CN110378509B

CN110378509B - Data prediction method, data prediction device, computer equipment and storage medium

Info

Publication number: CN110378509B
Application number: CN201910462939.2A
Authority: CN
Inventors: 钟向波
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2019-05-30
Filing date: 2019-05-30
Publication date: 2022-12-02
Anticipated expiration: 2039-05-30
Also published as: CN110378509A

Abstract

The application relates to a data prediction method, a data prediction device, computer equipment and a storage medium, wherein the data prediction method comprises the following steps: acquiring a first person compilation list, wherein the first person compilation list is used for storing all first person information predicted to be on duty in the next year, and each piece of first person information comprises a first person code, a first duty level, a first duty property and a first person entering progress; according to the first post level and the first post property corresponding to each first person code, adopting a pre-trained post grading model to obtain the person utilization rate and the post rate corresponding to each first person code; substituting the first entering progress, the personnel utilization rate and the post rate corresponding to each first personnel code into a preset next-year labor cost calculation formula, and calculating the labor cost corresponding to each first personnel code; and calculating the sum of the labor cost corresponding to each first person code to obtain a data prediction result of the labor cost. This application has realized enterprise's human cost's accurate data prediction.

Description

Data prediction method, data prediction device, computer equipment and storage medium

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a data prediction method, an apparatus, a computer device, and a storage medium.

Background

When the enterprise carries out cost budgeting, the labor cost of the second year needs to be budgeted so as to guarantee the moderate increase of the labor cost of the second year. Currently, the forecast of the second year's labor cost for a business is to roughly estimate the number of staff in each department and then to derive the estimated second year's labor cost. However, the accuracy of the prediction of the human cost by using the method is low, and the prediction may be far from the actual human cost in the next year, which may cause the budget reserved on the human cost by the enterprise to be inaccurate. Inaccurate data prediction of human cost directly influences the increase of economic benefits of enterprises.

Disclosure of Invention

The application mainly aims to provide a data prediction method, a data prediction device, computer equipment and a storage medium, and aims to accurately predict the labor cost of an enterprise.

In order to achieve the above object, the present application provides a data prediction method, including the steps of:

acquiring a first person compilation list, wherein the first person compilation list is used for storing all first person information predicted to be on duty in the next year, and each piece of first person information comprises a first person code, a first duty level, a first duty property and a first person entering progress;

according to a first post level and a first post property corresponding to each first person code, adopting a pre-trained post grading model to obtain a person utilization rate and a post rate corresponding to each first person code;

substituting the first entering progress, the personnel utilization rate and the post rate corresponding to each first personnel code into a preset next-year human cost calculation formula, and calculating the human cost corresponding to each first personnel code;

and calculating the sum of the labor cost corresponding to all the first person codes to obtain a data prediction result of the labor cost.

Further, the step of obtaining a first person list may be preceded by:

respectively obtaining a second personnel compilation list and a third personnel compilation list, wherein the second personnel compilation list is used for storing second personnel information on duty in the current year, each piece of the second personnel information comprises a second personnel code, a second post level and a second post property, the third personnel compilation list is used for storing third personnel information estimated to arrive at/leave a post in the next year, and each piece of the third personnel information comprises a third personnel code, a third post level and a third post property;

respectively calculating a second entering progress corresponding to each second personnel code according to a first preset entering progress statistical rule, and respectively calculating a third entering progress corresponding to each third personnel code according to a second preset entering progress statistical rule;

adding the second person entering progress into the second person compiling list to generate a first intermediate list, and adding the third person entering progress into the third person compiling list to generate a second intermediate list;

and merging the first intermediate list and the second intermediate list to generate the first personnel compilation list.

Further, before the step of respectively obtaining the second person organization list and the third person organization list, the method includes:

acquiring basic information of all third people from the human resource server, wherein the basic information comprises a people type, a third position level and a third position property, and the people type comprises people predicted to go to the position in the next year and people predicted to leave the position in the next year;

according to a preset personnel coding rule, automatically filling a plurality of first character slots included in a coding template in sequence, wherein the coding template is used for generating a third personnel code corresponding to a third personnel, the coding template includes a plurality of first character slots and a second character slot which are arranged in sequence, the first character slots are used for filling preset number characters, and the second character slots are used for filling identification codes;

respectively generating an identification code corresponding to each third person according to the person type of each third person, and filling the identification code into the corresponding second character slot to generate a third person code corresponding to each third person;

and sequentially adding a third person code, a third post level and a third post property corresponding to each third person to a blank list to generate the third person compiling list.

Further, the step of generating an identification code corresponding to each third person according to the person type of each third person, and filling the identification code into the corresponding second character slot to generate a third person code corresponding to each third person includes:

respectively judging whether each third person is a person expected to arrive at the post in the next year or a person expected to leave the post in the next year;

if the third person is a person expected to arrive at a post in the next year, setting the identification code as a first preset value, and writing the first preset value into a corresponding third person code; and if the third person is a person expected to leave the post in the next year, setting the identification code as a second preset value, and writing the second preset value into a corresponding third person code.

Further, the step of respectively calculating a third entering-person progress corresponding to each third person code according to a second preset entering-person progress statistical rule includes:

respectively judging whether the identification code of each third personnel code is the first preset value or the second preset value;

if the current value is the first preset value, acquiring a predicted post arrival date corresponding to the third person from the human resource server;

calculating the people entering progress corresponding to the third person code according to the estimated post arrival date and a first preset formula;

if the second preset value is the second preset value, acquiring a predicted off-duty date corresponding to the third person from the human resource server;

and calculating the person entering progress corresponding to the third person code according to a second preset formula according to the expected off-duty date.

Further, before the step of substituting the first entering progress, the staff utilization rate and the post rate corresponding to each first person code into a preset next-year human cost calculation formula, calculating the human cost corresponding to each first person code, the method includes:

acquiring the number of working days of the next year;

calculating the working hours of the whole year according to the preset working hours of each working day and the days of the working day;

and substituting the whole year working hours into a preset human cost calculation formula to obtain the next year human cost calculation formula.

