Employee behavior data evaluation method and system and storage medium

Abstract

The invention relates to an employee behavior data evaluation method and system and a storage medium. The method comprises the steps of determining a target node of a target employee in an employee graph through a constructed employee graph and a behavior evaluation model, and accurately positioning associated information of the employee. The mode of performing feature processing on the adjacent node sets is adopted, so that the target employees are comprehensively considered through the adjacent node sets, more detailed and more accurate target node features of the target employees are ensured to be obtained, and after evaluation is performed in combination with historical information, the evaluation accuracy is improved, and the evaluation efficiency is improved. And office efficiency intelligent analysis can be carried out on employee behaviors more accurately in real time.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an employee behavior data evaluation method, system, and storage medium. Background Art

[0002] As companies increasingly prioritize employee performance management and improving office efficiency, employee behavior assessment systems are becoming a crucial management tool. By collecting and analyzing employee behavior data, they help companies better understand their employees' work status, thereby improving work efficiency and optimizing human resource allocation.

[0003] Currently, there are some mature employee behavior analysis systems on the market, such as the Insight Eye MIT system, which can collect real-time data on employee work hours, work content, work efficiency, and other data, and provide companies with comprehensive employee behavior analysis reports through intelligent analysis. However, there are still some technical problems and challenges at the technical level. First, existing behavior assessment technologies are mostly post-analysis, lacking real-time performance and unable to be linked to employees' historical behavior. Second, current behavior assessment models mainly rely on limited evaluation indicators and cannot integrate heterogeneous data from different sources such as internal company, social networks, and the web. This makes it difficult to meet the specific needs of different companies and different positions and it is difficult to fully reflect the behavioral characteristics of employees. Summary of the Invention

[0004] Based on this, in order to address the shortcomings of existing employee behavior analysis systems in terms of real-time performance and comprehensiveness of evaluation indicators, the present application provides an intelligent employee behavior data evaluation method, system, computer device and storage medium.

[0005] In a first aspect, the present application provides a method for evaluating employee behavior data. The method comprises:

[0006] Determining a target employee and an employee map associated at the first time; the employee map includes a target node corresponding to the target employee;

[0007] Determining a plurality of adjacent node sets adjacent to the target node and located at different levels, and performing feature processing on the plurality of adjacent node sets to obtain a target node feature of the target node;

[0008] Evaluate the target employee in the second time through the behavioral assessment model and output historical information;

[0009] A behavior evaluation result of the target employee is obtained according to the target node characteristics and the historical information.

[0010] In one embodiment, determining a target employee and an employee graph associated at a first time includes: obtaining a plurality of initial nodes; the initial nodes include a project directory and attribute data; the project directory includes at least employee items, equipment items, task items, and tool items; the attribute data includes at least equipment status data, employee efficiency indicators, and office task data; determining the association relationship between each of the initial nodes, and associating the initial nodes through edges to obtain an initial graph; and extracting an employee graph corresponding to the target employee that is valid at the first time from the initial graph.

[0011] In one embodiment, feature processing is performed on multiple adjacent node sets to obtain target node features of the target node, including: determining the current level and the previous level of the target node in the employee graph; determining the first historical feature of the target node at the previous level and the second historical feature corresponding to the adjacent node set; and obtaining the target node features of the target node based on the first historical feature and the second historical feature.

[0012] In one embodiment, the target node feature of the target node is obtained based on the first historical feature and the second historical feature, including: performing mean processing on the first historical feature and the second historical feature to obtain the mean feature; obtaining the historical weight corresponding to the previous level; associating the mean feature and the historical weight to obtain the candidate node feature of the target node at the current level; and iterating in a loop until the candidate node feature at the last level is used as the target node feature of the target node.

