Method, device, equipment and medium for human resource evaluation

Abstract

The present disclosure provides a method for human resource evaluation, which can be applied to the field of artificial intelligence technology. The method includes: setting at least one evaluation rule, each of which is used to represent the mapping relationship between the performance behavior data of a position and a human resource evaluation indicator; based on each of the evaluation rules, constructing a decision tree; using the performance behavior data of the position involved in the evaluation rule in the historical data as sample data, and using the human resource evaluation indicators involved in the evaluation rule in the historical data as labels of the sample data, training the decision tree to obtain a human resource evaluation model; and using the human resource evaluation model to evaluate the performance of the staff in the corresponding position on the corresponding human resource evaluation indicators. The present disclosure also provides a device, equipment, storage medium and program product for human resource evaluation.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, and more specifically to a method, apparatus, device, medium and program product for human resource evaluation. Background Art

[0002] At present, the human resource evaluation of enterprises and other organizations mainly relies on manual evaluation and static quantitative statistics after the end of the work cycle. This method leads to low efficiency and timeliness of human resource evaluation. For example, with the current diversification of work forms, the work of some highly technical personnel is often no longer fixed in the office location. They may be transferred between multiple departments (for example, business architects), or they may work remotely. In this case, since the staff and the managers of human resource evaluation may not work in the same office for a long time, it is inevitable that the evaluation results will be unfair. For another example, the evaluation after the end of a fixed work cycle is neither timely nor accurate enough for the performance evaluation of short-term seconded, outsourced personnel or personnel who leave in the middle of the work cycle. Therefore, how to objectively and timely evaluate the performance of staff in various positions is very important for the management of human resources. Summary of the invention

[0003] In view of the above problems, the embodiments of the present disclosure provide a method, apparatus, device, medium and program product for human resource evaluation that improve the timeliness, effectiveness and accuracy of human resource evaluation.

[0004] In a first aspect of the disclosed embodiments, a method for human resources evaluation is provided, wherein the evaluation rules are used to represent the mapping relationship between the job performance data of a position and a human resources evaluation indicator; based on each of the evaluation rules, a decision tree is constructed; the job performance data of the position involved in the evaluation rules in the historical data are used as sample data, and the human resources evaluation indicators involved in the evaluation rules in the historical data are used as labels for the sample data to train the decision tree; and the human resources evaluation model is used to evaluate the performance of the staff in the corresponding position on the corresponding human resources evaluation indicators.

[0005] According to an embodiment of the present disclosure, the setting of at least one evaluation rule includes: when N evaluation rules are respectively used to represent the mapping relationship between the performance behavior data of the same position and N human resource evaluation indicators, the performance behavior data in the N evaluation rules are set to be the same but the algorithms are different, wherein N is an integer greater than or equal to 2.

[0006] According to an embodiment of the present disclosure, constructing a decision tree based on each of the evaluation rules includes: constructing N decision trees based on the N evaluation rules, wherein the N decision trees share input data.

[0007] According to an embodiment of the present disclosure, the N human resource evaluation indicators include a work contribution indicator and a salary cost indicator.

[0008] According to an embodiment of the present disclosure, the use of the human resources evaluation model to evaluate the performance of staff in corresponding positions on corresponding human resources evaluation indicators includes: obtaining first performance behavior data of a first staff member based on the performance behavior data of the position involved in the evaluation rules corresponding to the human resources evaluation model; and using the human resources evaluation model to process the first performance behavior data, and output a first indicator value of the first staff member on the corresponding human resources evaluation indicator.

[0009] According to an embodiment of the present disclosure, the use of the human resources evaluation model to evaluate the performance of staff in corresponding positions on corresponding human resources evaluation indicators also includes: based on the adjustment or confirmation of the first indicator value by management personnel, outputting the final value of the first staff member on the corresponding human resources evaluation indicator.

[0010] According to an embodiment of the present disclosure, the training of the decision tree further includes: merging the first job performance behavior data into the sample data, and using the final value as a label of the first job performance behavior data to participate in the training of the decision tree.

[0011] The second aspect of the embodiment of the present disclosure provides a device for human resource evaluation. The device includes an evaluation rule entry and adjustment module, and a data analysis and intelligent algorithm module. Among them, the evaluation rule entry and adjustment module is used to set at least one evaluation rule, and each evaluation rule is used to represent the mapping relationship between the performance behavior data of a position and a human resource evaluation indicator. The data analysis and intelligent algorithm module includes a decision tree construction submodule, a training submodule and an evaluation submodule. The decision tree construction submodule is used to construct a decision tree based on each evaluation rule. The training submodule is used to train the decision tree using the performance behavior data of the position involved in the evaluation rule in the historical data as sample data, and the human resource evaluation indicator involved in the evaluation rule in the historical data as the label of the sample data. The evaluation submodule is used to use the human resource evaluation model to evaluate the performance of the staff in the corresponding position on the corresponding human resource evaluation indicator.