The present application also provides a data prediction apparatus, comprising:

the system comprises a first obtaining unit, a first person compiling unit and a second obtaining unit, wherein the first person compiling unit is used for storing all first person information expected to be on duty in the next year, and each piece of first person information comprises a first person code, a first duty level, a first duty property and a first person entering progress;

the query unit is used for obtaining the personnel utilization rate and the post rate corresponding to each first person code by adopting a pre-trained post grading model according to the first post grade and the first post property corresponding to each first person code;

the first calculation unit is used for substituting the first entering progress, the personnel utilization rate and the post rate corresponding to each first person code into a preset next-year labor cost calculation formula, and calculating the labor cost corresponding to each first person code;

and the second calculation unit is used for calculating the sum of the labor costs corresponding to all the first personnel codes to obtain a data prediction result.

Further, the data prediction apparatus further includes:

a second obtaining unit, configured to obtain a second personnel compilation list and a third personnel compilation list respectively, where the second personnel compilation list is used to store second personnel information on duty in this year, each piece of the second personnel information includes a second personnel code, a second station level, and a second station property, the third personnel compilation list is used to store third personnel information expected to arrive at/leave a station in the next year, and each piece of the third personnel information includes a third personnel code, a third station level, and a third station property;

the third calculation unit is used for calculating a second entering progress corresponding to each second personnel code according to a first preset entering progress statistical rule and calculating a third entering progress corresponding to each third personnel code according to a second preset entering progress statistical rule;

the intermediate list generating unit is used for adding the second person entering progress into the second person compiling list to generate a first intermediate list, and adding the third person entering progress into the third person compiling list to generate a second intermediate list;

and the list merging unit is used for merging the first intermediate list and the second intermediate list to generate the first personnel compilation list.

The present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

The present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method of any of the above.

The beneficial effect of this application:

according to the data prediction method, the data prediction device, the computer equipment and the storage medium, a first person compiling list is firstly obtained, wherein the first person compiling list is used for storing all first person information predicted to be on duty in the next year, and each piece of first person information comprises a first person code, a first duty level, a first duty property and a first entering schedule; then, according to a first post level and a first post property corresponding to each first person code, adopting a pre-trained post grading model to obtain a person utilization rate and a post rate corresponding to each first person code; substituting the first entering progress, the personnel utilization rate and the post rate corresponding to each first personnel code into a preset next-year human cost calculation formula, and calculating the human cost corresponding to each first personnel code; finally, calculating the sum of the labor cost corresponding to each first person code to obtain a data prediction result of the labor cost; therefore, the budget of the labor cost of each first person is accurate, the accuracy of the data prediction result of the enterprise labor cost obtained through calculation is high, the human capital budget of the enterprise can be well made, and the management and the development of the enterprise can be facilitated.

Drawings

FIG. 1 is a schematic diagram illustrating steps of a data prediction method according to an embodiment of the present application;

FIG. 2 is a block diagram of a data prediction device according to an embodiment of the present application;

fig. 3 is a schematic block diagram of a structure of a computer device according to an embodiment of the present application.

The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

Referring to fig. 1, in an embodiment of the present application, a data prediction method is provided, including the following steps:

s1, obtaining a first person compilation list, wherein the first person compilation list is used for storing all first person information predicted to be on duty in the next year, and each piece of first person information comprises a first person code, a first duty level, a first duty property and a first person entering progress;

s2, according to a first post level and a first post property corresponding to each first person code, adopting a pre-trained post grading model to obtain a person utilization rate and a post rate corresponding to each first person code;

s3, substituting the first entering progress, the personnel utilization rate and the post rate corresponding to each first person code into a preset next-year human cost calculation formula, and calculating the human cost corresponding to each first person code;

and S4, calculating the sum of the labor cost corresponding to all the first person codes to obtain a data prediction result of the labor cost.

In this embodiment, the method is used for budgeting the labor cost of the enterprise in the next year.

In the step S1, the first person compiling list may be obtained from a human resource server, and all human resource information of the enterprise, including on-post person information, person recruitment information, person post adjustment information, person cutting information, post levels of the persons, post properties of the posts, post rates, person utilization rates, time of job entry, time of job leaving, and the like, is stored in the human resource server. All the first person information predicted to be on duty in the next year is sequentially stored in the first person compiling list, and the first person information comprises the persons already on duty in the current year and the persons predicted to go on duty/off duty in the next year.

The first person codes have uniqueness, and the first person codes corresponding to different first persons are different. The method can establish a coding template for generating the personnel codes in advance according to the preset personnel coding rule to distinguish different types of personnel. The encoding template may include a plurality of character slots, each of which is filled with a preset type of characters, for example, the encoding template includes three character slots, where one character slot is used to fill a year number, one character slot is used to fill a sequence number, and one character slot is used to fill an identification code, that is, the encoding template is < year > < sequence > < identification code >, and the sequence may be a natural number that is sequentially added, and for people who are already on duty in the present year, the sequence may be, for example, a worker job number; the identification code may be a predetermined letter or number, such as a being a person on duty in the present year, B being a person expected to go on duty in the next year, and C being a person expected to go off duty in the next year.

The first station level refers to a station level preset by an enterprise, such as a, B, C, D, etc., or a senior product manager, a senior project manager, a senior analyst, a junior consultant, etc. The first station property refers to either internal or external manpower. For the people who are on duty in the current year, the first entering schedule refers to the proportion of the working days of each person in the next year to the working days of the whole year, and is 1; for the staff expected to go to duty in the next year, the first people entering schedule refers to the proportion of the working days of each staff in the next year to the working days of the whole year, for example, for the staff expected to enter duty in 7 months and 1 day in the second year, the people entering schedule is 6/12. For the staff expected to leave the post in the next year, the above-mentioned entering schedule refers to the negative number of the proportion of the non-working days of each staff in the next year to the working days of the whole year, for example, for the staff expected to leave the post in 1 month and 31 days of the next year, the entering schedule is-11/12.