[0013] In one embodiment, the target node characteristics of the target node are obtained based on the first historical characteristics and the second historical characteristics, including: extracting multiple first sub-features of different feature types from the first historical characteristics, and extracting multiple second sub-features of different feature types from the second historical characteristics; the feature types include at least energy value, work ability, work willingness, and concentration; performing initial aggregation processing on the first sub-features and the second sub-features of the same feature type respectively to obtain multiple third sub-features; performing target aggregation processing on the multiple third sub-features to obtain the target node characteristics of the target node.

[0014] In one embodiment, the above method also includes: identifying existing target tool items from the employee graph; the target tool items include applications used by employees; determining multiple privacy interfaces and log information when the application is running; and performing privacy interface call detection on each of the log information to obtain the target employee's usage results of the application.

[0015] In one embodiment, the above method also includes: determining the task map associated at the first time and the corresponding multiple associated employees; extracting the office task data of each associated employee in the task map; the office task data at least includes work input and years of employment; and based on the office task data, displaying the obtained task evaluation results in a differentiated manner.

[0016] In a second aspect, the present application also provides an employee behavior data evaluation system. The system includes:

[0017] An employee map determination module is used to determine a target employee and an employee map associated at the first time; the employee map includes a target node corresponding to the target employee;

[0018] a node feature determination module, configured to determine a plurality of adjacent node sets adjacent to the target node and located at different levels, and perform feature processing on the plurality of adjacent node sets to obtain a target node feature of the target node;

[0019] A historical information determination module is used to evaluate the target employee in the second time through a behavior evaluation model and output historical information;

[0020] The evaluation result determination module is used to obtain the behavior evaluation result of the target employee according to the target node characteristics and the historical information.

[0021] In a third aspect, 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 above steps of employee behavior data evaluation when executing the computer program.

[0022] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above steps of employee behavior data evaluation.

[0023] The employee behavior data assessment method, system, computer device, and storage medium described above, through the constructed employee graph and behavior assessment model, can determine the target node of the target employee in the employee graph, accurately locate the employee's associated information, and lay the foundation for the subsequent comprehensive assessment of employee behavior. By employing feature processing of adjacent node sets, a comprehensive consideration of the target employee is achieved through adjacent node sets, ensuring more detailed and accurate target node features for the target employee. Furthermore, when combined with historical information for evaluation, not only does this improve the accuracy of the assessment, but it also enables more accurate and real-time intelligent analysis of employee behavior for office efficiency. Therefore, it helps optimize human resource management, improve team collaboration efficiency, and ultimately promote the overall development of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a diagram of an application environment of an employee behavior data evaluation method in one embodiment;

[0025] Figure 2 1 is a flow chart of a method for evaluating employee behavior data in one embodiment;

[0026] Figure 3 A schematic diagram of the structure of an initial map in one embodiment;

[0027] Figure 4 Schematic diagram of a behavior evaluation model in one embodiment;

[0028] Figure 5 A schematic diagram of a process for determining target node characteristics in one embodiment;

[0029] Figure 6 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0031] The employee behavior data evaluation method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 via a network. The server 104 is used to determine the target employee and employee map associated at the first time, determine multiple adjacent node sets adjacent to the target node and located at different levels, and perform feature processing on the multiple adjacent node sets to obtain the target node features of the target node. The server 104 is also used to evaluate the target employee at the second time using a behavior evaluation model, output historical information, and obtain the target employee's behavior evaluation results based on the target node features and historical information, and finally return the behavior evaluation results to the terminal 102 for display.

[0032] The terminal 102 may be, but is not limited to, various personal computers, laptops, smartphones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers. It may be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0033] In one embodiment, Figure 2 As shown in the figure, a method for evaluating employee behavior data is provided. Figure 1 The computer device in the example is used to illustrate, the computer device can be Figure 1 The terminal or server in the embodiment includes the following steps:

[0034] Step 202: Determine the target employee and employee map associated for the first time.

[0035] Among them, the employee map includes target nodes corresponding to target employees; the first time may be the current time when the enterprise needs to conduct intelligent analysis of the office efficiency of the target employees.

