidden variable matrix related to the job, the hidden variable matrix related to the company, the bias item related to the job and the bias item related to the company which minimize the loss function, and substituting the solutions into a salary prediction matrix to obtain target salary information of the target job.
According to the technical scheme of the embodiment, a salary calculation model is pre-constructed according to historical position data and the salary range of the historical positions, and target position data are input into the salary calculation model, so that market salaries corresponding to the target positions are obtained. The embodiment of the invention constructs the salary calculation model by extracting a large amount of real position related data, can carry out multi-angle, high-efficiency and dynamic salary analysis on the historical position data and the corresponding salary range, and realizes automatic evaluation of the market salary of each position. The accuracy and the efficiency of the position salary evaluation are improved, and the waste of manpower and material resources is reduced.
example two
on the basis of the first embodiment, the embodiment provides a preferred implementation of the position salary evaluation method, and can construct a salary calculation model according to the historical position data and the salary range of the historical positions.
fig. 2 is a flowchart for constructing a salary calculation model according to a second embodiment of the present invention, and as shown in fig. 2, the method includes the following specific steps:
s210, constructing a salary matrix by taking positions and companies as factors according to the historical position data and the salary range of the historical positions.
in the embodiment of the invention, a crawler technology can be adopted to capture the position information from related data sources such as an online recruitment website or a webpage, and an ETL technology is utilized to analyze, extract, clean, convert and load the captured position information, so that the processed historical position data is loaded into a data warehouse for storage according to a predefined data warehouse model, and the scattered, disordered and non-uniform historical position data in a network are integrated together according to the predefined data warehouse model to form the position salary database. And obtaining a simplified and optimized position salary database through logic analysis, clustering and other preprocessing. According to the historical position data in the position salary database and the salary range of the historical position, a position (time) -company (place) salary matrix S is constructed by taking the position and the company as factors, and the salary matrix S represents the salary range corresponding to the position, the time, the company and the place one by one. Fig. 3 is an exemplary diagram of a salary matrix of "job (time) -company (place)" provided in this embodiment, and as shown in fig. 3, each row of the salary matrix S represents a job with a time stamp, and each column represents a company with a place stamp. The values in the salary matrix S are the position with the time stamp and the lowest monthly salary or the highest monthly salary corresponding to the company with the place stamp. If there is no corresponding historical salary, the value is the deficit value in the salary matrix S, and the salary evaluation for different positions is equal to the prediction of these deficit values.
S220, decomposing the salary matrix based on the matrix decomposition model to obtain a salary prediction matrix comprising a position hidden variable matrix, a company hidden variable matrix, a position offset vector, a company offset vector and a salary matrix total offset.
In one embodiment of the present invention, the matrix decomposition is a decomposition of an original matrix into a product of two matrices. According to a traditional user-project scoring matrix decomposition model, namely, an original matrix is decomposed into two low-rank hidden variable matrixes and a form of combination of three offset items, the original salary matrix S is decomposed into a salary prediction matrix comprising a position hidden variable matrix J, a company hidden variable matrix C, a position offset vector BJ, a company offset vector BC and a salary matrix total offset mu, salary information without an observed value in the salary matrix S can be reasonably estimated by multiplying the position hidden variable matrix J and the company hidden variable matrix C, and then the salary prediction matrix is obtained so as to perform automatic and rapid salary evaluation according to salary conditions corresponding to different positions of different companies at different places and different release times.
and S230, respectively constructing regular constraint matrixes of positions, companies, places and release times.
In the embodiment of the invention, the difference is from the traditional matrix decomposition model, the influence of similar correlation of positions, companies, places and time on salaries is considered, and a corresponding similarity regular constraint matrix is constructed according to the four factors.
preferably, determining similarity between different positions comprises: generating a word frequency matrix of a word frequency-inverse text frequency index of each position demand description based on a word bag model according to each position demand description in historical position data; and calculating the cosine similarity of the vector space between the description texts of each position according to the word frequency matrix of the word frequency-inverse text frequency index corresponding to the description of the requirements of different positions, and determining the similarity between different positions.