In step S2, the training step of the post classification model includes: respectively acquiring post levels and post properties of employees who have already worked in each year, and corresponding personnel utilization rate and post rates from a server to construct a training set; and according to the training set, taking the post level, post property and post time of the employees who have already worked in each year as input, and taking the personnel utilization rate and the post rate as output, and carrying out model training to obtain a post grading model. And obtaining the predicted personnel utilization rate and the post rate in the next year according to the post grading model. The personnel utilization rate and the post rate obtained through the post grading model are predicted according to the data of the past year, accord with the change rule, and are more accurate compared with manual setting in the prior art. The personnel utilization is typically 100% and for a particular post, such as a primary consultant, the personnel utilization is set to 90%. The enterprise can adjust the personnel utilization rate of each post according to the actual conditions every year. The post rates refer to the labor cost price per hour, the post rates corresponding to different first post levels and different first post properties are different, and the enterprise can adjust the post rates according to actual conditions every year.

In the step S3, the calculation formula of the labor cost of the next year is used to estimate the labor cost of each first person of the next year. And the calculation formula of the manpower cost of the next year is human entering progress, full-year man hour of the next year, human utilization rate and post rate. When the next year is determined, the corresponding working hours of the whole year are also determined, and the first people entering progress, the personnel utilization rate and the post rate which are obtained in the steps S1 and S2 are substituted into the next year human cost calculation formula, so that the human cost corresponding to each first person code can be calculated.

In the step S4, the labor cost corresponding to each first person in the first person compilation list is summed, so as to obtain a data prediction result of the next-year labor cost of the enterprise.

In this embodiment, the method is used for accurately predicting the enterprise human cost. When an enterprise carries out data prediction on the human cost of the next year, all first person information predicted to be on duty of the next year is obtained from a first person compiling list, then a pre-trained post grading model is adopted, a first person entering progress, a person utilization rate and a post rate corresponding to each first person are obtained, the first person entering progress, the person utilization rate and the post rate are substituted into a preset human cost calculation formula of the next year, the human cost corresponding to each first person is calculated, and then the data prediction result of the enterprise of the next year is further calculated. Therefore, the budget of the labor cost of each first person is accurate, the accuracy of the data prediction result of the enterprise labor cost obtained through calculation is high, the human capital budget of the enterprise can be well made, and the management and the development of the enterprise can be facilitated.

In an embodiment, before the step S1 of obtaining the first person list, the method includes:

s01, respectively obtaining a second personnel compilation list and a third personnel compilation list, wherein the second personnel compilation list is used for storing second personnel information on duty in the current year, each piece of the second personnel information comprises a second personnel code, a second post level and a second post property, the third personnel compilation list is used for storing third personnel information estimated to arrive at/leave the post in the next year, and each piece of the third personnel information comprises a third personnel code, a third post level and a third post property;

s02, respectively calculating a second entering progress corresponding to each second person code according to a first preset entering progress statistical rule, and respectively calculating a third entering progress corresponding to each third person code according to a second preset entering progress statistical rule;

s03, adding the second progress into the second personnel compilation list to generate a first intermediate list, and adding the third progress into the third personnel compilation list to generate a second intermediate list;

and S04, combining the first intermediate list and the second intermediate list to generate the first personnel compilation list.

In this embodiment, the steps S01 to S04 are used to generate the first person list.

In the step S01, the second person compiling list stores information of second persons who are on duty in the current year, and specifically, the second person refers to the latest person on duty acquired from the human resource server when data prediction of human cost is performed. The setting of the second person code, the second post level and the second post property corresponding to the second person is the same as that in step S1, and is not described herein again.

In the third people list, the third people codes corresponding to the people expected to go to post in the next year and the people expected to go off post in the next year are respectively distinguished according to a predetermined rule, for example, two types of people are distinguished by the identification code of the third people code, such as B is the people expected to go to post in the next year and C is the people expected to go off post in the next year.

In the step S02, the first preset entering-person progress statistical rule indicates that for the second person who is on duty in the current year, the second entering-person progress is the proportion of the working days in the next year to the working days in the whole year. When the manpower budget is made, if the second person still works for a whole year in the next year, the corresponding second person entering progress is set to be 1.

The second preset entering-person progress statistical rule means that for the persons predicted to enter the post in the next year, the third entering-person progress is the proportion of the working days of each third person in the next year to the working days of the whole year, for example, for the staff predicted to enter the post in 7 months and 1 day in the second year, the entering-person progress is 6/12; and for the staff expected to leave the post in the next year, the third people entering schedule is the negative number of the proportion of the non-working days of each staff in the next year to the working days of the whole year, for example, for the staff expected to leave the post in 1 month and 31 days of the next year, the people entering schedule is-11/12.

In the above steps S03 to S04, the generated first intermediate list includes the second person code, the second position level, the second position property, and the second person entering progress corresponding to each second person, and the generated second intermediate list includes the third person code, the third position level, the third position property, and the third person entering progress corresponding to each third person. The first intermediate list and the second intermediate list are merged, i.e. a first person-compiled list is generated.

In another embodiment, before the step S01 of respectively obtaining the second person list and the third person list, the method includes:

s011, acquiring information of all third people predicted in the next year from a human resource server, wherein the types of the third people comprise people predicted to go to post in the next year and people predicted to go off post in the next year;

s012, according to a preset personnel code rule, automatically filling a plurality of first character slots included in a code template in sequence, wherein the code template is used for generating a third personnel code corresponding to a third personnel, the code template includes a plurality of first character slots and a second character slot which are arranged in sequence, the first character slots are used for filling preset number characters, and the second character slots are used for filling identification codes;

s013, respectively generating an identification code corresponding to each third person according to the person type of each third person, and filling the identification code into the corresponding second character groove to generate a third person code corresponding to each third person;

s014, sequentially adding a third person code, a third position grade and a third position property corresponding to each third person to a blank list to generate a third person compiling list.