[0012] According to an embodiment of the present disclosure, the device further includes a data collection and capture module. The data collection and capture module is used to obtain first job performance data of a first staff member based on the job performance data of the position involved in the evaluation rule corresponding to the human resource evaluation model. The evaluation submodule is used to process the first job performance data using the human resource evaluation model and output a first indicator value of the first staff member on the corresponding human resource evaluation indicator.

[0013] According to an embodiment of the present disclosure, the device further comprises a query and management module. The query and management module is used to output the final value of the human resource evaluation index based on the adjustment or confirmation of the first index value by the management personnel.

[0014] According to an embodiment of the present disclosure, the training submodule is also used to merge the first job performance behavior data into the sample data, and use the final value as a label of the first job performance behavior data to participate in the training of the decision tree.

[0015] In a third aspect of the embodiments of the present disclosure, an electronic device is further provided. The electronic device includes one or more processors and one or more memories. The one or more memories are used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors execute the above method.

[0016] According to a fourth aspect of the embodiments of the present disclosure, there is also provided a computer-readable storage medium on which executable instructions are stored, and when the instructions are executed by a processor, the processor executes the above method.

[0017] According to a fifth aspect of the embodiments of the present disclosure, a computer program product is provided, including a computer program, which implements the above method when executed by a processor.

[0018] One or more of the above embodiments have the following advantages or beneficial effects: different evaluation rules can be set for different positions and different combinations of human resource evaluation indicators, and different decision trees can be created accordingly. A human resource evaluation model can be obtained by training the decision tree, so that the human resource evaluation model can evaluate the performance of staff in a manner close to the historical real evaluation level, thereby realizing the diversification, refinement, automation and intelligence of human resource evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above contents and other purposes, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0020] Figure 1The application scenario diagram of the method, apparatus, device, medium and program product for human resource evaluation according to the embodiment of the present disclosure is schematically shown;

[0021] Figure 2 A flowchart of a method for human resource evaluation according to an embodiment of the present disclosure is schematically shown;

[0022] Figure 3 A schematic diagram schematically shows different decision trees constructed for different human resource evaluation indicators for the same position according to an embodiment of the present disclosure;

[0023] Figure 4 A flowchart schematically illustrates a method of evaluating the human resource evaluation index of a staff member in a corresponding position by using a human resource evaluation model according to an embodiment of the present disclosure;

[0024] Figure 5 A block diagram schematically shows a device for human resources evaluation according to an embodiment of the present disclosure;

[0025] Figure 6 A schematic diagram of a logical structure of a device for human resource evaluation according to another embodiment of the present disclosure is shown; and

[0026] Figure 7 The block diagram schematically shows an electronic device suitable for implementing the method for human resource evaluation according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0028] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0029] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0030] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0031] It should be understood herein that any number of elements in the specification and drawings is for illustration rather than limitation, and any naming (eg, first, second) is only for distinction but not for limitation.

[0032] The embodiments of the present disclosure provide a method, apparatus, device, medium and program product for human resource evaluation. The method may include: first setting at least one evaluation rule, each of which is used to represent the mapping relationship between the performance behavior data of a position and a human resource evaluation index; then building a decision tree based on each evaluation rule; next, using the performance behavior data of the position involved in the evaluation rule in the historical data as sample data, and using the human resource evaluation index involved in the evaluation rule in the historical data as the label of the sample data, training the decision tree; wherein the human resource evaluation model corresponds to the position and human resource evaluation index involved in the evaluation rule; finally, the human resource evaluation model can be used to evaluate the performance of the staff in the corresponding position on the corresponding human resource evaluation index.

[0033] According to the embodiments of the present disclosure, different evaluation rules can be set for different positions and different combinations of human resource evaluation indicators, and different decision trees can be created accordingly. A human resource evaluation model can be obtained by training the decision trees, so that the human resource evaluation model can evaluate the performance of staff in a manner close to the actual historical evaluation level, thereby realizing the diversification, refinement, automation and intelligence of human resource evaluation.

[0034] According to the embodiments of the present disclosure, evaluation rules for job performance data and corresponding human resource evaluation indicators can be set according to the business characteristics of the position (for example, short-term assignment or permanent residence, fixed-point office or remote office, fixed business content or cross-departmental cooperation, etc.) and business content, so that the human resource evaluation model finally trained can evaluate the performance of the staff in the position more objectively and specifically.