[0036] Specifically, if Figure 3 As shown, Figure 3 The computer device obtains the pre-associated initial graph and determines the target node to which the target employee belongs in the initial graph, for example Figure 3 Since the edges between each node carry multiple data features, the computer device can extract the edges associated with the attribute data of the target node that are associated at the first time, and obtain the employee map centered on the target node. Figure 3 An employee map composed of arrow-shaped edges.

[0037] In one embodiment, determining a target employee and an employee graph associated at a first time includes: obtaining a plurality of initial nodes; determining an association relationship between each initial node, and associating the initial nodes through edges to obtain an initial graph; and extracting an employee graph corresponding to the target employee that is valid at the first time from the initial graph.

[0038] Among them, Figure 3As shown, the initial graph includes multiple initial nodes and multiple connecting edges; the initial nodes include multiple project directories and the attribute data corresponding to each project directory; the project directory includes at least employee items, equipment items, task items, and tool items; and the attribute data includes at least equipment status data, employee efficiency indicators, and office task data. As can be easily understood, attribute data is heterogeneous data from various sources such as within the company, social networks, and the web, and can be adjusted to the specific needs of different companies and different positions. Therefore, when the computer device responds to the user's trigger operation, the project directory and corresponding attribute data are created and modified according to actual needs, providing data integration and optimization support for intelligent enterprise decision-making.

[0039] Edges represent the relationships between nodes, and the corresponding data features include at least the validity period of the relationship, the rank relationship, the equipment usage relationship, and whether the person is the task leader. For example, when the two initial nodes of a connection are an employee item and a equipment item, the corresponding data feature of the edge is equipment usage. When the two initial nodes of a connection are an employee item and a task item, the corresponding data features of the edge are, for example, whether the person is the task leader, the frequency of task communication, and the communication tools used.

[0040] Step 204 : determining a plurality of adjacent node sets adjacent to the target node and located at different levels, and performing feature processing on the plurality of adjacent node sets to obtain a target node feature of the target node.

[0041] Specifically, the computer device can determine different levels through the nodes that are directly or indirectly connected to the target node. Figure 3 As shown, the target node includes two hierarchical levels of adjacent node sets, with each level corresponding to an adjacent node set, and the adjacent node set includes multiple adjacent nodes. For example, the adjacent node set of the first level includes nodes 2, 4, and 5, and the adjacent node set of the second level includes nodes 8, 9, and so on. The computer device performs feature processing on the adjacent node sets of different levels to determine the candidate node features of the target node at different levels. When feature processing is an iterative process, the candidate node features of the last level can be used as the target node features of the target node in the employee map.

[0042] Step 206: Evaluate the target employee at a second time using the behavior evaluation model and output historical information.

[0043] The second time is a historical time earlier than the first time, and may also have a periodic interval. For example, when employee assessment is conducted on a quarterly basis, the end of each quarter may be selected to conduct employee behavior data assessment.

[0044] Specifically, the behavior evaluation model is determined by the target node features corresponding to different historical times in the memory storage module, that is, the behavior evaluation model is trained by the target node features corresponding to different historical times, such as Figure 4 As shown, Figure 4 This is a schematic diagram of a behavior assessment model. Since the behavior assessment model can be considered trained at this point, the computer device can directly access the trained behavior assessment model. When the behavior assessment model is a recurrent neural network model, which typically includes an input layer, a hidden layer, and an output layer, historical information about the hidden layer in the behavior assessment model can be determined.

[0045] Step 208: Obtain the behavior evaluation result of the target employee based on the target node characteristics and historical information.