In this embodiment, the steps S011 to S014 are used for generating the third person list.

In the step S011, the human resource server stores various human resource information of the enterprise, including information of people expected to go on duty in the next year and people expected to leave duty in the next year, wherein the information of people expected to go on duty in the next year can be obtained from the recruitment information list of the human resource server, and the information of people expected to leave duty in the next year can be obtained from the people reduction list of the human resource server.

In the step S012, the code pattern includes a plurality of first character slots and a second character slot. For example, the encoding template is < year > < sequence > < ID >, where < year > and < sequence > are both the first character slot and < ID > is the second character slot. And for the first character slot, filling the preset number characters according to the preset personnel coding rule: for example, a year number for the next year is filled for < year >; for < sequence > we can fill in sequentially increasing natural numbers, for people already on duty this year, the sequence can also be, for example, a staff number.

In step S013, the identification code may be a predetermined letter or number, for example, a is a person who is on duty in the current year, B is a person who is expected to go on duty in the next year, and C is a person who is expected to go off duty in the next year.

Specifically, in another embodiment, the step S013, which is to generate the identification code corresponding to each third person according to the person type of each third person and fill the identification code into the corresponding second character slot to generate the third person code corresponding to each third person, includes:

s0131, respectively judging whether each third person is a person expected to arrive at a post in the next year or a person expected to leave the post in the next year;

s0132, if the third person is a person expected to arrive at a post in the next year, setting the identification code as a first preset value, and writing the first preset value into a corresponding third person code; and if the third person is a person expected to leave the post in the next year, setting the identification code as a second preset value, and writing the second preset value into a corresponding third person code.

In the above step S0131, the type of the third person may be determined according to the acquired source of the third person, for example, if the source is the recruitment information list of the human resource server, the third person is a person expected to go to post in the next year, and if the source is the staff-reduction list of the human resource server, the third person is a person expected to go off post in the next year. In the above step S0132, for the person expected to arrive at post in the next year, the corresponding sequence is set to a default value (e.g., "000000", or "XX0000", where XX is used to indicate department number), and the corresponding identification code is set to a first preset value (e.g., B); for persons expected to be off duty in the next year, the corresponding sequence is set to the person job number (e.g., "123456"), and the corresponding identification code is set to a second preset value (e.g., C).

In step S014, the third person codes, the third post levels and the third post properties corresponding to the third persons are sequentially added to the blank list to generate a third person compiling list.

In addition, for the employee who is expected to make the adjustment of the position level or the position property in the next year, the employee can make the record of the person who is expected to leave the position in the next year in the third person compiling list, and then make the record of the person who is expected to go to the position in the next year. For example, if employee c (job number 111111) expects to adjust from internal level E to internal level D the next year, it will record the third personnel in the list, personnel code: 2019111111C, post level: e, position property: an inner portion; one more record, person code 2019000000B, post level: d, station property: inside.

In another embodiment, the step S02 of calculating the third entering-person progress corresponding to each of the third person codes according to the second preset entering-person progress statistical rule includes:

s021, respectively judging whether the identification code of each third personnel code is the first preset value or the second preset value;

s022, if the preset value is the first preset value, obtaining a predicted post arrival date corresponding to the third person from the human resource server;

s023, calculating a person entering progress corresponding to the third person code according to a first preset formula according to the estimated post arrival date;

s024, if the second preset value is the second preset value, acquiring a predicted off duty date corresponding to the third person from the human resource server;

and S025, calculating the people entering progress corresponding to the third person code according to the predicted off duty date and a second preset formula.

In this embodiment, in the step S021, the type of the third person is identified according to the identification code in the third person code. If the identification code is a first preset value, the third person is judged to be a person expected to arrive on duty in the next year; and if the identification code is a second preset value, judging that the third person is a person expected to leave the post in the next year.

In steps S022 to S023, the estimated staff arrival date is obtained from the human resources server. The predicted post dates can be automatically obtained from a recruitment information list or a website. The first preset formula is as follows: human progress = actual days of work in the next year/days of work all year round. For example, if a person predicts that the post time is 1 month and 1 day in 2019, the predicted working days in 2019 are equal to the actual working days in 2019, and the person entering progress is =100%; when a person expects a post time to be 12 months and 1 day in 2019, working days are expected to be 22 days in 2019, and the actual working days in 2019 are 232 days, the people entering progress is =22/232=9.48%.

In the above steps S024 to S025, the estimated staff arrival date is acquired from the human resource server. The expected post date can be obtained from the employee contract list or the staff reduction list. The second preset formula: people entering progress = - (actual days not worked in the next year/days worked throughout the year). For example, if a person expects the off duty time to be 2019, 1 month and 1 day, the actual non-working days in 2019 are equal to the full-year working days in 2019, and the person entering progress is = -100%; when the expected off duty time of a person is 12 months and 1 day in 2019, the actual non-working days in 2019 are 22 days, and the working days in the whole year in 2019 are 232 days, the entering schedule is = -22/232= -9.48%.

It should be noted that, for a person who is expected to leave the post on 12/1/2019, two pieces of information are stored in the first person compilation list, for example, the person number is 123456, the post level is F level, and the post level is an outsourced person, and two pieces of information are correspondingly stored about the person in the first person compilation list, as listed in table 1:

TABLE 1

Person coding	Rank of post	Characteristics of post	Progress of entering people
				2019123456A	F	Outer bag	100％
2019123456C	F	Outer bag	-9.48％

For an employee who is expected to perform the adjustment of the post level or the post property in the next year, three pieces of information are stored in the first person compiling list, for example, the person work number is 111111, the post is expected to be adjusted in 12 months and 1 day in 2019, the department level E is adjusted to the internal level D, and then three pieces of person information are correspondingly stored about the employee in the first person compiling list, as listed in table 2:

TABLE 2

In another embodiment, before the step S3 of substituting the first entering schedule, the staff utilization rate and the post rate corresponding to each first person code into the preset next-year labor cost calculation formula to calculate the labor cost corresponding to each first person code, the method includes:

s001, acquiring the days of the working day of the next year;

s002, calculating the working hours of the whole year according to the preset working hours of each working day and the days of the working day;

and S003, substituting the whole year working hours into a preset human cost calculation formula to obtain the human cost calculation formula of the next year.