[0035] According to the embodiments of the present disclosure, the performance of staff members in positions can be evaluated dynamically and in real time. For example, when a project is completed, the performance of a staff member in the project can be evaluated using a human resources evaluation model, or when a staff member is on short-term secondment, the performance of the staff member during the secondment period can be evaluated using the human resources evaluation model corresponding to the seconded position based on the staff member's performance data during the short secondment period; or when a person resigns, the human resources evaluation model can be used to evaluate the performance of the resigned person from the last evaluation deadline to the time of resignation. In this way, the embodiments of the present disclosure can realize real-time and dynamic human resources evaluation based on the actual work content, actual working hours or actual evaluation needs of the staff member, effectively improving the efficiency and accuracy of human resources evaluation.

[0036] It should be noted that the method, apparatus, device, medium and program product for human resource evaluation provided in the embodiments of the present disclosure can be used in the financial field, and can also be used in any field other than the financial field. The present disclosure does not limit the application field.

[0037] In the technical solution disclosed in the present invention, the acquisition, storage and application of personal information involved are in compliance with the provisions of relevant laws and regulations, necessary confidentiality measures are taken, and do not violate public order and good morals.

[0038] Figure 1 The following schematically illustrates an application scenario diagram of the method, apparatus, device, medium, and program product for human resource evaluation according to an embodiment of the present disclosure. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0039] like Figure 1 As shown, the application scenario 100 according to this embodiment may include at least one terminal device (three are shown in the figure, terminal devices 101, 102, 103), a network 104, and a server 105. The network 104 is used to provide a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0040] Human resource management personnel (hereinafter referred to as management personnel) can use terminal devices 101, 102, 103 to interact with server 105 via network 104 to receive or send messages, etc.

[0041] The server 105 may be a server that provides various human resource management services. A decision tree model may be deployed in the server 105 .

[0042] According to the embodiment of the present disclosure, the manager can use the terminal devices 101, 102, 103 to write the evaluation rules and upload them to the server 105. The server 105 can create a decision tree according to the evaluation rules uploaded by the manager using the terminal devices 101, 102, 103, and obtain a human resource evaluation model based on the training decision tree, and evaluate the performance of the staff in the corresponding position on the corresponding human resource evaluation indicators using the human resource evaluation model, and feed back the evaluation results to the terminal devices 101, 102, 103.

[0043] It should be noted that the method for human resource evaluation provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the apparatus, device, medium and program product for human resource evaluation provided in the embodiment of the present disclosure can generally be set in the server 105. The method for human resource evaluation provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the apparatus, device, medium and program product for human resource evaluation provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0044] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0045] The following will be based on Figure 1 The scene described by Figure 2 to Figure 4 The method for human resource evaluation according to the disclosed embodiment is described in detail.

[0046] Figure 2 The flowchart of the method for human resource evaluation according to the embodiment of the present disclosure is schematically shown.

[0047] like Figure 2 As shown, the method for human resource evaluation in this embodiment may include operations S210 to S240.

[0048] First, in operation S210, at least one evaluation rule is set, each of which is used to represent a mapping relationship between job performance data of a position and a human resource evaluation indicator.

[0049] Then in operation S220, a decision tree is constructed based on each of the evaluation rules.

[0050] The human resource evaluation index in the disclosed embodiment may be an index used to measure the performance of staff members in any dimension of their work, such as a work contribution index, a salary cost index, a responsibility index, etc. Among them, the work contribution index is used to measure the output contribution of staff members to the work of their positions over a period of time. The salary cost index is used to measure the cost invested in a staff member of a certain position over a period of time. The responsibility index is used to measure the degree of diligence of staff members in their positions over a period of time.

[0051] According to the embodiment of the present disclosure, the management personnel can set the evaluation rules for a certain position corresponding to a certain human resource evaluation indicator within a period of time through the terminal devices 101 , 102 , and 103 .

[0052] Evaluation rules can include both quantitative and qualitative parts. The evaluation rules can include the composition of the performance data used for quantitative evaluation, the source of each work data, and the calculation rules (or calculation methods) for the workload of each work in the calculation process of the human resource evaluation index. At the same time, the evaluation rules can also include the evaluators of various types of information used for qualitative evaluation, and the calculation rules (or calculation expressions) for the qualitative evaluation of each work in the calculation process of the human resource evaluation index.