[0046] Specifically, the computer device determines the target information within the first time period through the behavior evaluation model and according to the target node characteristics and historical information, and then evaluates the employee behavior data of the target employee within the first time period based on the target information to obtain the employee behavior data evaluation result. Figure 4 As shown, when t represents the first time, m (t) Indicates the target node feature corresponding to the first time, m (t-1) The target node feature corresponding to the second time is represented. When the computer device inputs the target node feature corresponding to the first time into the input layer, the target information at the first time is determined in the following manner:

[0047] h (t) =σ(Um (t) +Wh (t-1) +b

[0048] Among them, h (t) is the target information of the hidden layer in the first time period; U and W are the weight parameters in the behavior evaluation model, obtained through the process of training the behavior evaluation model; b is the bias constant. The computer device evaluates the employee behavior data of the target employee in the first time period in the following ways:

[0049] o (t) =Vh (t) +c

[0050] y (t) =σ(o (t) )

[0051] Among them, (t) represents the predicted output feature of the output layer of the behavior evaluation model in the first time; V is the weight parameter in the behavior evaluation model; c is the bias constant; σ is the preset activation function; y (t) Indicates the behavioral assessment results of the target employee.

[0052] In the aforementioned employee behavior data assessment method, the constructed employee graph and behavior assessment model can determine the target node of the target employee within the employee graph, accurately locating the employee's associated information and laying the foundation for a comprehensive assessment of employee behavior. By applying feature processing to adjacent node sets, a comprehensive consideration of the target employee is achieved through adjacent node sets, ensuring more detailed and accurate target node features for the target employee. Furthermore, when combined with historical information for evaluation, this not only improves assessment accuracy but also more accurately and realistically reflects changes in employee behavior.

[0053] In one embodiment, Figure 5 As shown, feature processing is performed on multiple adjacent node sets to obtain the target node feature of the target node, including the following process:

[0054] Step 502: Determine the current level and previous level of the target node in the employee graph.

[0055] Among them, when the employee map includes multiple levels, the previous level can be regarded as the first level, and the current level is the second level.

[0056] Step 504: Determine the first historical feature of the target node at the previous level and the second historical feature corresponding to the set of adjacent nodes.

[0057] Among them, the first historical feature of the target node and the second historical feature corresponding to each adjacent node are the equipment status data, employee efficiency indicators and office task data mentioned in the above embodiments. The office equipment status data includes equipment type, equipment status, equipment usage frequency and equipment usage time; employee behavior data includes office task completion time, communication record frequency, employee overtime and office task completion rate; office task parameter data includes office task type, office task importance level and office task complexity, etc.

[0058] Specifically, since the first historical feature and the second historical feature are usually high-dimensional data. Therefore, when the previous level is a hierarchical level, the computer device needs to encode the first historical feature through a preset encoder, that is, map the original high-dimensional data to a low-dimensional dense vector space, and then obtain the first historical feature of the target node at a hierarchical level. Among them, when the level of the target node represents a query depth k, the first historical feature can also be called the node representation of the target node at the previous query depth, that is, Where v represents the target node.

[0059] Similarly, the computer device maps the second historical features corresponding to each adjacent node to obtain the sub-historical features corresponding to each adjacent node, that is, the sub-historical features can also be called the node representation of the adjacent node at the previous query depth. Where u represents an adjacent node. The computer device integrates multiple sub-historical features to obtain the second historical feature corresponding to the adjacent node set of the previous level. For example, the second historical feature is When , N(v) represents the set of adjacent nodes corresponding to the previous level.

[0060] In one embodiment, the To represent the employee graph, t represents the employee graph corresponding to different time periods, T represents the total number of the first and second time periods, and v t Represents the node set of the employee graph, ε t The set of edges representing the employee graph.

[0061] Step 506: Obtain a target node feature of the target node according to the first historical feature and the second historical feature.

[0062] In one embodiment, a target node feature of a target node is obtained based on a first historical feature and a second historical feature, including: performing mean processing on the first historical feature and the second historical feature to obtain a mean feature; obtaining a historical weight corresponding to the previous level; associating the mean feature and the historical weight to obtain a candidate node feature of the target node at the current level; and iterating in a loop until the candidate node feature at the last level is used as the target node feature of the target node.