In this embodiment, step S201 is configured to automatically calculate the days of weekdays of the next year, and when a specific year is determined, for example, 2019, the days of weekdays of the year all year round can be determined; then, the preset working hours of each working day are obtained through the step S202, the preset working hours can be input by a user or can be automatically obtained from the attendance time, and the working day days are set by the preset formula of each working day to obtain the working hours of the whole year; and finally, calculating the whole year working hours corresponding to the next year through the step S003, and substituting the whole year working hours into a preset labor cost calculation formula, wherein the preset labor cost calculation formula is human entering progress and whole year working hours and personnel utilization rate.

Referring to fig. 2, in an embodiment of the present application, a data prediction apparatus is provided, including:

a first obtaining unit 10, configured to obtain a first person compilation list, where the first person compilation list is used to store all first person information expected to be on duty in the next year, and each piece of the first person information includes a first person code, a first post level, a first post property, and a first people entering schedule;

the query unit 20 is configured to obtain a staff utilization rate and a post rate corresponding to each first person code by using a pre-trained post classification model according to a first post level and a first post property corresponding to each first person code;

the first calculating unit 30 is configured to substitute a first entering schedule, a staff utilization rate and a post rate corresponding to each first person code into a preset next-year human cost calculation formula, and calculate a human cost corresponding to each first person code;

and the second calculating unit 40 is configured to calculate a sum of the human costs corresponding to all the first person codes, so as to obtain a data prediction result of the human costs.

In the first obtaining unit 10, the first person compiling list may be obtained from a human resource server, and all human resource information of the enterprise, including on-post person information, person recruitment information, person post adjustment information, person cutting information, post levels of the persons, post properties of the posts, post rates, person utilization rates, time of employment, time of leaving, and the like, are stored in the human resource server. All the first person information predicted to be on duty in the next year is sequentially stored in the first person compiling list, and the first person information comprises the persons already on duty in the current year and the persons predicted to go on duty/off duty in the next year.

The first person codes have uniqueness, and the first person codes corresponding to different first persons are different. The method can establish a coding template for generating the personnel codes in advance according to the preset personnel coding rule to distinguish different types of personnel. The encoding template may include a plurality of character slots, each of which is filled with a preset type of characters, for example, the encoding template includes three character slots, one of which is used to fill a year number, one of which is used to fill a sequence number, and one of which is used to fill an identification code, that is, the encoding template is < year > < sequence > < identification code >, and the sequence may be a natural number that is sequentially increased, and for the people who are already on duty in the year, the sequence may be, for example, a worker number; the identification code may be a predetermined letter or number, such as a being a person on duty in the current year, B being a person expected to go on duty in the next year, and C being a person expected to go off duty in the next year.

The first station level refers to a station level preset by an enterprise, such as a, B, C, D, etc., or a senior product manager, a senior project manager, a senior analyst, a junior consultant, etc. The first station property refers to either internal or external manpower. For the people who are already on duty in the year, the first people entering progress refers to the proportion of the working days of each person in the next year to the working days of the whole year, and is 1; for the staff expected to arrive at the post in the next year, the first people entering schedule refers to the proportion of the working days of each staff in the next year to the working days of the whole year, for example, for the staff expected to enter the post in 7 months and 1 day in the second year, the people entering schedule is 6/12. For the staff expected to leave the post in the next year, the above-mentioned entering schedule refers to the negative number of the proportion of the non-working days of each staff in the next year to the working days of the whole year, for example, for the staff expected to leave the post in 1 month and 31 days of the next year, the entering schedule is-11/12.

In the query unit 20, the training step of the post classification model includes: respectively acquiring post levels and post properties of employees who have already worked in each year, and corresponding personnel utilization rate and post rates from a server to construct a training set; and according to the training set, taking the post level, post property and post time of the employees who have already worked in each year as input, and taking the personnel utilization rate and the post rate as output, and carrying out model training to obtain a post grading model. And obtaining the predicted personnel utilization rate and the post rate in the next year according to the post grading model. The personnel utilization rate and the post rate obtained through the post grading model are predicted according to the data of the past years, accord with the change rule, and are more accurate compared with manual setting in the prior art. The personnel utilization is typically 100% and for a particular post, such as a primary consultant, the personnel utilization is set to 90%. The enterprise can adjust the personnel utilization rate of each post according to the actual conditions every year. The post rates refer to the labor cost price per hour, the post rates corresponding to different first post levels and different first post properties are different, and the enterprise can adjust the post rates according to actual conditions every year.

In the first calculating unit 30, the following year human cost calculating formula is used to estimate the human cost of each first person in the following year. And the calculation formula of the manpower cost of the next year is human entering progress, full-year man hour of the next year, human utilization rate and post rate. When the next year is determined, the corresponding working hours of the whole year are also determined, and then the first people entering progress, the personnel utilization rate and the post rate acquired by the first acquiring unit 10 and the inquiring unit 20 are substituted into the next year human cost calculation formula, so that the human cost corresponding to each first person code can be calculated.

The second calculating unit 40 is configured to sum the labor cost corresponding to each first person in the first person compilation list, so as to obtain a data prediction result of the labor cost of the enterprise in the next year.