[0053] For example, X1, X2, ...X k They represent the performance behavior data of a certain position, which are independent variables affecting the human resource evaluation index in the evaluation rules. β1, β2...β k Represents the degree of influence of the independent variable on the dependent variable Y (ie, the human resource evaluation index), and the influence of the independent variable on the dependent variable can be linear or nonlinear. Therefore, in some embodiments, the evaluation rule can be expressed by a linear expression or a nonlinear expression.

[0054] The expression or parameter of the evaluation rule can be based on the general model and historical data in the industry and the historical data of human resources of the enterprise to achieve flexibility and customized configuration of parameters. For example, in one embodiment, an evaluation rule can be expressed by formula (1).

[0055]

[0056] Of course, it can be understood that formula (1) is only an example. In practice, different algorithms can be recommended for human resource evaluation indicators based on the business characteristics of different positions. For example, the following Tables 1a to 1c exemplify the evaluation rules for evaluating business architects according to a certain human resource evaluation indicator (for example, work contribution), where the evaluation rules are different from formula (1). It should be noted here that Tables 1a to 1c are a whole, and for the sake of clarity, they are split into three tables for display in this article, which as a whole illustrate the evaluation rules for evaluating business architects according to the human resource evaluation indicator of work contribution.

[0057] Refer to Table 1a to Table 1c, where the exemplary business architect's performance behavior data X1, X2...X k The source of the influence parameters β1, β2, ...β k Settings. Among them, when evaluating the work contribution index of business architects in Tables 1a to 1c, different levels can be divided according to the work content of business architects, and hierarchical evaluation can be performed. And when evaluating the work contribution of business architects at each level, multiple algorithms such as absolute value evaluation method and ladder evaluation method can be used to set evaluation rules. Among them, in the calculation algorithm method column of Tables 1a to 1c, A represents the absolute value evaluation method, and S represents the ladder evaluation method.

[0058] For example, the calculation rules for the various tasks of the business architect entered in Table 1a automatically identify all the work items and original data at each level, match the calculation method for them, and obtain the corresponding independent variable values. For example, learning and training are identified as the first-level work items, and the corresponding second-level work items include learning and examinations. The calculation rule for learning is set to class hours>50, with a full score of 8 points; otherwise, 0 points. Therefore, it is recommended to use the absolute value evaluation method, and the value of the learning work item is obtained as X11, and the second-level indicator calculation formula is a11*X11. By analogy, the indicator calculation formulas of each level are obtained.

[0059] Therefore, according to Table 1a to Table 1c, the evaluation rule for evaluating business architects according to the work contribution index can be expressed as formula (2):

[0060]

[0061] Next, in operation S230, the performance behavior data of a position involved in an evaluation rule in the historical data is used as sample data, and the human resource evaluation index involved in the evaluation rule in the historical data is used as a label of the sample data to train a decision tree to obtain a human resource evaluation model.

[0062] For example, the values ​​of X11, X12, X311, etc. of a large number of business architects in a certain period of time can be obtained based on the work items of each level in Table 1a to Table 1c, thereby obtaining a large amount of sample data, and the value of the corresponding work contribution indicator of each business architect in the period of time is used as the label of the corresponding sample data to train the decision tree, so as to obtain a human resource evaluation model that evaluates the work contribution of business architects.

[0063]

[0064] Table 1a

[0065]

[0066] Table 1b

[0067]

[0068] Table 1c

[0069] According to the disclosed embodiment, the acquisition of performance data can be automatically realized according to the evaluation rules. For example, in terms of quantitative data, the original data of various performance data can be obtained in real time through the API interface with various information systems; in terms of qualitative data, the management personnel can be automatically reminded to conduct qualitative evaluation of the work of the staff, and then the real-time step-by-step evaluation data can be captured.

[0070] When training a decision tree, you can extract features and clean the data by using the industry's general historical data and the company's human resources historical data (including job types, job sub-items, quantitative data for each job, and qualitative evaluation data for each job. The original historical data can be captured and classified according to the evaluation rules). Then, the decision tree (such as the GBDT gradient enhancement decision tree) is repeatedly trained and iteratively corrected, and the accuracy rate is used as a standard to evaluate the model training effect. Among them, 80% of the captured historical data can be randomly extracted each time as a training set, and the remaining 20% ​​of the data can be used as a validation set. The decision tree is trained through the GBDT gradient enhancement decision tree to obtain a human resources evaluation model that evaluates the staff in the corresponding positions according to the corresponding human resources evaluation indicators.

[0071] Finally, in operation S240, the human resource evaluation model is used to evaluate the performance of the staff in the corresponding position on the corresponding human resource evaluation indicators.