in an embodiment of the present invention, it is assumed that SJ represents a similarity matrix of job requirement descriptions, and SJ (j, j ') represents the similarity between job j and job j'. Because similar salaries corresponding to the job requirement descriptions are similar, the present embodiment may use a bag-of-words model, omit the elements such as syntax and word order of the job requirement description text, regard the text as a set of a plurality of words, express each job requirement description text by using a set of unordered words through the bag-of-words model, and generate a word frequency matrix of the word frequency-inverse text frequency index (TF-IDF) of each job requirement description. And then, calculating the similarity among the positions by adopting a similarity calculation method, for example, determining the similarity SJ among different positions according to a formula by adopting a vector space cosine similarity calculation method.
preferably, the job regular constraint matrix is constructed according to the similarity between different jobs. In this embodiment, the job regular constraint matrix is defined as: wherein M represents the number of positions; j (J,: represents a row of salary data corresponding to the position J in the position hidden variable matrix J, and J (J ',: represents a row of salary data corresponding to the position J' in the position hidden variable matrix J); the F norm calculation is expressed by | | F | |; the matrix operation tr (a) ═ a11+ a22+ … + ann represents the summation of the traces of matrix a, i.e. the diagonal elements of matrix a. In the matrix operation tr (), JT represents a transposed matrix of the role hidden variable matrix J; the matrix represents a measurement matrix of a similarity matrix SJ described by the job requirement, namely the diagonal elements of the matrix are all 0.
Preferably, determining the similarity between different companies comprises: generating vector representation of each company according to at least one item of basic information of each company in the historical position data; according to the vector representations corresponding to different companies, calculating the Jacard similarity between the vector representations corresponding to the companies, and determining the similarity between the different companies.
in the embodiment of the present invention, it is assumed that SC represents the similarity matrix of company, and SC (c, c ') represents the similarity between company c and company c'. Since similar companies have similar salary policies, the present embodiment may generate vector representations of the companies according to at least one item of basic information of the companies in the historical position data, for example, information such as the scale, the industry, and/or the financing condition of the companies, so as to calculate a Jaccard (Jaccard) coefficient between the vector representations corresponding to the companies as a similarity SC (c, c ') between the company c and the company c ' according to the vector representations c and c ' corresponding to different companies. Since the Jaccard coefficient is mainly used for calculating the similarity between individuals with the symbol measurement or the boolean measurement, and since the characteristic attributes of the individuals are identified by the symbol measurement or the boolean, the sizes of specific values of the differences cannot be measured, and only the result of "whether the differences are the same" can be obtained, the Jaccard coefficient only concerns the problem of whether the characteristics commonly possessed by the individuals are consistent, and the Jaccard coefficient can be expressed so as to determine the similarity SC between different companies.
preferably, the company regular constraint matrix is constructed according to the similarity between different companies. The embodiment defines the regular constraint matrix of the company as follows: wherein N represents the number of companies; c (C,: represents a row of salary data corresponding to the company C in the company hidden variable matrix, and C (C ',: represents a row of salary data corresponding to the company C' in the company hidden variable matrix. In the matrix operation tr (), the CT represents a transposed matrix of the company hidden variable matrix C; the matrix represents the measurement matrix of the similarity matrix SC of the company, i.e. its diagonal elements are all 0.
Preferably, determining the similarity between different locations comprises: and determining the similarity between different cities according to the average income value of each city.
in the embodiment of the present invention, it is assumed that L represents a city similarity matrix, and L (c, c ') represents the similarity between the city where company c is located and the city where company c' is located. Since geographic location also has an important impact on salary, for example, a city with a high average salary level will also provide higher salary treatment for the same job position but different office locations. Therefore, the embodiment can determine the similarity between different places according to the average salary level of each city by acquiring the average income level AS of each city issued by the government, and determine the similarity L between different cities according to a formula. Wherein ASc is the average income value of the city of company c, ASc 'is the average income value of the city of company c', and max () is the maximum function operation.
preferably, the place regular constraint matrix is constructed according to the similarity between different places. The embodiment defines the location regular constraint matrix as follows: in the matrix operation tr (), the matrix DL represents a measurement matrix of the city similarity matrix L, i.e., the diagonal elements of the matrix are all 0.
preferably, determining the similarity between different release times includes: and determining the similarity between different release times according to the release time of each position.