[0063] Specifically, the computer device may perform feature processing on the first historical feature and the second historical feature using a preset mean function in the following manner:

[0064]

[0065] Among them, Mean represents the preset mean function, U represents the process of averaging the first historical feature and the second historical feature, and σ is the preset activation function. Since feature processing is an iterative process, the parameters will be updated during the training of the feature processing model in each iteration. The historical weight of the previous level is the weight parameter obtained after the feature processing model was trained in the previous iteration. The computer device associates the mean feature with the historical weight, and through the activation function, determines the candidate node feature of the target node at the current level, that is, the node representation of the target node at the current query depth.

[0066] Next, the computer device takes the current level as the new previous level and the candidate node feature as the new first historical feature, and returns to the step of determining the first historical feature of the target node at the previous level and the second historical feature corresponding to the set of adjacent nodes at the previous level, until the candidate node feature of the target node at the last level among multiple levels is obtained.

[0067] It is easy to understand that when the query depth k changes, the node representation of the target node at the previous query depth is Node representation of the adjacent nodes at the previous query depth Therefore, the computer device needs to continuously use the current level as the new previous level to enter the next round of feature processing iteration. When all levels are iterated, the target node feature of the target node can be obtained.

[0068] In this embodiment, the target node features are determined by using adjacent node sets for feature processing. This allows for comprehensive consideration of the target employee's historical information through adjacent node sets, ensuring a more detailed and accurate target node feature for the target employee. Furthermore, when the employee graph changes, only the new nodes are re-processed, ensuring scalability. Furthermore, since the resulting target node features are low-dimensional, dense feature vectors, the efficiency of subsequent evaluations at different times is improved.

[0069] Therefore, this application can accurately mine the characteristics of the target node in the employee map. Clarifying the current level and the previous level of the target node will help understand its position in the organizational structure. Obtaining the first historical feature under the previous level and the second historical feature corresponding to the set of adjacent nodes of the neighbor node can comprehensively consider the target node's own development trajectory and the influence of surrounding related personnel. The target node characteristics thus obtained can more comprehensively and accurately characterize the target node, provide a strong basis for human resource management, employee evaluation, team collaboration optimization, etc., and help enterprises better tap the potential of employees and improve organizational effectiveness.

[0070] In one embodiment, feature processing is performed on the first historical feature and the second historical feature, that is, a process of splicing vectors in a low-dimensional dense vector space.

[0071] In one embodiment, a target node feature of a target node is obtained based on the first historical feature and the second historical feature, including: extracting multiple first sub-features of different feature types from the first historical feature, and extracting multiple second sub-features of different feature types from the second historical feature; performing initial aggregation processing on the first sub-features and the second sub-features of the same feature type to obtain multiple third sub-features; and performing target aggregation processing on the multiple third sub-features to obtain the target node feature of the target node.

[0072] Other,characteristic types include at least energy value, work ability, work willingness, and concentration.

[0073] Specifically, the computer device extracts multiple first sub-features of different feature types from the first historical feature, and extracts multiple second sub-features of different feature types from the second historical feature. The data corresponding to the first sub-features and the second sub-features obtained at this time may not be the same. Therefore, for the same feature type of the two, the computer device performs initial aggregation processing on the corresponding ones to obtain multiple third sub-features. The initial aggregation processing at this time represents the process of grouping and counting the data, such as multi-dimensional aggregation, aggregation by category, aggregation by time, etc. For the first sub-features or second sub-features of the remaining feature types, the computer device directly performs target aggregation processing on them with multiple third sub-features to obtain the target node features of the target node. The target aggregation processing at this time represents the process of data feature fusion, such as weighted fusion, feature splicing, neural network-based fusion, etc.

[0074] Therefore, feature extraction of different feature types ensures the comprehensiveness and diversity of information, and also provides a more comprehensive and accurate basis for subsequent tasks such as employee performance evaluation and task allocation.

[0075] In one embodiment, the above method also includes: identifying existing target tool items from the employee map; determining multiple privacy interfaces and log information when the application is running; and performing privacy interface call detection on each log information to obtain the target employee's usage results of the application.