[0072] According to the embodiments of the present disclosure, different evaluation rules can be set for the same human resource evaluation index for different positions (for example, the content or source of the performance behavior data is different, or the algorithm of the evaluation rule is different), so that the corresponding human resource evaluation model can be trained separately. In this way, the human resource evaluation for different positions can be targeted and intelligent.

[0073] Alternatively, different evaluation rules can be set for different human resource evaluation indicators for the same position, and different decision trees can be constructed accordingly for training. In this case, in one embodiment, when N evaluation rules are used to represent the mapping relationship between the performance behavior data of the same position and N human resource evaluation indicators, the performance behavior data in the N evaluation rules can be set to be the same but with different algorithms, where N is an integer greater than or equal to 2. In this way, it is possible to facilitate the sharing of performance behavior data, reduce repeated collection of raw data, and improve the efficiency of using raw data.

[0074] Figure 3 A schematic diagram schematically shows different decision trees constructed for different human resource evaluation indicators for the same position according to an embodiment of the present disclosure.

[0075] like Figure 3 As shown in FIG. 1 , when different decision trees are constructed for different human resource evaluation indicators of the same position, when the performance behavior data in the evaluation rules corresponding to different human resource evaluation indicators of the same position are the same, the different decision trees constructed can share input data. Figure 3 Decision tree 1 and decision tree 2 can be used to process the performance behavior data of the same staff member to obtain the work contribution index and salary cost index of the staff member respectively.

[0076] By sharing input data, the utilization rate of input data used by decision tree 1 and decision tree 2 in the training phase and in the prediction phase after the training is completed (ie, as the corresponding human resource evaluation model) is improved, thereby improving the efficiency of human resource evaluation.

[0077] Figure 4 The flowchart of using the human resource evaluation model to evaluate the human resource evaluation indicators of the staff in the corresponding position in operation S240 according to the embodiment of the present disclosure is schematically shown.

[0078] like Figure 4 As shown, according to an embodiment of the present disclosure, operation S240 may include operations S401 to S403.

[0079] In operation S401, first job performance data of a first staff member is obtained based on job performance data of a position involved in an evaluation rule corresponding to a human resource evaluation model. For example, when the first staff member is a business architect, values ​​of work items at each level may be obtained according to Tables 1a to 1c.

[0080] In operation S402, the first job performance behavior data is processed using a human resource evaluation model to output a first indicator value of the first staff member on a corresponding human resource evaluation indicator.

[0081] The new performance behavior data can be analyzed in real time, combined with the latest one or more human resource evaluation models, to evaluate the index value of the first staff member in the corresponding one or more human resource evaluation indicators. In addition, the output results of the human resource evaluation model can be dynamically displayed, and the management personnel can be equipped with real-time query permissions.

[0082] Furthermore, in operation S403, based on the adjustment or confirmation of the first indicator value by the manager, the final value of the first staff member on the corresponding human resource evaluation indicator can be output. The manager can manually adjust and confirm the human resource evaluation indicator value of the staff member in real time, and then output the final value of the human resource evaluation indicator of the staff member in the current period as work performance.

[0083] According to the embodiment of the present disclosure, the first job performance behavior data can also be merged into the sample data after operation S403, and the final value of the above human resource evaluation index can be used as the label of the first job performance behavior data to participate in the training of the decision tree. In this way, the manually adjusted and confirmed data can be used as historical data to further repeat the training and iteratively correct the human resource evaluation model, forming a closed process loop.

[0084] Based on the methods for human resource evaluation described in the above embodiments, the present disclosure also provides a device for human resource evaluation. Figure 5 and Figure 6 The device is described in detail.

[0085] Figure 5 A block diagram of an apparatus 500 for human resource evaluation according to an embodiment of the present disclosure is schematically shown.

[0086] like Figure 5As shown, according to some embodiments of the present disclosure, the device 500 for human resource evaluation may include an evaluation rule entry and adjustment module 510, and a data analysis and intelligent algorithm module 520. The data analysis and intelligent algorithm module 520 includes a decision tree construction submodule 521, a training submodule 522, and an evaluation submodule 523. According to other embodiments of the present disclosure, the device 500 may further include a data collection and capture module 530, and / or a query and management module 540.

[0087] The evaluation rule input and adjustment module 510 is used to set at least one evaluation rule, each evaluation rule is used to represent the mapping relationship between the performance behavior data of a position and a human resource evaluation index. In one embodiment, the evaluation rule input and adjustment module 510 can be used to perform operation S210, for example.