In this embodiment, the device is used for accurately estimating the labor cost of an enterprise. When an enterprise carries out data prediction on the human cost of the next year, all first person information predicted to be on duty of the next year is obtained from a first person compiling list, then a pre-trained post grading model is adopted, a first person entering progress, a person utilization rate and a post rate corresponding to each first person are obtained, the first person entering progress, the person utilization rate and the post rate are substituted into a preset human cost calculation formula of the next year, the human cost corresponding to each first person is calculated, and then the data prediction result of the enterprise of the next year is further calculated. Therefore, the budget of the labor cost of each first person is accurate, the accuracy of the data prediction result of the enterprise labor cost obtained through calculation is high, the human capital budget of the enterprise can be well made, and the management and the development of the enterprise can be facilitated.

In one embodiment, the data prediction apparatus further includes:

In this embodiment, the second obtaining unit, the third calculating unit, the intermediate list generating unit, and the list merging unit are configured to generate the first person list.

In the second obtaining unit, the second person compilation list stores information of second persons who are on duty in the current year, and specifically, the second person refers to the latest person on duty obtained from the human resource server when data prediction of human cost is performed. The settings of the second person code, the second post level, and the second post property corresponding to the second person are the same as those in the first obtaining unit 10, and are not described herein again.

In the third calculating unit, the first preset entering-person progress statistical rule refers to a ratio of the working days of the second entering-person progress in the next year to the working days of the whole year for the second person who is on duty in the current year. When the manpower budget is made, if the second person still works for a whole year in the next year, the corresponding second person entering progress is set to be 1.

In the intermediate list generating unit and the list merging unit, the generated first intermediate list includes the second person code, the second position level, the second position property and the second person entering progress corresponding to each second person, and the generated second intermediate list includes the third person code, the third position level, the third position property and the third person entering progress corresponding to each third person. The first intermediate list and the second intermediate list are merged, i.e. a first person-compiled list is generated.

In another embodiment, the data prediction apparatus further comprises:

a third obtaining unit, configured to obtain information of all third people predicted in the next year from the human resource server, where the types of the third people include people predicted to go to post in the next year and people predicted to go off post in the next year;

the code filling unit is used for automatically filling a plurality of first character slots included in a code template in sequence according to a preset personnel code rule, wherein the code template is used for generating a third personnel code corresponding to a third personnel, the code template comprises a plurality of first character slots and a second character slot which are arranged in sequence, the first character slots are used for filling preset number characters, and the second character slots are used for filling identification codes;

the code generating unit is used for generating an identification code corresponding to each third person according to the person type of each third person and filling the identification code into the corresponding second character slot so as to generate a third person code corresponding to each third person;

and the list generating unit is used for sequentially adding the third person code, the third position level and the third position property corresponding to each third person into a blank list to generate the third person compiling list.

In this embodiment, the third acquiring unit, the code filling unit, the code generating unit, and the list generating unit are configured to generate a third personnel list.

In the third acquiring unit, various pieces of human resource information of the enterprise are stored in the human resource server, including information of people expected to go to post in the next year and information of people expected to leave post in the next year, where the information of people expected to go to post in the next year can be acquired from a recruitment information list of the human resource server, and the information of people expected to leave post in the next year can be acquired from a staff-reduction list of the human resource server.

In the code filling unit, the code template includes a plurality of first character slots and a second character slot. For example, the encoding template is < year > < sequence > < ID >, where < year > and < sequence > are both the first character slot and < ID > is the second character slot. And for the first character slot, filling the preset number characters according to the preset personnel coding rule: e.g., the year number for the next year is filled for < year >; for < sequence > sequentially increasing natural numbers can be filled, and for people already on duty this year, the sequence can also be, for example, a staff number.

In the code generating unit, the identification code may be a predetermined letter or number, for example, a is a person who is on duty in the current year, B is a person who is expected to go on duty in the next year, and C is a person who is expected to go off duty in the next year.

Specifically, in another embodiment, the code generating unit includes:

a first judging subunit, configured to respectively judge whether each of the third persons is a person expected to arrive at a post in the next year or a person expected to leave the post in the next year;

the code generation subunit is used for setting the identification code as a first preset value and writing the first preset value into a corresponding third person code if the third person is a person expected to arrive at a post in the next year; and if the third person is a person expected to leave the post in the next year, setting the identification code as a second preset value, and writing the second preset value into a corresponding third person code.

In the first determining subunit, the type of the third person may be determined according to the acquisition source of the third person, for example, if the source is the recruitment information list of the human resource server, the third person is a person expected to go to post in the next year, and if the source is the staff reduction list of the human resource server, the third person is a person expected to go off post in the next year. In the code generation subunit, for the person expected to arrive at post in the next year, the corresponding sequence is set to a default value (for example, "000000", or "XX0000", where XX is used to indicate the department number), and the corresponding identification code is set to a first preset value (for example, B); for persons expected to be off duty in the next year, the corresponding sequence is set to the person job number (e.g., "123456"), and the corresponding identification code is set to a second preset value (e.g., C).

And in the list generating unit, a third person code, a third position level and a third position property corresponding to each third person are sequentially added into the blank list to generate a third person compiling list.

In still another embodiment, the third calculation unit includes:

a second judging subunit, configured to respectively judge whether the identification code of each third person code is the first preset value or the second preset value;

a first obtaining subunit, configured to, if the preset value is the first preset value, obtain, from the human resource server, a predicted post arrival date corresponding to the third person;

the first calculating subunit is used for calculating a people entering progress corresponding to the third person code according to the estimated post arrival date and a first preset formula;

a second obtaining subunit, configured to, if the second preset value is the second preset value, obtain, from the human resource server, a predicted off-duty date corresponding to the third person;

and the second calculating subunit is used for calculating the people entering progress corresponding to the third person code according to the predicted off-duty date and a second preset formula.

In this embodiment, the second determining subunit is configured to identify the type of the third person according to the identification code in the third person code. If the identification code is a first preset value, judging that the third person is a person expected to arrive at the post in the next year; and if the identification code is a second preset value, judging that the third person is a person expected to leave the post in the next year.