In the embodiment of the present invention, let T represent a time similarity matrix, and T (j, j ') is a similarity between the release time of the position j and the release time of the position j'. As the salary level of the same position on the market fluctuates along with the time change, the closer the release time interval is, the salary level of the position is similar, and the farther the time interval of the release time of the opposite position is, the smaller the correlation of the salary level of the position is. Therefore, the time similarity can be defined according to the time interval of job release in the embodiment as follows: t (j, j ') is exp (- α | τ j- τ j' |), thereby determining the similarity T between different publication times. Wherein τ j represents the release time of position j, τ j 'represents the release time of position j', and α is a hyper-parameter.
Preferably, the time regular constraint matrix is constructed according to the similarity between different release times. The embodiment defines a time regular constraint matrix as follows: in the matrix operation tr (), the matrix DT represents a metric matrix of the temporal similarity matrix T, i.e., the diagonal elements of the matrix are all 0.
S240, constructing a loss function according to the salary matrix, the salary prediction matrix and the regular constraint matrix of positions, companies, places and release time.
in the embodiment of the invention, a multi-constrained salary matrix is carried out by fusing job, company, place and release time similarities, and the four regular constraint matrixes are combined with the traditional matrix decomposition with bias to obtain a loss function F: wherein Is represents an indication matrix of the salary matrix S, that Is, λ J, λ C, λ L and λ T are coefficients of a job latent variable matrix J, a company latent variable matrix C, a job bias vector BJ, a company bias vector BC, a similarity matrix SJ described by job demand, a similarity matrix SC of a company, a city similarity matrix L and a time similarity matrix T, respectively, and may be empirical values.
The multifactor constrained Matrix Factorization model (HSBMF) in this embodiment is shown in fig. 4. As can be seen from fig. 4, the salary matrix S can be decomposed into a form of co-constraint of a company related matrix and a position related matrix. Specifically, the salary matrix S is jointly determined by four hidden variables, namely a position hidden variable matrix J, a company hidden variable matrix C, a position offset vector BJ and a company offset vector BC; the job latent variable matrix J is jointly constrained by a similarity matrix SJ described by job requirements and a time similarity matrix T, the company latent variable matrix C is jointly constrained by a similarity matrix SC of a company and a city similarity matrix L, and the six variables are respectively constrained by respective coefficients lambda.
The technical scheme of the embodiment constructs a position (time) -company (place) salary matrix with defective values by automatically extracting position salary information released on a recruitment market, using position basic information, company basic information, work place, release time and lowest and highest salary levels in the existing recruitment information, decomposes the salary matrix into a multi-factor constrained salary prediction matrix based on a matrix decomposition model, building a regular constraint matrix of the position, the company, the place and the release time through respectively calculating the similarity of the position, the company, the place and the release time, and combines the regular constraint of job, company, place and time similarity with the matrix decomposition model with bias, and constructing a loss function according to the salary matrix, the salary prediction matrix and the regular constraint matrixes of the positions, the companies, the places and the release time. The embodiment of the invention constructs the salary calculation model in the form of a loss function through the decomposition of the salary matrix and the generation of the regular constraint matrix corresponding to multiple factors, and can quickly and automatically predict the reasonable salary range of a certain company and a certain position in different places and time periods. The method and the system can quickly respond to the change in the talent market for the enterprise, and improve the competitiveness of the enterprise in the talent market. Compared with the traditional method, the method not only greatly improves the working efficiency and saves the cost, but also considers the influence of different factors on the salaries, can carry out multi-angle, high-efficiency and dynamic salary analysis on the historical position data and the corresponding salary range thereof, improves the accuracy and the evaluation efficiency of position salary evaluation, and reduces the waste of manpower and material resources.