[0088] The decision tree construction submodule 521 is used to construct a decision tree based on each evaluation rule. In one embodiment, the decision tree construction submodule 521 can be used to perform operation S220.

[0089] The training submodule 522 is used to train a decision tree using the job performance data of the positions involved in the evaluation rules in the historical data as sample data and the human resource evaluation indicators involved in the evaluation rules in the historical data as labels of the sample data to obtain a human resource evaluation model. In one embodiment, the training submodule 522 can be used to perform operation S230.

[0090] The evaluation submodule 523 is used to evaluate the performance of the staff in the corresponding position on the corresponding human resource evaluation indicators using the human resource evaluation model. In one embodiment, the evaluation submodule 523 can be used to perform operation S240.

[0091] The data collection and capture module 530 is used to obtain the first performance behavior data of the first staff member based on the performance behavior data of the position involved in the evaluation rules corresponding to the human resource evaluation model. Accordingly, the evaluation submodule 523 is also used to process the first performance behavior data using the human resource evaluation model, and output the first indicator value of the first staff member on the human resource evaluation indicator corresponding to the human resource evaluation model. In one embodiment, the data collection and capture module 530 can be used to perform operation S401, and the evaluation submodule 523 can be used to perform operation S402 accordingly.

[0092] The query management module 540 is used to output the final value of the human resource evaluation index based on the adjustment or confirmation of the first index value by the management personnel. In one embodiment, the query management module 540 can be used to perform operation S403.

[0093] In addition, the training submodule 522 is also used to merge the first job performance behavior data into the sample data, and use the final value as the label of the first job performance behavior data to participate in the training of the decision tree.

[0094] According to an embodiment of the present disclosure, the device 500 can be used to implement reference Figure 2 to Figure 4 The described method is specifically described in the previous text and will not be repeated here.

[0095] According to an embodiment of the present disclosure, any multiple modules in the evaluation rule entry and adjustment module 510, the data analysis and intelligent algorithm module 520, the data acquisition and capture module 530 or the query and management module 540 can be combined in one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the evaluation rule entry and adjustment module 510, the data analysis and intelligent algorithm module 520, the data acquisition and capture module 530 or the query and management module 540 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in an appropriate combination of any of them. Alternatively, at least one of the evaluation rule entry and adjustment module 510, the data analysis and intelligent algorithm module 520, the data collection and capture module 530 or the query and management module 540 can be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is executed.

[0096] Figure 6 The following schematically shows a logical structure diagram of an apparatus 600 for human resources evaluation according to another embodiment of the present disclosure.

[0097] like Figure 6As shown, the logical structure of the device 600 for human resource evaluation can be divided into three parts: rule management, data processing, and information output. Among them, the evaluation rule input and adjustment module 610 and the query and management module 640 are used for rule management. The data collection and capture module 630 and the data analysis and intelligent algorithm module 620 are used for data processing. The work performance output module 650 is used for information output. The device 600 is a specific embodiment of the device 500, wherein the evaluation rule input and adjustment module 610, the data analysis and intelligent algorithm module 620, the data collection and capture module 630 and the query and management module 640 correspond to the specific embodiments of the evaluation rule input and adjustment module 510, the data analysis and intelligent algorithm module 520, the data collection and capture module 530 and the query and management module 540 respectively.

[0098] Table 2 describes in detail the input, output, and processing logic of each module in the device 600, wherein the human resource evaluation index is taken as a work contribution index as an example for illustration.

[0099]

[0100] Table 2 Detailed description of each module

[0101] The working process of the device 600 includes: the evaluation rule entry and adjustment module 640 determines the human resource evaluation rules, the data collection and capture module 630 obtains the original work contribution data, the data analysis and intelligent algorithm module 620 trains the human resource evaluation model and calculates the human resource evaluation indicators, and the work performance output module 650 outputs the work performance of the personnel.

[0102] The following is a review of the functions and processes of the device 600 based on an actual working example, so that the process of the device 600 can be more clearly seen.

[0103] The manager determines the work contribution index evaluation rule for a certain position in this period and calls the evaluation rule input and adjustment module 610 .

[0104] Obtaining the original data for calculating work contribution (i.e., job performance data), and calling the data collection and capture module 630;

[0105] The data analysis and intelligent algorithm module 620 is called to train the decision tree constructed based on the evaluation rules through the GBDT gradient enhancement decision tree according to historical data, and the human resource evaluation model obtained by training is used to calculate the human resource evaluation indicators of the company's external and internal employees.

[0106] Data analysis and intelligent algorithm module 620 This module can also realize the correction of model error ε (for example, see formula (1)); relying on the existing performance data, the overall model is corrected and modified.