[0076] Among them, the target tool items include applications used by employees. Applications generally refer to various web pages, software, enterprise system platforms, etc., and this application does not limit them here. An application usually includes multiple interfaces, and there may be privacy interfaces involving sensitive information calls in multiple interfaces. Privacy interface call detection is to detect the information recorded in the log information, for example, detecting the start and end time of different stages of the privacy interface, the stability and correctness of the privacy interface, the number of calls of the privacy interface within a preset time period, etc., to determine whether employees are using blacklist software for office work, or the efficiency of completing work through whitelist software, etc.

[0077] Specifically, for the target tool items identified from the employee graph, the computer device scans the code and code comments written in various languages involved in running the application, identifying multiple privacy interfaces with special identifiers. Since the application may encounter various situations during operation, such as debugging information, warnings, and errors, an embedded logging program can record the calls to various application interfaces, accurately locating the problem based on the recorded information and generating log information.

[0078] The computer device obtains a pre-set privacy interface call rule table, which records the maximum permissible call information for different privacy interfaces. For example, the maximum permissible call frequency for a privacy interface is 10 times per second. When the computer device performs real-time interface call detection on the log information and obtains initial results corresponding to the privacy interfaces, it compares the initial results with the privacy interface call rule table to obtain the detection results corresponding to each privacy interface. By combining the detection results corresponding to each privacy interface, the target employee's application usage results can be obtained. For example, if the initial detection result does not match the call information recorded in the privacy interface call rule table, the detection result for that privacy interface is an illegal call.

[0079] In this embodiment, identifying the applications used by employees from their employee graph allows for precise locating of employee behavior and effective monitoring of their actions. By identifying multiple privacy interfaces and log information during application runtime and performing privacy interface call detection on each log message, potential privacy compliance issues within the application can be promptly identified, mitigating the risk of privacy breaches within the enterprise.

[0080] In one embodiment, the above method includes: determining a task map associated at the first time and a corresponding plurality of associated employees; extracting office task data of each associated employee in the task map; and displaying the obtained task evaluation results according to the office task data.

[0081] Among them, office task data at least includes work input and years of employment.

[0082] Specifically, in addition to extracting an employee graph centered around the target node from the initial graph, the computer device can also extract different types of graphs based on the different project directories of the initial node. When a user triggers the initial node of a task item, the corresponding task graph is extracted with this node as the center. As can be easily understood, the task graph now includes multiple nodes associated with employees, as well as edges associated with the attribute data of the nodes associated with the employees at the first time.

[0083] Therefore, the computer device can extract attribute data, including office task data, for each associated employee from the task map, and then directly evaluate multiple associated employees within the first time period based on the attribute data to obtain task evaluation results, and then display the task evaluation results for each associated employee separately. The process of evaluating multiple associated employees within the first time period based on the attribute data to obtain task evaluation results can be seen in the specific process of evaluating employee behavior data of the target employee within the first time period based on the target information in step 208, and will not be further described in this embodiment.

[0084] In this embodiment, by identifying associated task graphs and employees, extracting and analyzing their office task data, we can accurately assess task completion and provide personalized feedback. Furthermore, based on the project records at different nodes, we can flexibly extract different types of graphs, enabling analysis and evaluation of employee behavior from different levels, enriching the evaluation dimensions.

[0085] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0086] Based on the same inventive concept, embodiments of the present application also provide an employee behavior data assessment device for implementing the aforementioned employee behavior data assessment method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more employee behavior data assessment device embodiments provided below can be found in the aforementioned limitations of the employee behavior data assessment method and will not be further elaborated here.

[0087] In one embodiment, an employee behavior data evaluation system is provided, comprising: an employee graph determination module, a node feature determination module, a historical information determination module, and an evaluation result determination module, wherein:

[0088] The employee map determination module is used to determine the target employee and employee map that are associated for the first time; the employee map includes the target node corresponding to the target employee.

[0089] The node feature determination module is used to determine multiple adjacent node sets adjacent to the target node and located at different levels, and perform feature processing on the multiple adjacent node sets to obtain the target node feature of the target node.