EXAMPLE III
On the basis of the second embodiment, the embodiment provides an optimal implementation of the position salary evaluation method, and can evaluate the target salary information based on the salary calculation model and the target position requirement description of the target position data, the basic information of the company, the office location and the release time of the corresponding recruitment information. Fig. 5 is a flowchart of a position salary evaluation method according to a third embodiment of the present invention, as shown in fig. 5, the method includes the following specific steps:
And S510, acquiring target position data.
in an embodiment of the present invention, the target position data may include basic information of the target position, basic information of a company, an office location, and a publication time of the corresponding recruitment information. The basic information of the job may include information such as a job name and job requirement description, and further, the job requirement description may include information such as job responsibilities and job eligibility. The basic company information may include information such as company name, company profile, company industry, company size, and financing situation. The office location refers to a required office location for the job or to an alternative office location for the job. The office place may be a prefecture city, an autonomous state, a union or a region under a province or an autonomous region, a prefecture city or a special administrative district, a lower-level county administrative district, or the like. The office location is subject to practical requirements and is not limited to the areas of the above-mentioned levels. Due to the fact that the market economy develops to cause different salary levels of residents in different periods, the release time of the recruitment information corresponding to positions also needs to be summarized as one of the factors influencing the salary condition. In addition to the above target position data, data information related to any other factors affecting position salary can be obtained.
The salary and welfare department of the company can acquire target position data when carrying out salary adjustment on the existing position or when carrying out salary setting on a novel position. The acquisition mode can be to combine the current release data of the current position with the current data information, or directly utilize the related data set for the novel position. The embodiment does not limit the manner of acquiring the target position data, and any manner that can acquire the target position data may be applied to the embodiment.
and S520, solving the position hidden variable matrix, the company hidden variable matrix, the position offset vector and the solution of the company offset vector which enable the loss function to be minimized.
In the specific embodiment of the present invention, a solution of an implicit variable that minimizes a loss function F min: F needs to be solved, and the solving process may be: through the processing of historical data, a salary matrix S, a similarity matrix SJ described by position requirements, a similarity matrix SC of a company, a time similarity matrix T, a city similarity matrix L, a measurement matrix D of each of the four variables, coefficients lambda of each of the eight variables, a learning rate gamma and a hyper-parameter alpha are input, and through the partial derivation of a loss function F and the use of a gradient descent principle, the solutions of a position hidden variable matrix J, a company hidden variable matrix C, a position offset vector BJ and a company offset vector BC of the optimization equation can be obtained.
S530, substituting the solution of minimizing the loss function into the salary prediction matrix to obtain target salary information of the target position.
in the embodiment of the invention, the solution which minimizes the loss function is substituted into the salary prediction matrix to obtain the salary prediction matrix containing the solution of the defect value, and then the target salary information of the target position can be read.
According to the technical scheme of the embodiment, target position data is input into a salary calculation model, a solution for minimizing a loss function is solved, the solution for minimizing the loss function is substituted into a salary prediction matrix, and target salary information of a target position is obtained. According to the embodiment of the invention, the salary calculation model constructed by processing a large amount of real position data is utilized, so that multi-angle, efficient and dynamic salary analysis can be carried out on the historical position data and the corresponding salary range, and the automatic and efficient evaluation on the market salary of the target position is realized. The accuracy and the efficiency of the position salary evaluation are improved, and the waste of manpower and material resources is reduced.
example four
on the basis of the above embodiments, the present embodiment provides an overall process of the position salary evaluation method, and integrates the construction of the early-stage model and the evaluation of the later-stage position salary. Fig. 6 is a flowchart of a position salary evaluation method according to a fourth embodiment of the present invention, as shown in fig. 6, the method includes the following specific steps:
And S610, acquiring a historical position data source.
and S620, capturing historical position data from the data source based on a crawler technology.
and S630, extracting, cleaning, converting and loading historical position data based on an ETL technology.
And S640, constructing a position salary database.
S650, extracting and preprocessing historical position data in the position salary database, and optimizing the position salary database.
And S660, constructing a salary calculation model based on the multi-factor matrix decomposition model.
And S670, acquiring target position data, and inputting the target position data into a salary calculation model for evaluation.
and S680, obtaining an evaluation result of the target salary information.