[0107] Managers can query the calculation results in real time, and manually adjust and confirm the employee's work contribution and performance results according to the actual situation, calling the query and management module 640;

[0108] The device 600 outputs the annual or quarterly work performance of the personnel and calls the work performance output module 650 .

[0109] The following, in conjunction with Tables 1a to 1c, uses a typical example of how to evaluate the work contribution and salary cost of cross-departmental business architects within an enterprise to further illustrate the actual processing logic of each module in the device 600.

[0110] First, the human resources department decomposes the business architect's sub-goals (such as asset construction, asset application, original value output, and architecture implementation) according to the business architect's annual work goals and key work tasks. Each sub-goal has qualitative evaluation standards and quantitative indicator evaluation rules, and clearly defines the contribution ratio of qualitative and quantitative work. The human resources management personnel enter the rules in the evaluation rule entry and adjustment module 610. If the evaluation rules change during this work cycle, the evaluation rules can also be adjusted in the evaluation rule entry and adjustment module 610.

[0111] Then, according to the decomposed work subtasks, the device 600 interacts with the related work system through the API interface to obtain the original work contribution data (i.e., performance data) related to each subtask. For example, in the asset application work subtask, the data collection and capture module 630 obtains the data information of the business architect's approval of the business architecture analysis during project establishment, demand plan review, and demand handover by linking the business R&D management system; the data collection and capture module 630 automatically reminds the management personnel to conduct a qualitative evaluation of the business architect's asset application work and obtain real-time step-by-step evaluation data.

[0112] Then, the data analysis and intelligent algorithm module 620 extracts features and cleans the industry's general historical data and the company's human resources historical data (including job types, job sub-items, quantitative data for each job, and qualitative evaluation data for each job. The original historical data can be captured and classified according to human resources evaluation rules). The initial model established based on the evaluation rules is repeatedly trained and iteratively corrected through the GBDT gradient enhanced decision tree, and the accuracy rate is used as a standard to obtain the human resources evaluation model. Among them, when it is necessary to evaluate the work contribution and salary cost of the business architect separately, two decision trees can be trained through the data analysis and intelligent algorithm module 620. The two decision trees can share the input performance behavior data and can simultaneously display the work contribution and salary cost of the business architect to the human resources management personnel in one interface.

[0113] The device 600 can also analyze new raw data, and calculate and dynamically display the work contribution and salary cost evaluation of the business architect in real time based on the entered evaluation rules and combined with the latest human resource evaluation model.

[0114] In device 600, a decision tree is constructed according to the parameters set in the evaluation rules or the recommended parameters based on the work type, and the work contribution of each level is calculated through the GBDT algorithm. The parameters also support real-time adjustment and flexible matching by managers to achieve customized measurement of work contribution.

[0115] The output of the human resources evaluation model is adjusted and confirmed by the management personnel. For example, the device 600 can output the work contribution or salary cost of the business architect at the end of each quarter or the end of the year. The management personnel can review the evaluation rules set at the beginning of the cycle based on the performance distribution, and adjust the evaluation rules for the next cycle. At the same time, the work contribution and performance results of each cycle will be used as stock data, and the algorithm model will be continuously trained and corrected in combination with the adjustments made by the management personnel. For example, the number of manual adjustments made by the management personnel to the contribution of a certain job, the adjustment range, the type of work, etc. are all used as input factors for the training model to provide accuracy for the new algorithm model.

[0116] In this way, the device 600 can use real-time work contribution quantitative data and real-time step-by-step evaluation data (for example, qualitative evaluation data) to train and iterate the algorithm model of historical data through machine learning technology, thereby realizing real-time calculation of human resource contribution and / or salary cost, and can calculate the performance cost of external and internal personnel in real time in combination with work contribution and salary cost accounting mechanism. In this way, the work contribution and performance cost of personnel can be displayed in real time and dynamically, supporting managers to query performance calculation results in real time. At the end of the work cycle, it also supports the output of personnel's annual or quarterly work performance in combination with the traditional management evaluation system.

[0117] Therefore, the device 600 can be used as a performance evaluation tool for outsourced technical personnel and cross-departmental matrix management team members within the enterprise, no longer relying entirely on traditional human resource evaluation models such as manual evaluation and static quantitative statistics, thereby improving the human resource evaluation efficiency of large enterprises.

[0118] Figure 7 The block diagram schematically shows an electronic device suitable for implementing the method for human resource evaluation according to an embodiment of the present disclosure.