[0090] The historical information determination module is used to evaluate the target employee in the second time through the behavior evaluation model and output historical information.

[0091] The evaluation result determination module is used to obtain the behavior evaluation results of the target employee based on the target node characteristics and historical information.

[0092] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for converting speech timbre is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0093] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0094] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0095] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above-mentioned method embodiments when executed by a processor.

[0096] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, etc., but are not limited to these.

[0097] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0098] The above embodiments merely illustrate several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for evaluating employee behavior data, characterized in that: The method comprises: Determining a target employee and an employee map associated at the first time; the employee map includes a target node corresponding to the target employee; Determining a plurality of adjacent node sets adjacent to the target node and located at different levels, and performing feature processing on the plurality of adjacent node sets to obtain a target node feature of the target node; Evaluate the target employee in the second time through the behavioral assessment model and output historical information; A behavior evaluation result of the target employee is obtained according to the target node characteristics and the historical information.

2. The method according to claim 1, characterized in that The determining of the target employee and employee map associated at the first time includes: Acquire multiple initial nodes; the initial nodes include a project directory and attribute data; the project directory includes at least employee items, equipment items, task items, and tool items; the attribute data includes at least equipment status data, employee efficiency indicators, and office task data; Determine the association relationship between each of the initial nodes, and associate the initial nodes through edges to obtain an initial graph; An employee graph corresponding to the target employee that is valid within the first time is extracted from the initial graph.

3. The method according to claim 1, characterized in that The performing feature processing on the plurality of adjacent node sets to obtain the target node feature of the target node includes: Determine the current level and previous level of the target node in the employee graph; Determine a first historical feature of the target node at the previous level and a second historical feature corresponding to the set of adjacent nodes; A target node feature of the target node is obtained according to the first historical feature and the second historical feature.

4. The method according to claim 3, characterized in that The obtaining, according to the first historical feature and the second historical feature, a target node feature of the target node includes: Performing mean processing on the first historical feature and the second historical feature to obtain a mean feature; Obtain the historical weight corresponding to the previous level; Associating the mean feature with the historical weight to obtain candidate node features of the target node at the current level; The process is iterated in a loop until the candidate node feature at the last level is used as the target node feature of the target node.

5. The method according to claim 3, characterized in that The obtaining the target node feature of the target node according to the first historical feature and the second historical feature further includes: Extracting a plurality of first sub-features of different feature types from the first historical feature, and extracting a plurality of second sub-features of different feature types from the second historical feature; the feature types include at least energy value, work ability, work willingness, and concentration; Performing initial aggregation processing on the first sub-features and the second sub-features of the same feature type respectively to obtain multiple third sub-features; Target aggregation processing is performed on the multiple third sub-features to obtain a target node feature of the target node.

6. The method according to any one of claims 1 to 5, characterized in that Also includes: Identifying existing target tool items from the employee graph; the target tool items include applications used by the employee; Determine multiple privacy interfaces and log information when the application is running; A privacy interface call detection is performed on each log information to obtain the target employee's usage result of the application.

7. The method according to claim 1, characterized in that The method further comprises: Determine the first-time associated task map and the corresponding multiple associated employees; Extracting office task data of each associated employee in the task map; the office task data at least includes work input and years of employment; According to the office task data, the obtained task evaluation results are displayed separately.

8. An employee behavior data evaluation system, characterized in that: The system comprises: An employee map determination module is used to determine a target employee and an employee map associated at the first time; the employee map includes a target node corresponding to the target employee; a node feature determination module, configured to determine a plurality of adjacent node sets adjacent to the target node and located at different levels, and perform feature processing on the plurality of adjacent node sets to obtain a target node feature of the target node; A historical information determination module is used to evaluate the target employee in the second time through a behavior evaluation model and output historical information; The evaluation result determination module is used to obtain the behavior evaluation result of the target employee according to the target node characteristics and the historical information.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images