According to the technical scheme, the position salary information released on the recruitment market is automatically extracted, the position salary database is constructed and optimized based on the crawler technology and the ETL technology, the salary calculation model based on the multi-factor matrix decomposition model is constructed according to the historical position data, and the evaluation result of the target salary information is obtained through the salary calculation model. The embodiment of the invention constructs the salary calculation model by extracting a large amount of real position related data, can carry out multi-angle, high-efficiency and dynamic salary analysis on the historical position data and the corresponding salary range, and realizes automatic evaluation of the market salary of each position. The accuracy and the efficiency of the position salary evaluation are improved, and the waste of manpower and material resources is reduced.
EXAMPLE five
Fig. 7 is a schematic structural diagram of a position salary evaluation device according to a fifth embodiment of the present invention, which is applicable to evaluating market salaries of various positions, and the device can implement the position salary evaluation method according to any embodiment of the present invention. The device specifically includes:
A target position data obtaining module 710, configured to obtain target position data;
the target salary calculation module 720 is used for inputting the target position data into a pre-constructed salary calculation model to obtain target salary information; the salary calculation model is constructed according to the historical position data and the salary range of the historical positions.
further, the target salary calculation module 720 includes:
A salary matrix construction unit 7201 configured to construct a salary matrix based on the historical position data and the salary range of the historical positions, taking positions and companies as factors;
the matrix decomposition unit 7202 is used for decomposing the salary matrix based on a matrix decomposition model to obtain a salary prediction matrix comprising a position hidden variable matrix, a company hidden variable matrix, a position offset vector, a company offset vector and a salary matrix total offset;
The regular constraint construction unit 7203 is used for respectively constructing regular constraint matrixes of positions, companies, places and release time;
The loss function building unit 7204 is configured to build a loss function according to the salary matrix, the salary prediction matrix, and the regular constraint matrices of the positions, companies, locations, and release times.
further, the target salary calculation module 720 includes:
a solving unit 7205 configured to solve a solution of the position hidden variable matrix, the company hidden variable matrix, the position offset vector, and the company offset vector that minimize the loss function;
And a target salary obtaining unit 7206, configured to substitute the solution that minimizes the loss function into the salary prediction matrix to obtain target salary information of the target position.
preferably, the regular constraint building unit 7203 is specifically configured to:
Constructing a job regular constraint matrix according to the similarity between different jobs;
Constructing a company regular constraint matrix according to the similarity between different companies;
Constructing a site regular constraint matrix according to the similarity between different sites;
and constructing a time regular constraint matrix according to the similarity between different release times.
Preferably, the regular constraint building unit 7203 is further configured to:
Generating a word frequency matrix of the word frequency-inverse text frequency index of each position demand description based on a word bag model according to each position demand description in the historical position data;
And calculating the cosine similarity of the vector space between the description texts of each position according to the word frequency matrix of the word frequency-inverse text frequency index corresponding to the description of the requirements of different positions, and determining the similarity between different positions.
Preferably, the regular constraint building unit 7203 is further configured to:
Generating vector representation of each company according to at least one item of basic information of each company in the historical position data;
According to the vector representations corresponding to different companies, calculating the Jacard similarity between the vector representations corresponding to the companies, and determining the similarity between the different companies.
preferably, the regular constraint building unit 7203 is further configured to:
Determining similarity between different cities according to the average income value of each city;
the similarity between different sites is determined according to the following formula:
Where L (c, c ') is the similarity between the city of company c and the city of company c', ASc is the average revenue value of the city of company c, ASc 'is the average revenue value of the city of company c', and max () is a max function.
Preferably, the regular constraint building unit 8203 is further specifically configured to:
Determining the similarity between different release times according to the release time of each position;
the similarity between different release times is determined according to the following formula:
T(j,j')＝exp(-α|τ-τ|)，
Wherein, T (j, j ') represents the similarity between different release times, τ j represents the release time of position j, τ j ' represents the release time of position j ', and α is a hyper-parameter.
according to the technical scheme of the embodiment, a salary calculation model is pre-constructed according to historical position data and the salary range of the historical positions, and target position data are input into the salary calculation model, so that market salaries corresponding to the target positions are obtained. The embodiment of the invention constructs the salary calculation model by extracting a large amount of real position related data, can carry out multi-angle, high-efficiency and dynamic salary analysis on the historical position data and the corresponding salary range, and realizes automatic evaluation of the market salary of each position. The accuracy and the efficiency of the position salary evaluation are improved, and the waste of manpower and material resources is reduced.