[0119] like Figure 7 As shown, the electronic device 700 according to an embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include an onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0120] In RAM 703, various programs and data required for the operation of electronic device 700 are stored. Processor 701, ROM 702 and RAM 703 are connected to each other via bus 704. Processor 701 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 702 and / or RAM 703. It should be noted that the program can also be stored in one or more memories other than ROM 702 and RAM 703. Processor 701 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0121] According to an embodiment of the present disclosure, the electronic device 700 may further include an input / output (I / O) interface 705, which is also connected to the bus 704. The electronic device 700 may further include one or more of the following components connected to the I / O interface 705: an input portion 706 including a keyboard, a mouse, etc.; an output portion 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 708 including a hard disk, etc.; and a communication portion 709 including a network interface card such as a LAN card, a modem, etc. The communication portion 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage portion 708 as needed.

[0122] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0123] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 702 and / or RAM 703 described above and / or one or more memories other than ROM 702 and RAM 703.

[0124] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the method provided by the embodiment of the present disclosure.

[0125] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 701. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0126] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 709, and / or installed from the removable medium 711. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0127] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the processor 701, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0128] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0129] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0130] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0131] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for human resource evaluation, comprising: Setting a plurality of evaluation rules, each of which is used to represent a mapping relationship between the performance behavior data of a position and a human resource evaluation indicator; Based on each of the evaluation rules, a decision tree is constructed; wherein different decision trees are constructed for different evaluation rules; For each decision tree, the performance behavior data of each person in the position involved in the evaluation rule corresponding to the decision tree in the historical data is used as a sample data, and the human resource evaluation index involved in the evaluation rule in the historical data is used as a label of the sample data to train the decision tree to obtain a human resource evaluation model; wherein the human resource evaluation index involved in the evaluation rule in the historical data includes the human resource evaluation index obtained by mapping the performance behavior data in the historical data according to the evaluation rule; and The human resource evaluation model is used to evaluate the performance of the staff in the corresponding positions on the corresponding human resource evaluation indicators.

2. The method according to claim 1, wherein: The setting of at least one evaluation rule comprises: When N evaluation rules are used to represent the mapping relationship between the performance behavior data of the same position and N human resource evaluation indicators, the performance behavior data in the N evaluation rules are set to be the same but the algorithms are different, where N is an integer greater than or equal to 2.

3. The method according to claim 2, wherein: The step of constructing a decision tree based on each of the evaluation rules comprises: N decision trees are constructed based on the N evaluation rules, wherein the N decision trees share input data.

4. The method according to claim 2, wherein: The N human resource evaluation indicators include a work contribution indicator and a salary cost indicator.

5. The method according to any one of claims 1 to 4, wherein The use of the human resource evaluation model to evaluate the performance of staff members in corresponding positions on corresponding human resource evaluation indicators includes: Based on the job performance data of the position involved in the evaluation rule corresponding to the human resource evaluation model, obtaining first job performance data of the first staff member; and The first job performance behavior data is processed using the human resource evaluation model to output a first indicator value of the first staff member on a corresponding human resource evaluation indicator.

6. The method according to claim 5, wherein: The use of the human resource evaluation model to evaluate the performance of staff members in corresponding positions on corresponding human resource evaluation indicators also includes: Based on the adjustment or confirmation of the first indicator value by the management personnel, the final value of the first staff member in the corresponding human resources evaluation indicator is output.

7. The method according to claim 6, wherein: The method further comprises: The first job performance behavior data is merged into the sample data, and the final value is used as a label of the first job performance behavior data to participate in the training of the decision tree.

8. A device for human resources evaluation, comprising: An evaluation rule input and adjustment module is used to set multiple evaluation rules, each of which is used to represent the mapping relationship between the performance behavior data of a position and a human resource evaluation indicator; Data analysis and intelligent algorithm modules, including: A decision tree construction submodule is used to construct a decision tree based on each of the evaluation rules; wherein different decision trees are constructed for different evaluation rules; A training submodule is used for training each decision tree by using the job performance data of the position involved in the evaluation rule corresponding to the decision tree in the historical data as sample data, and using the human resource evaluation index involved in the evaluation rule in the historical data as a label of the sample data, so as to obtain a human resource evaluation model; wherein the human resource evaluation index involved in the evaluation rule in the historical data includes the human resource evaluation index obtained by mapping the job performance data in the historical data according to the evaluation rule; The evaluation submodule is used to evaluate the performance of the staff in the corresponding position on the corresponding human resource evaluation indicators using the human resource evaluation model.

9. An electronic device, comprising: one or more processors; one or more memories for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images