In the first acquiring subunit and the first calculating subunit, the predicted post date may be automatically acquired from a recruitment information list or a website. The first preset formula is as follows: human progress = actual days of work in the next year/days of work all year round. For example, if a person predicts that the post time is 2019, 1 month and 1 day, the predicted working days in 2019 are equal to the actual working days in 2019, and the person entering progress is =100%; when a person expects the post time to be 12 months and 1 day in 2019, the expected working days in 2019 are 22 days, and the actual working days in 2019 are 232 days, the person entering progress is =22/232=9.48%.

In the second acquiring subunit and the second calculating subunit, the expected post date may be acquired from an employee contract list or a staff reduction list. The second preset formula: human progress = - (actual days off work for next year/days on work for all year). For example, if a person expects to leave the post for 1 month and 1 day in 2019, the actual non-working days in 2019 are equal to the full-year working days in 2019, and the person entering progress is = -100%; when the expected off duty time of a person is 12 months and 1 day in 2019, the actual non-working days in 2019 are 22 days, and the working days in the whole year in 2019 are 232 days, the entering schedule is = -22/232= -9.48%.

It should be noted that, for a person who is expected to leave the post in 12.1.2019, two pieces of information are stored in the first person compilation list, for example, the job number of the person is 123456, the post level is F level, the post level is outsourced person, and two pieces of information about the person are correspondingly stored in the first person compilation list, as listed in table 1:

TABLE 1

Personnel coding	Rank of post	Property of post	Progress of entering people
				2019123456A	F	Outer bag	100％
2019123456C	F	Outer bag	-9.48％

For an employee who is expected to perform position level or position property adjustment in the next year, three pieces of information are stored in the first person compiling list, for example, the number of the person is 111111, the position is expected to be adjusted in 12 months and 1 day in 2019, the department level E is adjusted to the internal level D, and then three pieces of information are correspondingly stored about the employee in the first person compiling list, as listed in table 2:

TABLE 2

Person coding	Rank of post	Characteristics of post	Progress of entering people
				2019111111A	E	Inner part	100％
2019111111C	E	Inner part	-9.48％
				2019000000B	D	Inner part	9.48％

In another embodiment, the data prediction apparatus further comprises:

a fourth acquiring unit configured to acquire the number of days of a working day of the next year;

the fourth calculation unit is used for calculating the annual working hours according to the preset working hours of each working day and the days of the working day;

and the formula generation unit is used for substituting the whole year working hours into a preset human cost calculation formula to obtain the human cost calculation formula of the next year.

In this embodiment, the fourth obtaining unit is configured to automatically calculate the number of days of a next year, and when a specific year is determined, for example, 2019, the number of days of a whole year workday of the year may be determined; then, the preset working hours of each working day are obtained through the fourth calculating unit, the preset working hours can be input by a user or can be automatically obtained from attendance time, and the working day days are set by a preset formula of each working day to obtain the whole year working hours; and finally, calculating the full-year working hours corresponding to the next year through a formula generation unit, and substituting the full-year working hours into a preset human cost calculation formula, wherein the preset human cost calculation formula is the human-entering progress, the full-year working hours, the human utilization rate and the post rate.

Referring to fig. 3, an embodiment of the present application further provides a computer device, where the computer device may be a server, and an internal structure of the computer device may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing data such as personnel information. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a data prediction method.

The processor executes the data prediction method and comprises the following steps:

acquiring a first person compiling list, wherein the first person compiling list is used for storing all first person information expected to be on duty in the next year, and each piece of the first person information comprises a first person code, a first duty level, a first duty property and a first entering progress;

In an embodiment, the step of obtaining the first person list by the processor comprises:

In an embodiment, before the step of obtaining the second person organization list and the third person organization list by the processor respectively, the method includes:

and sequentially adding a third person code, a third position grade and a third position property corresponding to each third person to a blank list to generate the third person compiling list.

In an embodiment, the step of generating, by the processor, an identification code corresponding to each third person according to the person type of each third person, and filling the identification code into the corresponding second character slot to generate a third person code corresponding to each third person includes:

In an embodiment, the step of calculating, by the processor, a third entering-person progress corresponding to each third person code according to a second preset entering-person progress statistical rule includes:

if the current value is the first preset value, acquiring the predicted post arrival date corresponding to the third person from the human resource server;

calculating a people entering progress corresponding to the third person code according to the estimated post arrival date and a first preset formula;

In an embodiment, before the step of calculating the human cost corresponding to each first person code by substituting the first entering schedule, the person utilization rate, and the post rate corresponding to each first person code into a preset human cost calculation formula for the next year, the processor includes:

acquiring the number of working days of the next year;

and substituting the annual working hours into a preset human cost calculation formula to obtain the human cost calculation formula of the next year.

Those skilled in the art will appreciate that the architecture shown in fig. 3 is only a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects may be applied.

An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a data prediction method, and specifically:

respectively obtaining a second personnel compilation list and a third personnel compilation list, wherein the second personnel compilation list is used for storing second personnel information on duty in the current year, each piece of second personnel information comprises a second personnel code, a second post level and a second post property, the third personnel compilation list is used for storing third personnel information predicted to arrive at/leave a post in the next year, and each piece of third personnel information comprises a third personnel code, a third post level and a third post property;

In an embodiment, before the step of obtaining the second person organization list and the third person organization list by the processor, respectively, the method includes:

acquiring basic information of all third people from the human resource server, wherein the basic information comprises a people type, a third position level and a third position property, and the people type comprises people predicted to go to the position in the next year and people predicted to go off the position in the next year;

and calculating the people entering progress corresponding to the third person code according to a second preset formula and the predicted off-duty date.