EXAMPLE six
Fig. 8 is a schematic structural diagram of a server according to a sixth embodiment of the present invention, and fig. 8 shows a block diagram of an exemplary server suitable for implementing the embodiment of the present invention. The server shown in fig. 8 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
the server 12 shown in fig. 8 is only an example, and should not bring any limitation to the function and the scope of use of the embodiment of the present invention.
As shown in FIG. 8, the server 12 is in the form of a general purpose computing device. The components of the server 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
the server 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by server 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. The server 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 8, and commonly referred to as a "hard drive"). Although not shown in FIG. 8, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination may comprise an implementation of a network environment. Program modules 42 generally perform the functions and/or methodologies of the described embodiments of the invention.
the server 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with the server 12, and/or with any devices (e.g., network card, modem, etc.) that enable the server 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, the server 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet) via the network adapter 20. As shown, the network adapter 20 communicates with the other modules of the server 12 via the bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the server 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, for example, implementing the position salary assessment method provided by the embodiment of the present invention
EXAMPLE seven
A seventh embodiment of the present invention further provides a computer-readable storage medium, on which a computer program (or referred to as computer-executable instructions) is stored, where the computer program is used for executing a method for estimating position salary, and the method includes:
acquiring target position data;
inputting the target position data into a pre-constructed salary calculation model to obtain target salary information; the salary calculation model is constructed according to the historical position data and the salary range of the historical positions.
computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, 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), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
computer program code for carrying out operations for embodiments of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code 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).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions without departing from the scope of the invention. Therefore, although the embodiments of the present invention have been described in more detail through the above embodiments, the embodiments of the present invention are not limited to the above embodiments, and many other equivalent embodiments can be included without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (18)
1. A method for estimating position salary, comprising:
Acquiring target position data;
Inputting the target position data into a pre-constructed salary calculation model to obtain target salary information; the salary calculation model is constructed according to the historical position data and the salary range of the historical positions.
2. the method of claim 1, wherein constructing a salary calculation model based on historical position data and salary ranges for historical positions comprises:
Constructing a salary matrix by taking positions and companies as factors according to the historical position data and the salary range of the historical positions;
Decomposing the salary matrix based on a matrix decomposition model to obtain a salary prediction matrix comprising a position hidden variable matrix, a company hidden variable matrix, a position offset vector, a company offset vector and a salary matrix total offset;
Respectively constructing regular constraint matrixes of positions, companies, places and release time;
and constructing a loss function according to the salary matrix, the salary prediction matrix and the regular constraint matrix of the positions, the companies, the places and the release time.
3. The method of claim 1, wherein inputting the target position data into a pre-constructed salary calculation model to obtain target salary information comprises:
Solving the solutions of the position hidden variable matrix, the company hidden variable matrix, the position offset vector and the company offset vector which minimize the loss function;
and substituting the solution which minimizes the loss function into a salary prediction matrix to obtain target salary information of the target position.
4. The method of claim 2, wherein the building of the canonical constraint matrix for job, company, place, and release time, respectively, comprises:
Constructing a job regular constraint matrix according to the similarity between different jobs;
constructing a company regular constraint matrix according to the similarity between different companies;
Constructing a site regular constraint matrix according to the similarity between different sites;
and constructing a time regular constraint matrix according to the similarity between different release times.
5. The method of claim 4, wherein determining similarity between different positions comprises:
Generating a word frequency matrix of the word frequency-inverse text frequency index of each position demand description based on a word bag model according to each position demand description in the historical position data;
And calculating the cosine similarity of the vector space between the description texts of each position according to the word frequency matrix of the word frequency-inverse text frequency index corresponding to the description of the requirements of different positions, and determining the similarity between different positions.
6. The method of claim 4, wherein determining similarity between different companies comprises:
generating vector representation of each company according to at least one item of basic information of each company in the historical position data;
According to the vector representations corresponding to different companies, calculating the Jacard similarity between the vector representations corresponding to the companies, and determining the similarity between the different companies.
7. The method of claim 4, wherein determining similarity between different locations comprises:
determining similarity between different cities according to the average income value of each city;
The similarity between different sites is determined according to the following formula:
where L (c, c ') is the similarity between the city of company c and the city of company c', ASc is the average revenue value of the city of company c, ASc 'is the average revenue value of the city of company c', and max () is a function of the maximum value.
8. the method of claim 4, wherein determining similarity between different publication times comprises:
Determining the similarity between different release times according to the release time of each position;
The similarity between different release times is determined according to the following formula:
T(j,j')＝exp(-α|τ-τ|)，
Wherein, T (j, j ') represents the similarity between different release times, τ j represents the release time of position j, τ j ' represents the release time of position j ', and α is a hyper-parameter.
9. an apparatus for estimating position salary, comprising:
The target position data acquisition module is used for acquiring target position data;
the target salary calculation module is used for inputting the target position data into a pre-constructed salary calculation model to obtain target salary information; the salary calculation model is constructed according to the historical position data and the salary range of the historical positions.
10. The apparatus of claim 9, wherein the target salary calculation module comprises:
The salary matrix construction unit is used for constructing a salary matrix by taking positions and companies as factors according to the historical position data and the salary range of the historical positions;
The matrix decomposition unit is used for decomposing the salary matrix based on a matrix decomposition model to obtain a salary prediction matrix comprising a position hidden variable matrix, a company hidden variable matrix, a position offset vector, a company offset vector and a salary matrix total offset;
The regular constraint construction unit is used for respectively constructing regular constraint matrixes of positions, companies, places and release time;
And the loss function building unit is used for building a loss function according to the salary matrix, the salary prediction matrix and the regular constraint matrix of the positions, the companies, the sites and the release time.
11. the apparatus of claim 9, wherein the target salary calculation module comprises:
the solving unit is used for solving the solutions of the position hidden variable matrix, the company hidden variable matrix, the position offset vector and the company offset vector which minimize the loss function;
And the target salary obtaining unit is used for substituting the solution which minimizes the loss function into the salary prediction matrix to obtain the target salary information of the target position.
12. the apparatus according to claim 10, wherein the canonical constraint building unit is specifically configured to:
constructing a job regular constraint matrix according to the similarity between different jobs;
constructing a company regular constraint matrix according to the similarity between different companies;
constructing a site regular constraint matrix according to the similarity between different sites;
And constructing a time regular constraint matrix according to the similarity between different release times.
13. The apparatus according to claim 12, wherein the canonical constraint building unit is further specifically configured to:
Generating a word frequency matrix of the word frequency-inverse text frequency index of each position demand description based on a word bag model according to each position demand description in the historical position data;
And calculating the cosine similarity of the vector space between the description texts of each position according to the word frequency matrix of the word frequency-inverse text frequency index corresponding to the description of the requirements of different positions, and determining the similarity between different positions.
14. the apparatus according to claim 12, wherein the canonical constraint building unit is further specifically configured to:
Generating vector representation of each company according to at least one item of basic information of each company in the historical position data;
According to the vector representations corresponding to different companies, calculating the Jacard similarity between the vector representations corresponding to the companies, and determining the similarity between the different companies.
15. the apparatus according to claim 12, wherein the canonical constraint building unit is further specifically configured to:
And determining the similarity between different cities according to the average income value of each city.
16. the apparatus according to claim 12, wherein the canonical constraint building unit is further specifically configured to:
And determining the similarity between different release times according to the release time of each position.
17. A server, comprising:
One or more processors;
A memory for storing one or more programs;
When executed by the one or more processors, cause the one or more processors to implement the position salary assessment method of any one of claims 1-8.