In an embodiment, before the step of substituting the first entering schedule, the staff utilization rate and the post rate corresponding to each first person code into a preset next-year human cost calculation formula by the processor, calculating the human cost corresponding to each first person code, the method includes:

acquiring the days of the next year working day;

In summary, for the data prediction method, apparatus, computer device and storage medium provided in this embodiment of the present application, a first person compilation list is first obtained, where the first person compilation list is used to store all first person information expected to be on duty in the next year, and each piece of first person information includes a first person code, a first duty level, a first duty property and a first progress; then according to a first post level and a first post property corresponding to each first person code, adopting a pre-trained post grading model to obtain a person utilization rate and a post rate corresponding to each first person code; substituting the first entering progress, the personnel utilization rate and the post rate corresponding to each first personnel code into a preset next-year human cost calculation formula, and calculating the human cost corresponding to each first personnel code; finally, calculating the sum of the labor cost corresponding to each first person code to obtain a data prediction result of the labor cost; therefore, the budget of the labor cost of each first person is accurate, the accuracy of the data prediction result of the enterprise labor cost obtained through calculation is high, the human capital budget of the enterprise can be well made, and the management and the development of the enterprise can be facilitated.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware related to instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRDRAM), enhanced SDRAM (ESDRAM), synchronous Link (Synchlink) DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct bused dynamic RAM (DRDRAM), and bused dynamic RAM (RDRAM).

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of another identical element in a process, apparatus, article, or method comprising the element.

The above description is only for the preferred embodiment of the present application and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are intended to be included within the scope of the present application.

Claims

1. A method of data prediction, comprising the steps of:

sequentially adding a third person code, a third post level and a third post property corresponding to each third person to a blank list to generate a third person compiling list;

respectively obtaining a second personnel compilation list and a third personnel compilation list, wherein the second personnel compilation list is used for storing second personnel information on duty in the current year, each piece of the second personnel information comprises a second personnel code, a second post level and a second post property, the third personnel compilation list is used for storing third personnel information estimated to arrive at/leave the post in the next year, and each piece of the third personnel information comprises a third personnel code, a third post level and a third post property;

generating a first personnel compilation list according to the second personnel compilation list and the third personnel compilation list;

acquiring the first person compiling list, wherein the first person compiling list is used for storing all first person information expected to be on duty in the next year, and each piece of the first person information comprises a first person code, a first duty level, a first duty property and a first person entering progress;

substituting the first entering progress, the personnel utilization rate and the post rate corresponding to each first person code into a preset next-year human cost calculation formula, and calculating the human cost corresponding to each first person code;

and calculating the sum of the labor costs corresponding to all the first person codes to obtain a data prediction result of the labor costs.

2. The data prediction method of claim 1, wherein the step of generating a first personnel list from the second personnel list and a third personnel list comprises:

merging the first intermediate list and the second intermediate list to generate the first personnel compilation list.

3. The data prediction method of claim 1, wherein the step of generating an identification code corresponding to each third person according to the person type of each third person and filling the identification code into the corresponding second character slot to generate a third person code corresponding to each third person comprises:

4. The data prediction method of claim 3, wherein the step of calculating a third entering progress corresponding to each third person code according to a second preset entering progress statistical rule comprises:

respectively judging whether the identification code of each third person code is the first preset value or the second preset value;

5. The data prediction method of claim 1, wherein before the step of calculating the human costs corresponding to each of the first person codes by substituting the first entering schedule, the person utilization rate and the post rate corresponding to each of the first person codes into a preset human cost calculation formula for the next year, the method comprises:

acquiring the number of working days of the next year;

6. A data prediction apparatus, comprising:

a first obtaining unit, configured to obtain basic information of all third people from the human resource server, where the basic information includes a people type, a third position level, and a third position property, and the people type includes people expected to go to a position in the next year and people expected to go off position in the next year;

the encoding module is used for automatically filling a plurality of first character slots included in an encoding template in sequence according to a preset personnel encoding rule, wherein the encoding template is used for generating a third personnel code corresponding to a third personnel, the encoding template comprises a plurality of first character slots and a second character slot which are arranged in sequence, the first character slots are used for filling preset number characters, and the second character slots are used for filling identification codes;

a third person code generating unit, configured to generate an identification code corresponding to each third person according to the person type of each third person, and fill the identification code into the corresponding second character slot to generate a third person code corresponding to each third person;

a third personnel compilation list generating unit, configured to add a third personnel code, a third post level and a third post property corresponding to each third person to a blank list in sequence, so as to generate a third personnel compilation list;

a second obtaining unit, configured to obtain a second personnel compilation list and a third personnel compilation list, where the second personnel compilation list is used to store second personnel information on duty in this year, each piece of the second personnel information includes a second personnel code, a second station level, and a second station property, the third personnel compilation list is used to store third personnel information expected to go to/leave a station in a next year, and each piece of the third personnel information includes a third personnel code, a third station level, and a third station property;

the first personnel compilation list generating unit is used for generating a first personnel compilation list according to the second personnel compilation list and the third personnel compilation list;

a third obtaining unit, configured to obtain the first person compilation list, where the first person compilation list is used to store all first person information expected to be on duty in the next year, and each piece of the first person information includes a first person code, a first post level, a first post property, and a first people entering schedule;

the inquiry unit is used for obtaining the personnel utilization rate and the post rate corresponding to each first person code by adopting a pre-trained post grading model according to the first post grade and the first post property corresponding to each first person code;

the second calculation unit is used for substituting the first entering progress, the personnel utilization rate and the post rate corresponding to each first personnel code into a preset next-year human cost calculation formula, and calculating the human cost corresponding to each first personnel code;

and the third calculating unit is used for calculating the sum of the labor cost corresponding to all the first person codes to obtain a data prediction result of the labor cost.

7. The data prediction device of claim 6, further comprising:

the fourth calculation unit is used for calculating a second entering progress corresponding to each second person code according to a first preset entering progress statistical rule and calculating a third entering progress corresponding to each third person code according to a second preset entering progress statistical rule;

the intermediate list generating unit is used for adding the second progress of people to the second personnel compiling list to generate a first intermediate list, and adding the third progress of people to the third personnel compiling list to generate a second intermediate list;

8. A computer device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method according to any of claims 1 to 5.

9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.