18. a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of position salary assessment according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810521480.4A CN110543996A (en) | 2018-05-28 | 2018-05-28 | job salary assessment method, apparatus, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810521480.4A CN110543996A (en) | 2018-05-28 | 2018-05-28 | job salary assessment method, apparatus, server and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110543996A true CN110543996A (en) | 2019-12-06 |
Family
ID=68700930
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810521480.4A Withdrawn CN110543996A (en) | 2018-05-28 | 2018-05-28 | job salary assessment method, apparatus, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110543996A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111125343A (en) * | 2019-12-17 | 2020-05-08 | 领猎网络科技(上海)有限公司 | Text analysis method and device suitable for human-sentry matching recommendation system |
| CN111724127A (en) * | 2020-06-12 | 2020-09-29 | 北京字节跳动网络技术有限公司 | Data generation method and device, electronic equipment and storage medium |
| CN113722368A (en) * | 2020-05-22 | 2021-11-30 | 百度在线网络技术（北京）有限公司 | Data processing method, device, equipment and storage medium |
| CN117371972A (en) * | 2023-12-05 | 2024-01-09 | 广东电网有限责任公司 | Performance compensation management method and system |
-
2018
- 2018-05-28 CN CN201810521480.4A patent/CN110543996A/en not_active Withdrawn
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111125343A (en) * | 2019-12-17 | 2020-05-08 | 领猎网络科技(上海)有限公司 | Text analysis method and device suitable for human-sentry matching recommendation system |
| CN113722368A (en) * | 2020-05-22 | 2021-11-30 | 百度在线网络技术（北京）有限公司 | Data processing method, device, equipment and storage medium |
| CN113722368B (en) * | 2020-05-22 | 2024-04-30 | 百度在线网络技术（北京）有限公司 | Data processing method, device, equipment and storage medium |
| CN111724127A (en) * | 2020-06-12 | 2020-09-29 | 北京字节跳动网络技术有限公司 | Data generation method and device, electronic equipment and storage medium |
| CN117371972A (en) * | 2023-12-05 | 2024-01-09 | 广东电网有限责任公司 | Performance compensation management method and system |
| CN117371972B (en) * | 2023-12-05 | 2024-03-19 | 广东电网有限责任公司 | Performance compensation management method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rappaport et al. | Model fit estimation for multilevel structural equation models | |
| Aizaki et al. | Stated preference methods using R | |
| Zhou et al. | Comparing MCDA aggregation methods in constructing composite indicators using the Shannon-Spearman measure | |
| Garg et al. | Challenges and techniques for testing of big data | |
| US7765123B2 (en) | Indicating which of forecasting models at different aggregation levels has a better forecast quality | |
| US9483544B2 (en) | Systems and methods for calculating category proportions | |
| CN110543996A (en) | job salary assessment method, apparatus, server and storage medium | |
| Coad et al. | Firm growth and productivity growth: evidence from a panel VAR | |
| Chirici | Assessing the scientific productivity of Italian forest researchers using the Web of Science, SCOPUS and SCIMAGO databases | |
| Kim | Spatiotemporal scale dependency and other sensitivities in dynamic land-use change simulations | |
| Zhao et al. | Research on the impact evaluation of academic journals based on altmetrics and citation indicators | |
| Mittman et al. | A hierarchical model for heterogenous reliability field data | |
| CN110209589B (en) | Knowledge base system test method, device, equipment and medium | |
| Buckland et al. | Measuring temporal trends in biodiversity | |
| Manjunath et al. | A study on sampling techniques for data testing | |
| Emami et al. | Buildingsbench: A large-scale dataset of 900k buildings and benchmark for short-term load forecasting | |
| Deng et al. | An interactive platform for the analysis of landscape patterns: a cloud-based parallel approach | |
| Dong et al. | Recalculating the agricultural labor force in china | |
| Silvestrini et al. | Linear regression analysis with JMP and R | |
| Almomani et al. | Selecting a good stochastic system for the large number of alternatives | |
| Lyu et al. | Empirical Bayes small area prediction under a zero‐inflated lognormal model with correlated random area effects | |
| CN116701935A (en) | Sensitivity prediction model training method, sensitivity information processing method and sensitivity information processing device | |
| CN114266414A (en) | Loan amount prediction method, loan amount prediction device, loan amount prediction electronic device, and loan amount prediction medium | |
| Yang et al. | The survival probability of the SABR model: asymptotics and application | |
| Klüppelberg et al. | Testing for reduction to random walk in autoregressive conditional heteroskedasticity models |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191206 |
|
| WW01 | Invention patent application withdrawn after publication |